diff --git a/docs/Admin-and-data/Billing/Cloud/overview.md b/docs/Admin-and-data/Billing/Cloud/overview.md index 1b009997..6b30f544 100644 --- a/docs/Admin-and-data/Billing/Cloud/overview.md +++ b/docs/Admin-and-data/Billing/Cloud/overview.md @@ -62,7 +62,7 @@ The total cost depends on the number of Ultimate and Developer seats selected. O The Developer edition is not licensed for production use. !!! info "Learn more" - [FusionReactor licensing](https://docs.fusionreactor.io/Admin-and-data/Licensing/Licensing/) + [FusionReactor licensing](../../Licensing/Licensing.md) ### Starter @@ -106,7 +106,7 @@ Need a large number of seats or a tailored plan? Contact our Sales Team for cust **OpsPilot AI** is an advanced observability solution that leverages generative AI to provide powerful insights into the performance of your applications. Using OpsPilot AI tokens enables you to identify and resolve issues before they occur, optimize the performance of your applications, and reduce downtime. !!! info "Learn more" - [OpsPilot](/Data-insights/Features/OpsPilot/AIoverview/) + [OpsPilot Coworker](/Data-insights/Features/OpsPilot/Coworker/overview/) !!! warning @@ -128,7 +128,7 @@ A seat covers a single unique virtual or physical host with up to 4 instances of It is possible to be billed fully on-demand with no seat reservation required. !!! info "Learn more" - [FusionReactor Ultimate](https://docs.fusionreactor.io/Admin-and-data/Billing/Cloud/overview/#fusionreactor-ultimate) + [FusionReactor Ultimate](#fusionreactor-ultimate) diff --git a/docs/Data-insights/Features/Integrations/Chat/opspilot-mcp.md b/docs/Data-insights/Features/Integrations/Chat/opspilot-mcp.md index 444ae49a..dab428d4 100644 --- a/docs/Data-insights/Features/Integrations/Chat/opspilot-mcp.md +++ b/docs/Data-insights/Features/Integrations/Chat/opspilot-mcp.md @@ -2,7 +2,7 @@ Let AI assistants query OpsPilot over the Model Context Protocol (MCP). -OpsPilot MCP brings OpsPilot to where your team already works. An AI assistant there can work with your telemetry and situations the way the OpsPilot coworker does, so you can ask without switching tools. +OpsPilot MCP brings OpsPilot to where your team already works. An AI assistant there can work with your telemetry and situations the way OpsPilot Coworker does, so you can ask without switching tools. Navigate to **Integrations** from the left-hand sidebar, then select **OpsPilot MCP**. @@ -10,7 +10,7 @@ Navigate to **Integrations** from the left-hand sidebar, then select **OpsPilot ## What assistants can do -Once connected, an assistant can read your **dashboards**, **metrics**, **logs**, **traces**, and the **situations** your coworker is tracking - and, depending on the permission tier, act on them. +Once connected, an assistant can read your **dashboards**, **metrics**, **logs**, **traces**, and the **situations** your Coworker is tracking - and, depending on the permission tier, act on them. Each person connects their own assistant and signs in as themselves, so there is no key to paste and everyone sees what they can already see in OpsPilot. diff --git a/docs/Data-insights/Features/Integrations/Chat/slack.md b/docs/Data-insights/Features/Integrations/Chat/slack.md index 8ad39705..3f9ed1eb 100644 --- a/docs/Data-insights/Features/Integrations/Chat/slack.md +++ b/docs/Data-insights/Features/Integrations/Chat/slack.md @@ -2,7 +2,7 @@ Talk to OpsPilot from Slack - mention it in a channel or DM it directly. -The Slack integration brings OpsPilot to where your team already talks. Invite the bot to a channel and switch posting on, and the alerts, situations, and digests the coworker surfaces land there as they happen. Mention it there or message it directly and you get the same coworker you use in the app, so you can ask about what it just posted without switching tools. +The Slack integration brings OpsPilot to where your team already talks. Invite the bot to a channel and switch posting on, and the alerts, situations, and digests Coworker surfaces land there as they happen. Mention it there or message it directly and you get the same Coworker you use in the app, so you can ask about what it just posted without switching tools. DMs are personal: each person links their own account. @@ -58,6 +58,9 @@ OpsPilot introduces itself and waits. Situation posting is off until someone tur Situations at **warning** severity or above then land in that channel. +!!! tip "Filtering to critical won't hide an escalation" + If you narrow a channel to critical only, a situation that is *later* raised to critical is still posted at that point, even though its earlier severity was filtered out. Escalations always notify, so you won't miss something that becomes serious after it was first raised. + --- ## Connecting your own account @@ -70,12 +73,21 @@ Channel mentions need no linking - only DMs. ## What OpsPilot reads -OpsPilot only reads messages that mention it. Background reading is off in every channel until someone turns it on: +Background reading is off in every channel until someone turns it on, so by default OpsPilot is not watching your conversations. Two things reach it: + +- **When you @-mention OpsPilot**, it reads the recent message history in that channel so it understands what you are asking about. It stores only your message - not the surrounding messages it used as context. +- **When you reply in the thread of a situation it posted**, those replies become context for its next check-up on that situation. OpsPilot says so explicitly in the thread each time. + +Nothing else in your Slack is read. + +Turning on listening changes that deliberately - every message in the channel is then sent to OpsPilot, both as context for investigations and to learn from: ``` /opspilot listen passive ``` +In **active** mode it goes further, investigating things it can help with and replying on its own. + `/opspilot status` shows where a channel stands, and `/opspilot listen off` stops it again. --- diff --git a/docs/Data-insights/Features/OpsPilot/AIoverview.md b/docs/Data-insights/Features/OpsPilot/AIoverview.md deleted file mode 100644 index 8f5f51db..00000000 --- a/docs/Data-insights/Features/OpsPilot/AIoverview.md +++ /dev/null @@ -1,93 +0,0 @@ -# OpsPilot AI Platform - -
- -OpsPilot is an AI-powered observability and autonomous reliability platform. It gives your team an AI SRE teammate that continuously monitors your systems, investigates issues, and helps prevent, detect, and resolve disruptions before they impact your customers - so your engineers spend less time firefighting and more time building. - -Built on FusionReactor’s telemetry platform and powered by advanced AI reasoning, OpsPilot combines deep observability with agentic AI - correlating metrics, logs, and traces, investigating root causes, and surfacing prioritised, actionable findings across your entire environment. - -From scheduled background investigations and real-time alert analysis to conversational queries and autonomous remediation guidance, OpsPilot works as an operational partner - not just a monitoring tool. - -!!! info "Learn more" - [OpsPilot user guide](/Data-insights/Features/OpsPilot/OpsPilot-user-guide/) - -## What’s new in OpsPilot - -The latest version of OpsPilot introduces a suite of advanced capabilities designed to enhance your observability and reasoning experience: - -- **AI reasoning engine** – Understands complex system behavior and delivers context-rich explanations in plain language. - -- **Code analysis & logic review** – Detects bugs, logic errors, and refactoring opportunities directly from your code. - -- **Memory diagnostics** – Investigates heap and non-heap usage, identifies anomalies, and recommends performance optimizations. - -- **External knowledge & patch lookup** – Retrieves the latest version, patch, and release information from trusted sources. - -- **Grafana & Telemetry integration** – Correlates metrics with real-time data for deeper insights into system health. - -- **Actionable recommendations** – Prioritizes fixes and next steps to help you focus on what matters most. - -- **Seamless integrations** – Works with Microsoft Teams, Jira, and Slack - and can automatically create tickets to accelerate issue resolution. - -- **OpsPilot Vision** – Allows you to upload screenshots from FusionReactor, Grafana, or similar tools for instant, readable insights. - -## Ways to interact with OpsPilot - -### Ask OpsPilot questions - -Engage with OpsPilot anytime through the interactive chat interface. Simply select **New Chat**, type your question, and receive an instant, clear response. - -**OpsPilot can:** - -- Convert natural language into system or data queries. - -- Identify anomalies and correlate causes. - -- Analyze code and suggest improvements. - -- Review logs, stack traces, and exceptions. - -- Generate meaningful charts and visualizations. - -- Retrieve external patch, release, and version data. - -**OpsPilot communicates naturally - so you can ask things like:** - -- “What’s causing memory spikes in the last hour?” -- “Show me slow transaction trends this week.” -- “Review this code and highlight potential issues.” -- “What’s the latest patch version for ColdFusion 2025?” - -And OpsPilot will respond with structured, easy-to-understand answers - plus recommended actions you can take immediately. - -### Intuitive integration points - -OpsPilot is built directly into the FusionReactor UI, offering contextual insights where they’re most useful. Whether you’re viewing traces, metrics, logs, or code, OpsPilot is right there to explain what’s happening - and why. - -With external integration support, OpsPilot also connects to Microsoft Teams, Jira, and Slack, allowing seamless collaboration and automatic ticket creation from within your observability workflow. - - -## Benefits of using OpsPilot - -- **Reduced MTTR** – Agentic investigation and real-time reasoning dramatically cut the time from alert to resolution. - -- **Proactive reliability** – Continuous autonomous monitoring detects and surfaces issues before they reach your customers, protecting uptime and revenue. - -- **Operational resilience** – Automated investigations run 24/7, ensuring nothing is missed even outside business hours. - -- **Human-Friendly insights** – Get complex technical explanations in plain language, ready to share with your team. - -- **Increased productivity** – Spend less time digging through logs and more time building. - -- **Collaboration ready** – Share insights, tickets, and actions across Teams, Jira, or Slack with a single step. - -- **Continuous availability** – OpsPilot works 24/7, giving you confidence and clarity even outside business hours. - - -!!! info "Learn more" - [How to use OpsPilot AI](/Data-insights/Features/OpsPilot/OpsPilot-user-guide/) - -___ - -!!! question "Need more help?" - Contact support in the chat bubble and let us know how we can assist. \ No newline at end of file diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/background-activity.md b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/background-activity.md index 03eb659f..15abb753 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/background-activity.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/background-activity.md @@ -12,7 +12,7 @@ The meter at the top projects how many AI Tokens your current background setting Working style presets set your triage frequency and check-up cadence together, so you can pick a rhythm in one click rather than tuning each control by hand: -| Preset | Behaviour | Triage | Check-ups | +| Preset | Behavior | Triage | Check-ups | |---|---|---|---| | **Active ops team** | Investigates and actions situations of all severities promptly | Hourly | Balanced | | **Daily review** | Checks in daily and jumps on anything critical as it lands. One daily triage batch, lighter checkups | Daily | Light Touch | diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/behavior.md b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/behavior.md index f2b55085..4de90bb0 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/behavior.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/behavior.md @@ -1,12 +1,12 @@ # Behavior -Behavior controls how Coworker communicates and acts - how much detail it gives when it reports, and whether it applies its own optimisation suggestions automatically - so its output fits how your team works. These settings apply across your organisation. +Behavior controls how Coworker communicates and acts - how much detail it gives when it reports, and whether it applies its own optimization suggestions automatically - so its output fits how your team works. These settings apply across your organization. ![!Screenshot](../../../../../Coworker/behaviour.png) ## Report detail -Controls how much Coworker writes when it reports a finding. Applies to every task in your organisation. +Controls how much Coworker writes when it reports a finding. Applies to every task in your organization. | Mode | Description | |---|---| @@ -18,7 +18,7 @@ Controls how much Coworker writes when it reports a finding. Applies to every ta When Coworker spots a way to make a task cheaper or more reliable, it can either propose the change for your review or apply it automatically. -**Auto-accept optimisation suggestions** - apply suggested changes immediately. Off by default; most teams prefer to review each one first. +**Auto-accept optimization suggestions** - apply suggested changes immediately. Off by default; most teams prefer to review each one first. --- diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/budget-cost.md b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/budget-cost.md index 8772483f..1532b321 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/budget-cost.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/budget-cost.md @@ -6,7 +6,7 @@ The **Budget & cost** tab is a single **Coworker spend** card that controls how | Control | Description | |---|---| -| **Your plan allowance** | Your organisation's total monthly AI Token allowance (read-only) | +| **Your plan allowance** | Your organization's total monthly AI Token allowance (read-only) | | **On-demand usage** | **On / Off**, off by default. **Off** makes your plan allowance a hard ceiling - Coworker pauses new work until the period renews, and nothing bills as on-demand. **On** lets Coworker keep working past the plan allowance, up to your monthly spend cap | | **Monthly spend cap** | The most Coworker may spend each month, in tokens. The panel shows the approximate number of investigations that buys per month, alongside your recent monthly average for comparison. Pick a preset (**50%**, **80%**, or **Plan**) or drag the slider; set it to **Plan** and Coworker stops exactly at your plan allowance | | **Warning threshold** | Sends a notification when spend reaches this percentage of the cap. Pick a preset (**5%** - **100%**) or drag the slider | @@ -14,7 +14,7 @@ The **Budget & cost** tab is a single **Coworker spend** card that controls how !!! warning "On-demand usage can exceed your allowance" With **On-demand usage** on, Coworker can spend past your plan allowance, up to your **Monthly spend cap**. Set the cap to bound the extra cost. -Click **Save** to apply your changes. See [AI Tokens](../usage.md#ai-token-allowance) for full usage details and optimisation suggestions. +Click **Save** to apply your changes. See [AI Tokens](../usage.md#ai-token-allowance) for full usage details and optimization suggestions. --- diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/overview.md b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/overview.md index b6889a5d..6eb8a394 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/overview.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/overview.md @@ -1,6 +1,6 @@ # Settings -Settings is where you tune Coworker to your team - what it surfaces, how hard it works in the background, how it communicates, and what it can spend - with no config files involved. Open it from the Coworker menu; it's organised into four tabs: +Settings is where you tune Coworker to your team - what it surfaces, how hard it works in the background, how it communicates, and what it can spend - with no config files involved. Open it from the Coworker menu; it's organized into four tabs: | Tab | Description | |---|---| diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/preferences.md b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/preferences.md index 814f580e..9def2879 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/Settings/preferences.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/Settings/preferences.md @@ -9,14 +9,14 @@ The **Preferences** tab controls what reaches your personal feed. It has two car Feed relevance shapes what reaches your personal feed. You can also ask Coworker to adjust these from any chat. !!! info "Feed filtering only" - Coworker still investigates everything across your organisation - Feed relevance only controls what surfaces for you versus what stays in the team view. + Coworker still investigates everything across your organization - Feed relevance only controls what surfaces for you versus what stays in the team view. | Setting | Description | |---|---| | **Your role** | Pick as many roles as fit: Developer, SRE / DevOps, Tech lead, or Manager / leadership. If every role you pick is a leadership one, Coworker keeps low-level observations out of your feed and surfaces only the things worth escalating | -| **Focus services** | Service names you own or primarily work on. Glob patterns like `opspilot-*` work too. Situations affecting these services are prioritised in your feed | +| **Focus services** | Service names you own or primarily work on. Glob patterns like `opspilot-*` work too. Situations affecting these services are prioritized in your feed | | **Muted services** | Situations on these services stay out of your feed, DMs, and notifications. Muting wins over everything else, including a service you also focus on. Glob patterns like `legacy-*` work too | -| **Focus areas** | The kinds of things Coworker should prioritise when filtering your feed: Errors and exceptions, Application performance, Infrastructure and runtime, Databases and data stores, Data pipelines and quality, Deploys and releases, Team and delivery health, Reliability and SLOs, Cost and capacity, Security and auth | +| **Focus areas** | The kinds of things Coworker should prioritize when filtering your feed: Errors and exceptions, Application performance, Infrastructure and runtime, Databases and data stores, Data pipelines and quality, Deploys and releases, Team and delivery health, Reliability and SLOs, Cost and capacity, Security and auth | | **Custom keywords** | Anything beyond the domains above. A match nudges related situations into your feed | | **Advanced - focus area label** | A free-form team or area label that boosts situations tagged with it (e.g. `payments`, `platform infra`). Usually filled in automatically when you mention it during onboarding; set directly here if needed | diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/activity.md b/docs/Data-insights/Features/OpsPilot/Coworker/activity.md new file mode 100644 index 00000000..8e372642 --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/activity.md @@ -0,0 +1,37 @@ +# Activity + +**Activity** is the record of everything Coworker has done, and every situation change, over the last 30 days. Where [Situations](situations.md) show you what needs attention and [Insights](insights.md) show you what Coworker found, Activity shows you what it *did* - including the many times it decided not to involve you. + +Navigate to **Coworker > Activity** to open it. + +## Finding something + +| Control | What it does | +|---|---| +| **Search activity** | Find an entry by its text | +| **All kinds** | Narrow the list to particular kinds. Opens a searchable list with **Select all**, covering situation lifecycle changes - **opened**, **escalated**, **de-escalated**, **resolved**, **reopened**, **merged**, **self-resolved**, **awaiting you** - alongside Coworker's own **notes** and **checkups** | +| **Summarize** | Ask Coworker to sum up the activity in view | + +Entries run newest first, each showing its kind, what it concerned, a short account of what Coworker did and why, and how long ago. Where the entry relates to a situation, **Open situation** takes you straight to it. + +## What the entries say + +Each entry is labeled with what Coworker did: + +| Label | What it means | +|---|---| +| **Checked** | Coworker ran a checkup on a situation and reported where it stands - what is still breaching, and by how much | +| **Extended** | Coworker attached further insights to an existing situation, because they turned out to be part of the same problem | +| **Noted** | Coworker recorded an observation against a situation without changing its state | +| **Silenced duplicate** | Something arrived that was already covered, so Coworker attached it to the existing situation instead of raising a new one | +| **Silent check** | Coworker investigated and concluded no new situation was needed, because what it found was already accounted for | + +!!! tip "This is where the quiet work shows" + **Silenced duplicate** and **Silent check** are Coworker deciding not to interrupt you. A triage sweep that finds four insights and recognizes them as a recurrence of something already open produces no alert, no situation and no notification - only an Activity entry explaining the decision. + + If you are ever unsure whether Coworker is doing anything, this page is the answer. See also [Why does Coworker raise so few situations?](faq.md#why-does-coworker-raise-so-few-situations) + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/chat.md b/docs/Data-insights/Features/OpsPilot/Coworker/chat.md new file mode 100644 index 00000000..6c72050e --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/chat.md @@ -0,0 +1,120 @@ +# Chat + +Coworker works in the background on its own, but you can also talk to it directly. Use the chat to investigate issues, query your telemetry in plain English, and get AI-guided analysis - without writing queries or navigating dashboards by hand. + +## Access + + + +Coworker opens by default on login. It can also be reached at any time from the Coworker buttons found throughout the platform. + +Type your question in the message box and press **Enter** to send it. Press **Shift+Enter** for a new line instead, so you can write a longer question across several lines without sending it early. + +The panel header shows the current thread's name, with a **New thread** button, a **book** icon for the documentation, a **⋯** menu, and a button to close the panel. When the thread is about a situation, an **Open the situation** button appears first, taking you to its [full detail](situations.md#what-a-situation-shows-you). + +The **⋯** menu holds: + +| Option | What it does | +|---|---| +| **Set up a task** | Create a task by describing what you want watched | +| **Update preferences** | Change what Coworker shows you by talking to it | +| **All threads** | Open your thread history. See [Threads](#threads) | + +The first two open a guided conversation rather than a form, and both reach settings you can also edit directly: + +- **Set up a task** opens a thread headed **Task creation**, offering a starting point for each kind of task - *Create a scheduled task to check error rates every hour*, *Watch a service and tell me when something looks off*, or *Listen to a webhook and run a check on every event*. See [Tasks](tasks.md). +- **Update preferences** asks what you want to change - the services you track, the categories and severities you see, your role and team - and updates them as you go. The form version is in [Settings](Settings/overview.md). + +## Suggestions + +Rather than leaving you with an empty box, Coworker suggests ways to start. + +A new conversation opens on **What can I help with?**, with **Get started** cards for the two things people most often want first: + +| Card | What it does | +|---|---| +| **Set up a task** | Create a task by describing what you want watched. See [Tasks](tasks.md) | +| **Update preferences** | Change what Coworker shows you by talking to it, rather than filling in a form | + +Both open a guided conversation rather than a form - see [the **⋯** menu](#access), which offers the same two. + +Above the message box sit suggested questions drawn from what is happening right now. With a situation open they are about that situation - *What's the fastest fix?*, *Should we page someone?*, *Is anything else cascading?* Click one to send it. + +You can ignore all of it and type your own question instead. + +## Watching Coworker work + +While Coworker is answering, a **Thinking** section shows what it is doing rather than leaving you with a spinner. Each step names the work and its state - *Fetching trace data · Completed*, for example - and expands if you want the detail. + +This is worth a glance on a slow answer. It tells you whether Coworker is still gathering data or already reasoning about it, and which sources it went to. + +## Replying to part of an answer + +Coworker's answers can run long. Select any passage in one and a **Quote in reply** button appears - click it to quote just that part in your next message, so your follow-up is anchored to the sentence you are asking about rather than the whole answer. + +## Web search + +Coworker can search the web when a question needs current information - a version number, a published advisory, a vendor's documentation. This is always available and there is no per-message switch for it. + +## Threads + +Each conversation with Coworker is a **thread**, and they are all kept. Click the **⋯** menu in the chat panel header and choose **All threads** to open the list. + +Threads are grouped by when they happened - **Yesterday** at the top, then by month - and each row shows the thread's name and how long ago it was last used, such as *19h 37m ago* or *2 months ago*. A thread you never named is listed as **New thread**, so it is worth giving the ones you want to come back to a name. + +Use **Search** to find a thread by name, or the **calendar** button beside it to narrow the list by date. Click the **✕** to close the panel. + +## Voice mode + +You can speak a question instead of typing it: + +1. Open Coworker, if it is not already open. +2. Click the **microphone** icon in the message box. +3. The first time, your browser asks whether to let OpsPilot use your microphone. Allow it - the browser remembers your choice, so you are not asked again. +4. The panel shows **I'm listening.** and the icon turns **red**. Ask your question - for example, *do I have any errors?* + +Your words appear in the message box once you stop speaking, not as you talk - so there is a pause before anything shows up. Wait for it rather than repeating yourself. + +!!! tip + While recording, click the **✕** icon to cancel. + +## Images + +Attach an image to give Coworker visual context alongside your question - a dashboard you want explained, a stack trace, a graph that looks wrong. Add one in any of three ways: + +1. Paste it from your clipboard directly into the message box. +2. Click the **Add image** icon in the message box. +3. Drag and drop it from your file explorer. + +## PromQL queries + +Coworker can generate and run PromQL queries to answer questions about your metrics. Ask in plain English and it builds and runs the query for you. + +## Query specific time frames + +Ask for a specific period and Coworker scopes its answer to it - recent performance, anomalies from a particular week, or long-term trends. Useful for pinning down when something changed rather than only what is happening now. + + + +## Sending context to Coworker + +You don't have to arrive at the chat with a question already typed. Most places that chart or list your data can hand what you are looking at straight to Coworker, which opens with that context already loaded. + +**Metric panels carry an Ask AI button** in their top-right corner, throughout OpsPilot - on Servers, Services, and anywhere else your data is graphed. Click it to send that panel to Coworker for an explanation of the pattern or anomaly in it. See [Metric graph actions](../../Servers/metrics.md#metric-graph-actions) for the icons alongside it. + +!!! tip "Start a new thread for a separate investigation" + Sending context adds it to the thread that is currently open, so several of these in a row build up in one conversation. That is useful when you are working through a single problem, and confusing when you have moved on to something else. + + If you are starting a fresh investigation, click **New thread** in the chat panel first, then send the context. + +A few views send richer context than a graph: + +| Where | What it sends | +|---|---| +| [Logs](../../Servers/logs.md) | A log entry, for an explanation and troubleshooting suggestions | +| [Traces](../../Services/traces.md) | **Analyze Trace** sends the whole trace, for analysis of where the time went | + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/event-sources.md b/docs/Data-insights/Features/OpsPilot/Coworker/event-sources.md index 18a4f0c3..85a05b9f 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/event-sources.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/event-sources.md @@ -21,7 +21,7 @@ Use the toggle at the top to enable or disable OpsPilot Alerts entirely. The hea ![!Screenshot](../../../../Coworker/configure-event-source.png) -If Coworker has optimisation suggestions for your alert setup, a banner appears at the top of the configure panel showing the estimated monthly saving. Click **View** to see the suggestion. +If Coworker has optimization suggestions for your alert setup, a banner appears at the top of the configure panel showing the estimated monthly saving. Click **View** to see the suggestion. Under **Alert Rules**, you can: @@ -44,7 +44,7 @@ To set up a new event source, open a new thread, select **Set up a task**, and d | **Type** | The webhook type, e.g. Generic Webhook | | **Name** | A name for the event source (e.g. Production Alerts) | | **Description** | What events this webhook will receive | -| **Custom Instructions** (optional) | Guides how events are investigated, e.g. *"Focus on database-related issues and suggest query optimisations"* | +| **Custom Instructions** (optional) | Guides how events are investigated, e.g. *"Focus on database-related issues and suggest query optimizations"* | | **Model Tier** | Controls how the event is investigated. **Thorough** for critical or complex events; **Efficient** for high-volume, routine events | | **Monthly Budget** (optional) | A token budget for this event source. If not set, the org budget is the only cap. | diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/faq.md b/docs/Data-insights/Features/OpsPilot/Coworker/faq.md index 6c1493df..a0b01bf5 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/faq.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/faq.md @@ -8,11 +8,11 @@ When you first open Coworker, a short [six-step setup](getting-started.md) tailo ### Can I have more than one Coworker? -No. Each user has one Coworker. Your feed and preferences are personal to you, but tasks and investigations are shared across your organisation - everyone on the team can see what Coworker has raised. +No. Each user has one Coworker. Your feed and preferences are personal to you, but tasks and investigations are shared across your organization - everyone on the team can see what Coworker has raised. ### Can my team share a Coworker? -Tasks and investigations are already shared across your organisation. Use the **Just for me** dropdown at the top of the dashboard to toggle between your personalised feed and the full team view. +Tasks and investigations are already shared across your organization. Use the **Just for me** dropdown at the top of the dashboard to toggle between your personalized feed and the full team view. ### Can I restart the setup? @@ -82,7 +82,7 @@ If the underlying issue hasn't been fixed, Coworker will continue to surface it. ### How do I change what types of insights I see? -Open **Settings > Preferences** and adjust **Feed relevance** - your role, focus services, focus areas (the domains Coworker prioritises), and custom keywords. You can also just ask Coworker to adjust these from any chat. This changes what reaches your feed, not what Coworker investigates across your organisation. +Open **Settings > Preferences** and adjust **Feed relevance** - your role, focus services, focus areas (the domains Coworker prioritizes), and custom keywords. You can also just ask Coworker to adjust these from any chat. This changes what reaches your feed, not what Coworker investigates across your organization. !!! info "Learn more" [Preferences](Settings/preferences.md) @@ -93,7 +93,7 @@ Open **Settings > Preferences** and adjust **Feed relevance** - your role, focus ### What do the situation statuses mean? -A situation moves through four statuses: **Open** (newly raised, not yet actioned), **In progress** (someone is working it), **Resolved** (handled), and **Dismissed** (not a real problem). Status is separate from severity (Critical, Warning, or Info) - a Critical can be In progress, and a Warning can sit Open. +A situation has three statuses: **Active** (a live problem), **Watching** (Coworker is keeping an eye on it rather than pressing you about it), and **Resolved** (handled). You can also dismiss one that was never a real problem. Status is separate from severity (Critical, Warning, or Info) - a Critical can sit in Watching, and a Warning can be Active. !!! info "Learn more" [Severity and status](situations.md#severity-and-status) @@ -107,6 +107,57 @@ Open the situation and click **Assign**. Choose **I'll take this** to assign it --- +## Notifications + +### Does Coworker notify me when it finds something? + +Not on its own. Coworker raises situations in your feed, but it does not contact you outside OpsPilot unless you connect Slack. + +### Can I get situations in Slack? + +Yes. Install the [Slack integration](../../Integrations/Chat/slack.md), invite the bot to the channel you want situations in, then enable situation notifications using the slash command in the setup message. + +You can also do the whole thing from the Slack integration page in OpsPilot, which walks you through the steps after you install it. + +### How will I know about a situation when OpsPilot isn't open? + +Slack is the way to be told. You can also ask [OpsPilot MCP](../../Integrations/Chat/opspilot-mcp.md) about currently active situations from your editor or AI assistant, without opening OpsPilot at all. + +### How quickly will I hear about a situation? + +That depends on severity: + +| Severity | Typical time from the triggering event | +|---|---| +| **Critical** | 3-5 minutes | +| **Everything else** | Up to the triage cadence - one hour by default | + +Coworker starts investigating the moment an alert fires, and the investigation itself takes roughly 30 seconds to 2 minutes. Its findings are then picked up at the next **triage**, which runs on a cadence you set in account settings. Critical findings skip that wait: Coworker triggers triage immediately rather than holding them for the next cycle. + +Once a situation exists, Slack delivery is near-instant - OpsPilot checks for events to post every five seconds. + +### Can I be notified only about critical situations? + +Yes. Choose which severities are posted to Slack. + +A situation that is later raised to critical is posted at that point, even if its earlier severity was filtered out, so filtering to critical does not mean missing something that becomes critical. Escalations always notify. + +### Are browser or desktop notifications supported? + +No. Coworker uses the same notification system as the rest of OpsPilot, which has no browser or desktop notifications. + +### Why does Coworker raise so few situations? + +By design. Coworker investigates far more than it reports - alerts, anomalies and other signals that turn out not to indicate a real problem are recorded quietly as [insights](insights.md) rather than raised as situations. + +It raises a situation for recurring issues, customer-facing problems, clear faults, and anything you have explicitly asked it to watch through a [task](tasks.md). Critical is reserved for major faults and things affecting your customers. + +You can also teach it. If it raises something you don't consider important, tell it - Coworker can remember that and either stop raising it, or raise it at a lower severity. + +Expect more noise in the first few weeks. Coworker surfaces pre-existing issues in your environment, and is still learning what your team cares about from your conversations and from what you dismiss. + +--- + ## Costs ### What are OpsPilot AI Tokens? @@ -123,7 +174,7 @@ AI Tokens are used whenever Coworker performs AI-powered work: - Answering questions in chat - Investigating alerts and situations - Triaging and performing background checkups on open situations -- Analysing telemetry and service behaviour +- Analyzing telemetry and service behavior - Running scheduled checks - Generating recommendations, suggested fixes and debriefs - Updating situations and producing findings @@ -156,8 +207,8 @@ You can set a monthly task allowance to control spend, with configurable warning ### How do I reduce AI Token usage? - Review **Optimization Suggestions** in the [AI Tokens tab](usage.md#optimization-suggestions); these appear automatically after a task has run a few times and Coworker detects ways it could be improved -- **Apply** an optimisation suggestion to apply the recommended change immediately -- Click **Analyse & Optimise** to trigger an on-demand optimisation review at any time +- **Apply** an optimization suggestion to apply the recommended change immediately +- Click **Analyse & Optimise** to trigger an on-demand optimization review at any time - Switch high-volume or routine tasks to the [Efficient model tier](tasks.md#model-tier) - Reduce the frequency of scheduled tasks that run often but find little - Review the **AI Token Breakdown** table to identify the most expensive tasks and consolidate or adjust them @@ -177,7 +228,7 @@ Yes. The **Warning threshold** in Settings > Budget & cost triggers a notificati !!! info "Learn more" [Allowance](usage.md#ai-token-allowance) -### How do I accept or dismiss an optimisation suggestion? +### How do I accept or dismiss an optimization suggestion? Open the **AI Tokens** tab in Usage and scroll to **Optimization Suggestions**. Expand any suggestion to see the reasoning under **Why this suggestion** and the proposed change under **Instruction changes**. Click **Apply** to apply it immediately, or **Dismiss** to ignore it. @@ -220,7 +271,18 @@ Please contact support if you need to reset Coworker's [memory](overview.md#memo ### What data does Coworker have access to? -Coworker has access to the observability data in your OpsPilot account: metrics, logs, traces, and alert rules. It does not have access to data outside your organisation's account. +Coworker has access to the observability data in your OpsPilot account: metrics, logs, traces, and alert rules. It does not have access to data outside your organization's account. + +### Does Coworker read our Slack conversations? + +By default, almost nothing. Connecting the [Slack integration](../../Integrations/Chat/slack.md) does not put Coworker in your conversations: + +- **When you @-mention OpsPilot**, it reads the recent message history in that channel for context. It stores only your message - not the surrounding messages it used as context. +- **When you reply in the thread of a situation it posted**, those replies become context for its next check-up on that situation. Coworker says so explicitly in the thread each time. + +It sees nothing else in your Slack. + +Turning on **passive** or **active listening** for a channel changes that deliberately: every message in that channel is sent to Coworker, both as context for investigations and to learn from. In active mode it will also investigate things it can help with and reply on its own. --- diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/getting-started.md b/docs/Data-insights/Features/OpsPilot/Coworker/getting-started.md index a10907fa..9ce07003 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/getting-started.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/getting-started.md @@ -83,7 +83,7 @@ Click **Continue** when done, or **Skip** to proceed without selecting any. ![!Screenshot](../../../../Coworker/onboarding5.png) -Select the domains you want Coworker to prioritise in your feed: +Select the domains you want Coworker to prioritize in your feed: | Area | What it covers | |---|---| @@ -102,17 +102,17 @@ Select as many as apply. These can be updated at any time from **Settings > Pref --- -### Step 6: Which services do you want front and centre? +### Step 6: Which services do you want front and center? ![!Screenshot](../../../../Coworker/onboarding6.png) -Coworker asks which services to put front and centre, so it can prioritise what reaches you first: +Coworker asks which services to put front and center, so it can prioritize what reaches you first: > *"Everything still gets monitored - this just decides what reaches you first, and what sits under the rest of the org. Skip if you'd rather not narrow by service. Either way, you can change it any time."* Choose how to proceed: -- **Sure** - pick the services to put front and centre, so situations touching them are prioritised in your feed. +- **Sure** - pick the services to put front and center, so situations touching them are prioritized in your feed. - **Skip** - finish onboarding without narrowing by service. --- @@ -123,12 +123,12 @@ Whether set during onboarding or later from Settings, three controls decide what | Setting | Description | |---|---| -| **Focus services** | The specific services you own or care about, by name or glob pattern (e.g. `payments-*`). Situations touching these are prioritised in your feed. | -| **Focus areas** | The domains you want prioritised: Errors and exceptions, Application performance, Infrastructure and runtime, Databases and data stores, Data pipelines and quality, Deploys and releases, Team and delivery health, Reliability and SLOs, Cost and capacity, Security and auth. | +| **Focus services** | The specific services you own or care about, by name or glob pattern (e.g. `payments-*`). Situations touching these are prioritized in your feed. | +| **Focus areas** | The domains you want prioritized: Errors and exceptions, Application performance, Infrastructure and runtime, Databases and data stores, Data pipelines and quality, Deploys and releases, Team and delivery health, Reliability and SLOs, Cost and capacity, Security and auth. | | **Custom keywords** | Any terms beyond the focus areas above - a library, technology, or feature name specific to your stack. A match nudges related situations into your feed. | !!! info "Feed filtering only" - None of these change what Coworker investigates or raises across your organisation - they only change what reaches your personal feed. + None of these change what Coworker investigates or raises across your organization - they only change what reaches your personal feed. --- diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/heartbeat.md b/docs/Data-insights/Features/OpsPilot/Coworker/heartbeat.md index 00e89045..18d1d781 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/heartbeat.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/heartbeat.md @@ -58,7 +58,7 @@ Expand a service to see its individual **signals** - each shows the underlying m - Requires at least one **cataloged service**. - Monitoring runs **per service** using learned baselines. -- Investigation history is **organisation-wide**. +- Investigation history is **organization-wide**. - Heartbeat activity is tracked so you have visibility into noise and cost. --- @@ -75,7 +75,7 @@ No. Heartbeat's checks are private to Coworker and never create Grafana or Alert Every five minutes. **Why didn't it react to a one-off spike?** -Heartbeat waits for sustained abnormal behaviour across several consecutive checks before it investigates. +Heartbeat waits for sustained abnormal behavior across several consecutive checks before it investigates. **It investigated something that turned out to be benign - is that a problem?** No. Those outcomes are exactly what Coworker uses to re-tune noisy signals over time. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/insights.md b/docs/Data-insights/Features/OpsPilot/Coworker/insights.md index 0003b1a9..4d87fd5e 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/insights.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/insights.md @@ -12,6 +12,31 @@ The header shows the total insight count, and the **Search insights** box finds ## Filtering +A filter bar runs across the top of the list, with the number of matching insights shown beneath it. Alongside the filters described below, it offers: + +| Control | What it does | +|---|---| +| **Search insights** | Find an insight by its title | +| **Status** | Narrow to a state such as **Unresolved** | +| **Not in a situation** | Show only insights Coworker recorded without raising a [situation](situations.md) from them - the quiet majority of what it finds | +| **Sort** | Order the list, **Newest first** by default | +| **Clear all** | Drop every filter at once | + +Arriving from **Help me see more** on the Coworker dashboard lands you here with the filters already set, so you see that slice rather than everything. + +### Category + +Insights are sorted into broad categories. Pick one to show only its insights, or **Any category** for all of them: + +| Category | What it holds | +|---|---| +| **Errors** | Things failing | +| **Performance** | Things degrading | +| **Points of interest** | Things worth knowing about that are not faults | +| **Coverage gaps** | Things Coworker cannot see - a service not shipping telemetry, a metric it expected and is not getting | + +**Coverage gaps** is what the dashboard's **Help me see more** panel is showing you. These are worth clearing first: everything else Coworker does depends on what reaches it. + ### Severity Each insight is ranked by severity - **Critical**, **Notable**, or **Info**, from most to least important. Select a severity to show only insights at that level; the count beside each shows how many insights it contains. @@ -46,18 +71,19 @@ Click any row to open the insight in full. Opening an insight shows the full write-up: -- **Header** - the severity, category, and affected service, plus the title, occurrence count, and when it was last seen +- **Header** - the severity, category, and affected service, plus the title, occurrence count, when it was last seen, and tags such as the service name or `observability-gap` - **Part of** - if the insight belongs to a situation, a banner links through to that [situation](situations.md) - **Description** - what Coworker found, with root-cause detail -- **Recommended** - concrete next steps Coworker suggests -- **Evidence** - the supporting signals: exceptions, transaction IDs, and log lines +- **Recommended** - concrete next steps Coworker suggests, often linking to the documentation for whatever it is asking you to set up +- **Evidence** - the supporting signals behind the finding. These can be log lines, exceptions and transaction IDs, or metric series shown as charts, each with **Open in Explore** to take it further - **History** - each occurrence of the insight over time. Click **View execution** to see the investigation run that produced it ### Acting on an insight | Action | Description | |---|---| -| **Chat** | Open quick actions and a conversation about the insight, with its full context already loaded (see below) | +| **Chat** | Open a free-form conversation about the insight, with its full context already loaded (see below) | +| **Ask** | Put one of four preset questions to Coworker - **Is this still an issue?**, **Investigate root cause**, **Create a ticket**, or **Suggest a fix** | | **Watch** | Set up a recurring check on the insight - opens the **Watch This Insight** dialog (see below) | | **Resolve** | Mark the insight resolved | | **...** | More actions: **Hide similar** (stop surfacing insights like this one) and **Not right** (tell Coworker the insight is off the mark, so it learns) | @@ -65,17 +91,18 @@ Opening an insight shows the full write-up: ### Chatting about an insight -**Chat** opens a menu of quick actions, each sending the insight to Coworker with its full context already loaded: +**Ask** opens a menu of preset questions, each sending the insight to Coworker with its full context already loaded: ![!Screenshot](../../../../Coworker/insight-chat.png) -| Action | Description | +| Question | What it does | |---|---| | **Is this still an issue?** | Checks the current state to see if the problem is ongoing or resolved | | **Investigate root cause** | Kicks off a root cause analysis | | **Create a ticket** | Creates a ticket for the issue | | **Suggest a fix** | Recommends remediation steps or best practices | -| **Discuss this insight** | Opens a free-form conversation about the insight | + +**Chat** opens a free-form conversation about the insight instead, for anything those four don't cover. ### Watching an insight diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/knowledge.md b/docs/Data-insights/Features/OpsPilot/Coworker/knowledge.md index 672f3ef6..ade2dd3f 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/knowledge.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/knowledge.md @@ -4,7 +4,7 @@ Coworker builds a growing understanding of your systems, your services, and your Click the **Knowledge** button on the Coworker dashboard to explore what Coworker has learned - its memories, areas, and observations. -The header shows live counts for your organisation: memories and observations throughout, plus the number of areas in the **Areas** view and the number of nodes and links in the **Graph** view. +The header shows live counts for your organization: memories and observations throughout, plus the number of areas in the **Areas** view and the number of nodes and links in the **Graph** view. Knowledge is available in three views, selectable from the tabs at the top: **Areas**, **Graph**, and **List**. @@ -20,7 +20,7 @@ There are four kinds: | Area | What it holds | |---|---| -| **System** | Higher-level understanding that governs the whole system - how services interact and behave together, what's normal across the estate, and what tends to break. Shared across your organisation | +| **System** | Higher-level understanding that governs the whole system - how services interact and behave together, what's normal across the estate, and what tends to break. Shared across your organization | | **Services** | Service-specific memories for an individual cataloged service (e.g. `cart`). A first-class memory type introduced with the service catalog, so system memory can focus on the bigger picture rather than single-service detail | | **Tasks** | What a recurring task or event source has turned up over its runs (e.g. OpsPilot Alerts, a daily error review, the heartbeat health screen). Reusing this context can cut token costs by up to 50% on long-running tasks | | **You** | Your personal preferences and the way you like to work, learned from your conversations. This builds up the more you talk to Coworker, so it may be sparse at first | diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/manage-tasks.md b/docs/Data-insights/Features/OpsPilot/Coworker/manage-tasks.md index 4d2960ca..37433dd7 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/manage-tasks.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/manage-tasks.md @@ -1,15 +1,15 @@ # Manage tasks -The **All tasks** panel is one place to see and control everything Coworker runs - pause a noisy task, trigger one on demand, or check when each last fired - without hunting through the feed. +The **Tasks** page is one place to see and control everything Coworker runs - pause a noisy task, trigger one on demand, or check when each last fired - without hunting through the feed. -The tasks sidebar shows your active **Event Sources** and **Scheduled** tasks, each with its name, schedule, and when it last ran. Click **Manage all tasks** to open the full panel. +Navigate to **Coworker > Tasks** to open it, or click **All** on the Tasks panel of the Coworker dashboard. ![!Screenshot](../../../../Coworker/manage-tasks.png) -## The All tasks panel +## The Tasks page -- Click **Preferences** to open **Coworker Preferences** (see [Preferences](#preferences)), or **+ Create Task** to create a new task. A **...** menu offers additional actions. -- Filter using the tabs: **All**, **Scheduled**, **Monitoring**, **Event Sources** - each tab shows the count of tasks in that category. +- Click **Preferences** to open **Coworker Preferences** (see [Preferences](#preferences)), or **+ Create Task** to create a new task. **Disable all** turns off every task at once. +- Use the filter dropdown at the right of the search bar to narrow by category - it shows the total alongside, such as **All 12**. - Search tasks by name using the search bar. - The **System** section shows built-in tasks such as **OpsPilot Alerts**, with a badge showing the current state (e.g. *No alerts yet* if none are connected, or a watch count such as *38/44 watched* once alerts are enabled). - The **Active** section lists your enabled tasks with their schedule, next run time, and last run date. Each task has a **Run** button to trigger it immediately, a toggle to disable it, and a delete button. @@ -19,11 +19,11 @@ The tasks sidebar shows your active **Event Sources** and **Scheduled** tasks, e ## Preferences -Click **Preferences** in the All tasks panel to open **Coworker Preferences**, which controls how tasks generate reports for your organisation. +Click **Preferences** on the Tasks page to open **Coworker Preferences**, which controls how tasks generate reports for your organization. ![!Screenshot](../../../../Coworker/manage-preferences.png) -Its one setting, **Report Detail Level**, sets the verbosity of task execution reports - **Concise**, **Standard**, or **Detailed**. This is the same organisation-wide setting as [Report detail](Settings/behavior.md) in the Behavior tab, where each level is described in full. +Its one setting, **Report Detail Level**, sets the verbosity of task execution reports - **Concise**, **Standard**, or **Detailed**. This is the same organization-wide setting as [Report detail](Settings/behavior.md) in the Behavior tab, where each level is described in full. --- diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/overview.md b/docs/Data-insights/Features/OpsPilot/Coworker/overview.md index 834807c3..c2af2916 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/overview.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/overview.md @@ -1,17 +1,47 @@ # Coworker -Coworker is the connective layer that binds your observability data, alerting, service knowledge, and incident response into one place. Rather than switching between dashboards, alert feeds, and runbooks, you get a single AI SRE teammate that watches your systems, investigates what it finds, and hands you a clear, prioritised picture of what needs attention - so your team spends less time fighting tools and more time fixing problems. +Coworker is the connective layer that binds your observability data, alerting, service knowledge, and incident response into one place. Rather than switching between dashboards, alert feeds, and runbooks, you get a single AI SRE teammate that watches your systems, investigates what it finds, and hands you a clear, prioritized picture of what needs attention - so your team spends less time fighting tools and more time fixing problems. -Each user gets their own personalised Coworker that learns what's relevant to them. It talks to you in the first person, remembers context, and keeps working between your visits. +Each user gets their own personalized Coworker that learns what's relevant to them. It talks to you in the first person, remembers context, and keeps working between your visits.
+## OpsPilot and Coworker + +The two names describe different halves of the same product: + +- **OpsPilot** is the platform - where your metrics, logs, traces, alerts, dashboards, and service catalog live. +- **Coworker** is the AI working on top of it - the part that watches that data, investigates what it finds, and tells you about it. + +The split is a useful one when you are deciding where to look. Storing, querying, and visualizing your data is OpsPilot. Reasoning about it is Coworker. + +What Coworker can reason about depends on what is connected. Installing an [integration](../../integrations.md) widens its view - adding Windows, database, or cloud metrics gives it more to correlate the next time it investigates. + ## How to think about it Think of Coworker as a single teammate rather than a monitoring tool. Behind that one voice it is doing several jobs at once: watching for signals, investigating them, writing down what it finds, and deciding what to tell you. You don't need to think about those internal jobs. You just get one Coworker who keeps you informed. Coworker also shows you what it cannot see. Coverage gaps in your telemetry, unconnected alert rules, uncataloged services - these surface in your feed so you know exactly what to fix to make Coworker more effective. The onboarding experience is not just setup; it is a diagnostic that tells you where your observability has blind spots. +## The dashboard + +Coworker opens on its dashboard, which is also where you land when you log in. The left side is what Coworker has been doing; the right is the [chat](chat.md). + +**Just for me** at the top filters what you see to your own slice of the organization. Switch to the broader view when you are on call or covering someone else - see [Your view or the team's](situations.md#your-view-or-the-teams). + +| Panel | What it holds | +|---|---| +| **Your standup** | A short summary of what matters right now, written by Coworker in its own words. It names the situation it is most concerned about and offers follow-ups you can click - jumping straight to that situation, or asking what to change and why earlier episodes closed. The panel says when it was last written, and you can rewrite it on demand with the refresh icon | +| **Situations** | The situations currently open, with their severity and the service they affect. See [Situations](situations.md) | +| **Help me see more** | Gaps in what Coworker can see - a service that has stopped shipping traces, telemetry it expected and is not getting. These are worth fixing first, because everything else Coworker does depends on what reaches it. **All** opens [Insights](insights.md) filtered to coverage gaps | +| **Recent activity** | What Coworker handled without involving you: checks it ran on its own, and findings it recorded without raising a situation. **Summarize** asks it to sum that up for you, and **All** opens the full [Activity](activity.md) record | +| **Tasks** | Your [Heartbeat](heartbeat.md), [event sources](event-sources.md) and [scheduled tasks](scheduled.md), each showing when it next runs or how long it has been quiet | + +The standup is rewritten on a cadence you set in [Settings > Background activity](Settings/overview.md). + +!!! tip "Findings are not situations" + **Recent activity** often shows a large number of findings not tied to a situation - that is Coworker working as intended. It investigates far more than it reports, and records what turned out not to matter rather than interrupting you with it. See [Why does Coworker raise so few situations?](faq.md#why-does-coworker-raise-so-few-situations) + ## What Coworker does | Capability | Description | @@ -23,10 +53,22 @@ Coworker also shows you what it cannot see. Coverage gaps in your telemetry, unc | **Alert response** | Automatically investigates firing alerts and posts one clean situation instead of a stream of raw alert noise | | **[Tasks](tasks.md)** | Scheduled, monitoring, and webhook-driven jobs that run recurring analysis and report back proactively | | **[Memory](knowledge.md)** | Builds a growing understanding of your systems, your team, and your preferences over time | -| **[Cost management](usage.md)** | Allowance tracking and optimisation suggestions to keep AI Token spend under control | +| **[Cost management](usage.md)** | Allowance tracking and optimization suggestions to keep AI Token spend under control | New here? [Getting started](getting-started.md) walks through onboarding. See [Situations](situations.md) for how findings surface in your feed and how to triage them. +## Where you can reach it + +Coworker is not confined to the OpsPilot UI: + +| Where | What you get | +|---|---| +| **The platform** | The Coworker dashboard, and the Coworker buttons throughout the UI | +| **[Slack](../../Integrations/Chat/slack.md)** | The same Coworker you use in the app. Mention it in a channel or message it directly, and the alerts, situations, and digests it surfaces land there as they happen | +| **[OpsPilot MCP](../../Integrations/Chat/opspilot-mcp.md)** | Your own AI assistant - in an editor or elsewhere - reading your dashboards, metrics, logs, traces, and the situations Coworker is tracking | + +The third row is a different kind of thing from the first two. An assistant connected over MCP reads your OpsPilot data; it is not Coworker itself. + --- ## Memory diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/scheduled.md b/docs/Data-insights/Features/OpsPilot/Coworker/scheduled.md index bb1be477..d2ac0b02 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/scheduled.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/scheduled.md @@ -1,6 +1,6 @@ # Scheduled tasks -Scheduled tasks are how Coworker keeps watch so you don't have to - running a check on the cadence you choose and staying quiet unless there's something worth telling you. They're the core of Coworker's continuous analysis. Choose any interval - hourly, daily, weekly, monthly, or custom - and each run produces a report summarising what Coworker found. Scheduled tasks run until you turn them off. +Scheduled tasks are how Coworker keeps watch so you don't have to - running a check on the cadence you choose and staying quiet unless there's something worth telling you. They're the core of Coworker's continuous analysis. Choose any interval - hourly, daily, weekly, monthly, or custom - and each run produces a report summarizing what Coworker found. Scheduled tasks run until you turn them off. Run any scheduled task on-demand with the **Run now** button, and view the full execution history to see what it found on each run. @@ -8,6 +8,11 @@ Run any scheduled task on-demand with the **Run now** button, and view the full Each run produces the report you set the task up for and also surfaces anything else worth flagging - see [What every task run does](tasks.md#what-every-task-run-does). +!!! warning "Schedules run in UTC" + Coworker works in UTC. Ask for a check at 9am and it runs at **9am UTC**, whatever your own time zone. + + Say which time zone you mean and Coworker converts it - *run at 9am Pacific* becomes 2am UTC. If a task is running at a time you did not expect, this is usually why. + ## Running and reviewing a task Open a scheduled task to see its details and history. Alongside the **On/Off** toggle you can: diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/situations.md b/docs/Data-insights/Features/OpsPilot/Coworker/situations.md index c0fbae31..30708db3 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/situations.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/situations.md @@ -17,12 +17,12 @@ Severity and status answer two different questions: | | Question | Values | |---|---|---| | **Severity** | How bad is this? | Critical, Warning, Info | -| **Status** | Where is it in its lifecycle? | Open, In progress, Resolved, Dismissed | +| **Status** | Where is it in its lifecycle? | Active, Watching, Resolved | -A situation starts **Open**, moves to **In progress** while it's being worked, and ends as **Resolved** (handled) or **Dismissed** (not a real problem). +**Active** is a live problem, **Watching** is one Coworker is keeping an eye on rather than pressing you about, and **Resolved** is handled. You can also **dismiss** a situation that was never a real problem - it closes and drops out of the list. !!! note "Severity and status are independent" - A Critical can be In progress while someone works it, and a Warning can sit Open if it's worth a look but not urgent. Keeping them separate lets the feed show what matters without conflating how bad something is with whether it's being handled. + A Critical can sit in Watching while Coworker keeps an eye on it, and a Warning can be Active. Keeping them separate lets the feed show what matters without conflating how bad something is with whether it is being handled. --- @@ -36,62 +36,68 @@ Coworker is never just a snapshot. Three things run continuously: **Re-checking what's open.** Every open situation is re-investigated on a cadence that depends on its severity. Criticals are checked roughly every 10-15 minutes at first; warnings and quieter items less frequently. When a situation recovers on its own, Coworker resolves it and tells you why. As a situation stays stable, checks become less frequent; if something shifts, the cadence tightens back up. Once resolved, a situation gets a couple of follow-up checks over the next few hours to confirm the fix held. -![!Screenshot](../../../../Coworker/overview1.png) --- -## The home page +## Your view or the team's -The home page is a feed of messages from your Coworker, more like a conversation with a colleague who has been working while you were away than a static dashboard. Everything arrives as a message in that feed: new situations, updates to existing ones, checks that came back clean, and pointers to coverage gaps. +Use **Just for me** to filter situations to your personalized slice - those relevant to your services and setup. Switch to the broader view when you're on call, covering someone else's area, or want the full picture across your organization. -![!Screenshot](../../../../Coworker/situations-home.png) +--- -A **WATCHING** badge in the header confirms Coworker is actively monitoring your environment. +## The situations list -The interface uses a tab bar across the top. **Home** is always the first tab. Each situation thread or conversation you open appears as an additional tab alongside it, so you can switch between multiple threads without losing context. Click **+** to open a new thread. Tabs with an orange dot indicate an active or critical situation. +**Coworker > Situations** lists everything Coworker is actively working on, with the number of matches shown above the list. -### Your view or the team's +| Control | What it does | +|---|---| +| **Search by title or service** | Find a situation by its name or the service it affects | +| **Status** | Filter by state - **Active**, **Watching**, or **Resolved**. Starts on Active and Watching, so resolved situations stay out of the way until you ask for them. Selections show as chips you can remove individually, with **Select all** and **Clear all** in the dropdown | +| **Any severity** | Filter to one severity | +| **Just for me** | Switch between your own slice and the full team view - see [Your view or the team's](#your-view-or-the-teams) | +| **By service** | Group the list by affected service | -Use the **Just for me** dropdown at the top of the page to filter the feed to your personalised slice - situations relevant to your services and setup. Switch to a broader view when you're on call, covering someone else's area, or want the full picture across your organisation. +Each row shows the situation's severity as a colored dot and as a label, the service it affects, its current state, and when it last changed. Services appear as they are named in your telemetry, so a namespaced one reads in full - `opentelemetry-demo/recommendation`, for example - which is also what **Search by title or service** matches on. -### How the feed adapts +## Situations and threads -Coworker changes how it leads depending on what it has to tell you: +Every situation opens into a thread: a dedicated conversation about that one problem, with all context already loaded. At the top sits the situation itself; below it runs the history of Coworker's checkups and state changes, interleaved with any messages between you and it. -| State | What you see | -|---|---| -| **Quiet** | An "all clear" note on what Coworker has been doing and watching. Silence means "checked and fine", not "nothing running" | -| **One critical** | A single focus card with the full story: summary, affected service, impact, latest checkup, and evidence | -| **A few criticals** | Prominent rows in urgency order, each with enough detail to triage at a glance | -| **Many criticals** | A status overview showing the count and affected services. When everything is urgent, a wall of full-size cards doesn't help | -Below the critical items sits the quieter list: warnings and lower-severity items Coworker is watching rather than actively raising. This is where tomorrow's situation often first appears. Recently resolved situations collapse into a short list near the bottom. +### What a situation shows you -### Other message types +Above the thread, the situation opens with its severity, the service it affects, and its status, then Coworker's own summary of what is happening and how far it has spread. Alongside that summary sit three panels: -Alongside situations, the feed contains: +| Panel | What it holds | +|---|---| +| **Right-now impact** | The numbers that make this matter at this moment - the latency, error rate, or throughput that moved, and the services it has reached | +| **Timeline** | What happened and when, oldest to newest, including whether this same pattern has occurred before | +| **Data** | The evidence behind the summary - trend charts over the recent window, and the log lines Coworker drew on | -- **Coverage gaps**: one of Coworker's most useful signals. When it can't investigate something, or spots telemetry it can't trust, it says so - from the broad (a service with no telemetry, an unconnected alert rule) to the specific (a JVM pool with no metrics, a p95 query using the wrong label). Each gap names what's missing, with a **Help me set this up** button, a **link** icon to copy it, and a **dismiss** (✕). This makes Coworker a diagnostic for your observability, not just a consumer of it. -- **The digest**: a snapshot Coworker keeps current, summarising the checks it ran and things it handled quietly in the background. -- **Debriefs**: short notes for when Coworker investigated something and concluded there was nothing worth raising, so the work is visible rather than silent. +### Signals watched -### Sidebar +Coworker sets up its own watches on a situation so it hears about a change immediately, rather than waiting for its next scheduled checkup. -The right-hand sidebar gives a quick status view alongside the feed: +Each watched signal shows what it is watching and why, the threshold that counts as a breach, and its current state - **breaching** or **clear** - over a recent window. A signal that was clear at the last checkup and is breaching now is how Coworker catches an escalation early. -| Section | Description | -|---|---| -| **Tasks** | The number of open tasks currently assigned to you, with a link to the full Tasks board | -| **Event sources** | Your connected event sources and their recent activity - showing whether each has been quiet or firing, and when it last triggered | -| **Scheduled** | Your scheduled tasks, showing their run cadence and when they last ran. A green highlight indicates a task that just finished | +These are Coworker's own, set for this situation. They are not [alert rules](../../New-alerting/rules.md) and do not notify anyone on their own. ---- +### Showing its working -## Situations and threads +A row of tabs at the foot of the situation opens up everything behind the summary, each with a count so you can see what is there before clicking: -Every situation opens into a thread: a dedicated conversation about that one problem, with all context already loaded. At the top sits the situation itself; below it runs the history of Coworker's checkups and state changes, interleaved with any messages between you and it. +| Tab | What it holds | +|---|---| +| **Evidence** | What Coworker read before it concluded any of this | +| **Raised from** | The insights the situation was built from | +| **Fixes** | Fixes recorded against this situation. Reads *No fixes recorded yet* until one is | +| **Repeat firings** | How many times this has recurred | +| **Updates** | Each time Coworker revised its own account of the situation. An entry gives its reasoning for the change and badges which fields it rewrote - **Updated title**, **Updated summary**, and so on | +| **History** | The full record of checkups and state changes | + +The counts are worth reading on their own. A situation **raised from** several hundred insights with a high **repeat firings** count is a long-running pattern rather than a one-off, and tells you something before you have opened a single tab. -![!Screenshot](../../../../Coworker/situation-detail.png) +**Updates** is worth a look on anything long-running. A situation is not a fixed statement - as Coworker learns more it rewrites its own title and summary, and that tab is where it explains why. A situation that reads differently today than when you last saw it will say so there. From a situation thread you can: @@ -101,13 +107,13 @@ From a situation thread you can: | **Verify now** | Triggers a fresh investigation immediately, rather than waiting for the next scheduled checkup. The result lands in the thread when done | | **Suggest a fix** | Prompts Coworker to propose concrete remediation steps based on what it has found | | **Assign** | Give the situation an owner. Click **I'll take this** to assign it to yourself, or search members and pick a teammate | -| **Set status** | Move the situation through its lifecycle - **Open**, **In progress**, **Resolved**, or **Dismissed**. Choosing Resolved or Dismissed asks for a quick reason, which also teaches Coworker what not to raise next time | +| **Set status** | Move the situation through its lifecycle - **Active**, **Watching**, or **Resolved** - or dismiss it. Closing a situation asks for a quick reason, which also teaches Coworker what not to raise next time | | **Share** | Copies a shareable link to the thread | | **Copy** | Copies the full situation as a markdown brief, ready to paste into another tool or hand off to a teammate | ### Insight shortcuts -Click **Chat** on any insight for five quick actions: +**Ask** offers four preset questions about an insight, so you don't have to phrase them yourself: | Action | Description | |---|---| @@ -115,9 +121,10 @@ Click **Chat** on any insight for five quick actions: | **Investigate root cause** | Kicks off a root cause analysis | | **Create a ticket** | Creates a ticket for the issue | | **Suggest a fix** | Recommends remediation steps or best practices | -| **Discuss this insight** | Opens a free-form conversation about the insight | -These shortcuts are available everywhere insights appear: the priority queue, insight lists, and insight detail views. You can also click **Help me triage** to send your current priority insights and recent activity to Coworker for a prioritisation recommendation. +**Chat** opens a free-form conversation about the insight instead, with its full context already loaded. + +These shortcuts are available everywhere insights appear: the priority queue, insight lists, and insight detail views. You can also click **Help me triage** to send your current priority insights and recent activity to Coworker for a prioritization recommendation. --- @@ -125,7 +132,6 @@ These shortcuts are available everywhere insights appear: the priority queue, in You can start a fresh thread at any time to ask about a service, a recent change, a metric, or anything else Coworker can investigate. Click **+** in the tab bar to open a new thread. -![!Screenshot](../../../../Coworker/new-thread.png) Three shortcuts are offered to get started quickly: diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/tasks.md b/docs/Data-insights/Features/OpsPilot/Coworker/tasks.md index e4311cfa..ececfdaa 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/tasks.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/tasks.md @@ -5,7 +5,7 @@ Tasks are the standing jobs you give Coworker to run in the background. Rather t Coworker is not limited to your observability data. As an LLM, it can also search the web as part of an investigation, bringing in external context (documentation, known issues, best practices) alongside your metrics, logs, and traces. !!! info - Tasks are currently configured at the organisation level. + Tasks are currently configured at the organization level. --- @@ -17,7 +17,7 @@ Coworker's always-on health screen. Once your services are cataloged, it watches ### Scheduled tasks -Run on a recurring schedule you choose: hourly, daily, weekly, monthly, or a custom interval. Each run produces a report summarising what Coworker found - the core of Coworker's continuous analysis. See [Scheduled tasks](scheduled.md) for details. +Run on a recurring schedule you choose: hourly, daily, weekly, monthly, or a custom interval. Each run produces a report summarizing what Coworker found - the core of Coworker's continuous analysis. See [Scheduled tasks](scheduled.md) for details. ### Event sources diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/usage.md b/docs/Data-insights/Features/OpsPilot/Coworker/usage.md index b711f4d5..bce2b0f9 100644 --- a/docs/Data-insights/Features/OpsPilot/Coworker/usage.md +++ b/docs/Data-insights/Features/OpsPilot/Coworker/usage.md @@ -15,7 +15,7 @@ Usage varies depending on the amount of context, telemetry and reasoning require | Source | Description | |---|---| | **Chat** | AI Tokens used by direct questions and conversations with Coworker | -| **Coworker investigations** | AI Tokens used when Coworker investigates alerts, situations, telemetry patterns or service behaviour | +| **Coworker investigations** | AI Tokens used when Coworker investigates alerts, situations, telemetry patterns or service behavior | | **Scheduled checks** | AI Tokens used by recurring Coworker tasks, such as daily error checks, performance reviews or resource usage analysis | | **Recommendations** | AI Tokens used to generate suggested fixes, explanations and next steps | @@ -36,7 +36,7 @@ Four summary metrics are shown at the top: | **New findings** | Number of new findings generated across all investigations | | **Situations raised** | Number of situations Coworker raised in the selected period | -A **Runs over time** chart stacks activity across the period, coloured by task alongside the held-off categories (allowance and paced). The legend below the chart identifies each task and the held-off types; when there are many tasks, the smaller ones are grouped together as **Other tasks (N)**. +A **Runs over time** chart stacks activity across the period, colored by task alongside the held-off categories (allowance and paced). The legend below the chart identifies each task and the held-off types; when there are many tasks, the smaller ones are grouped together as **Other tasks (N)**. The **By task** table breaks down activity per task: @@ -128,7 +128,7 @@ Toggle **Auto-apply optimization suggestions** to have Coworker automatically ap ### On-demand analysis -Click **Analyse & Optimise** to trigger an on-demand optimisation review at any time. If no optimisations are needed, you'll see a **Looking good!** confirmation. +Click **Analyse & Optimise** to trigger an on-demand optimization review at any time. If no optimizations are needed, you'll see a **Looking good!** confirmation. --- diff --git a/docs/Data-insights/Features/OpsPilot/OpsPilot-user-guide.md b/docs/Data-insights/Features/OpsPilot/OpsPilot-user-guide.md deleted file mode 100644 index 9b593245..00000000 --- a/docs/Data-insights/Features/OpsPilot/OpsPilot-user-guide.md +++ /dev/null @@ -1,175 +0,0 @@ - - -# User Guide - -OpsPilot is your AI-powered operations platform, combining autonomous background monitoring with an on-demand chat interface. Use the chat to investigate issues, query your telemetry in plain English, and get AI-guided analysis - without writing queries or navigating dashboards manually. - - - -
- - - -## Access - -![!Screenshot](/Data-insights/Features/OpsPilot/images/OPmain.png) - -OpsPilot opens by default on login. It can also be accessed at any time via the OpsPilot integration buttons found throughout the platform. - - -## Web Search Toggle - - - -OpsPilot now includes a feature that allows users to **enable or disable web search** when asking questions. This gives you better control over how your queries are handled - especially when working with private or internal information. - -### Where to find it - -In the assistant chat bar (bottom of the screen), there is a **globe icon** next to the microphone button. This icon is the **web Search Toggle**. - - - -![!Screenshot](/Data-insights/Features/OpsPilot/images/web-search.png) - -### How it works - -- **Enabled:** OpsPilot will use **live web search** to help answer your question with up-to-date information. - -- **Disabled:** OpsPilot will only use internal knowledge and the connected knowledge base - no external web queries are made. - - - - -### Why this matters - -This feature was added primarily for **privacy control**. While web search is helpful, there may be cases where you might not want your input interpreted as a search (e.g., asking about passwords, credentials, or internal topics). With the toggle off, your message won't be used for any web searches. - - -### Best practice - -- For **internal, private, or sensitive questions** → Keep web search **OFF**. - -- For **general knowledge or live information** → Toggle web search **ON**. - - - -## Suggestions - -When you start a new conversation, OpsPilot displays a set of **Suggestions** - pre-built questions based on common observability scenarios. Clicking a suggestion sends it directly as your first message, giving you a fast starting point without needing to type anything. - -Suggestions cover areas such as errors, performance, network latency, and database health. You can also ignore them entirely and type your own question in the message box at the bottom of the screen. - -## Conversations - -Click the **Conversations** icon to view and search your previous OpsPilot conversations, grouped by date. - -![!Screenshot](/Data-insights/Features/OpsPilot/images/history.png) - -## Voice mode - -OpsPilot allows you to send a voice message instead of typing your query. This is yet another time-saving feature of the assistant. - -Using voice mode: - -1. Open OpsPilot (if not already open by default). - -2. Click the blue microphone icon. - -3. Wait for the 'I'm listening' written response. - -4. Ask OpsPilot your question. For example, 'Do I have any errors?' - -!!! tip - While recording a question, you can click the X icon to cancel it. - -## OpsPilot Vision - -You can upload images to give OpsPilot visual context alongside your questions. Images can be added in three ways: - -1. Paste an image from your clipboard directly into the message box. -2. Click the **Attach Image** button in the bottom left corner. -3. Drag and drop an image from your file explorer. - - - - -## PromQL queries - - -
- -OpsPilot can generate and execute PromQL queries to answer questions about your metrics. Type your question in plain English and OpsPilot will build and run the query for you. - -![!Screenshot](/Data-insights/Features/OpsPilot/images/promql.png) - -Type `/` to see a list of available commands. - - -![!Screenshot](/Data-insights/Features/OpsPilot/images/commands.png) - - -![!Screenshot](/Data-insights/Features/OpsPilot/images/activity.png) - - - - - - - -## Query specific time frames - -Whether you need to scrutinize recent performance data, investigate anomalies from a particular week, or review long-term trends, OpsPilot is at your service. Simply request information for the time frame of your choice, and OpsPilot swiftly generates insights tailored to that period. This feature ensures that you have the flexibility to focus on the time intervals that matter most to your monitoring and analysis efforts, empowering you to pinpoint issues, track progress, and make data-driven decisions with precision and confidence. - - -![!Screenshot](/Data-insights/Features/OpsPilot/images/timeframe.png) - -## FusionReactor integration points - -Wherever you see the blue **OpsPilot AI** button in the FusionReactor UI, you can send that context directly to OpsPilot for analysis. - -### Error context - -🔎 **FusionReactor** > **Applications** > **Errors** > **Trace** > **Error Snapshot** - -Click the OpsPilot AI button to send error details to OpsPilot. It will explain the method, identify potential causes, and suggest fixes. - -![!Screenshot](/Data-insights/Features/OpsPilot/images/code1.png) - -### Code helper - -Highlight any decompiled code and right-click to access three options: - -- **Debug code** - flags potential error causes -- **Explain code** - explains what the code does -- **Suggest optimization** - recommends readability and performance improvements - -![!Screenshot](/Data-insights/Features/OpsPilot/images/codehelp1.png) - -### Profile - -🔎 **FusionReactor** > **Applications / Servers** > **Tracing** > **Trace** > **Profile** - -Sends profile data to OpsPilot for an explanation of where issues may be located. - -![!Screenshot](/Data-insights/Features/OpsPilot/images/profile1.png) - -### Log explain - -🔎 **FusionReactor** > **Logging** > **Logs** - -Click the OpsPilot AI button next to a log entry to get an explanation of what caused it and suggested fixes. - -![!Screenshot](/Data-insights/Features/OpsPilot/images/logexplain.png) - -### Stack trace - -🔎 **FusionReactor** > **Applications / Servers** > **Tracing** > **Trace** > **Error Output** - -Click the OpsPilot AI button next to an error to get insight into the stack trace and potential causes. - -![!Screenshot](/Data-insights/Features/OpsPilot/images/stacktrace1.png) - -___ - -!!! question "Need more help?" - Contact support in the chat bubble and let us know how we can assist. \ No newline at end of file diff --git a/docs/Data-insights/Features/OpsPilot/images/General1.png b/docs/Data-insights/Features/OpsPilot/images/General1.png deleted file mode 100644 index e3a55ebc..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/General1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/Graphs1.png b/docs/Data-insights/Features/OpsPilot/images/Graphs1.png deleted file mode 100644 index 5d8eecb9..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/Graphs1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/Jira-config.png b/docs/Data-insights/Features/OpsPilot/images/Jira-config.png deleted file mode 100644 index 063c5c16..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/Jira-config.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/Jira1.png b/docs/Data-insights/Features/OpsPilot/images/Jira1.png deleted file mode 100644 index 6a284557..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/Jira1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/NewOps.png b/docs/Data-insights/Features/OpsPilot/images/NewOps.png deleted file mode 100644 index 40a12b06..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/NewOps.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/OP-main.png b/docs/Data-insights/Features/OpsPilot/images/OP-main.png deleted file mode 100644 index f085ee56..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/OP-main.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/OPimage.png b/docs/Data-insights/Features/OpsPilot/images/OPimage.png deleted file mode 100644 index 026715f8..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/OPimage.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/OPmain.png b/docs/Data-insights/Features/OpsPilot/images/OPmain.png deleted file mode 100644 index 4d3d51c9..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/OPmain.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/Opspilotfind.png b/docs/Data-insights/Features/OpsPilot/images/Opspilotfind.png deleted file mode 100644 index 223fb8ed..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/Opspilotfind.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/Services.png b/docs/Data-insights/Features/OpsPilot/images/Services.png deleted file mode 100644 index 5ec78c8d..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/Services.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/Vision.png b/docs/Data-insights/Features/OpsPilot/images/Vision.png deleted file mode 100644 index 26dfe541..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/Vision.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/WN3.png b/docs/Data-insights/Features/OpsPilot/images/WN3.png deleted file mode 100644 index 2b81d9f6..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/WN3.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/WNOP1.png b/docs/Data-insights/Features/OpsPilot/images/WNOP1.png deleted file mode 100644 index 45af72df..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/WNOP1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/WNOP2.png b/docs/Data-insights/Features/OpsPilot/images/WNOP2.png deleted file mode 100644 index dbcf91d5..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/WNOP2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/access.png b/docs/Data-insights/Features/OpsPilot/images/access.png deleted file mode 100644 index 7ca5951f..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/access.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/actions.png b/docs/Data-insights/Features/OpsPilot/images/actions.png deleted file mode 100644 index 986ed1b8..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/actions.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/activity.png b/docs/Data-insights/Features/OpsPilot/images/activity.png deleted file mode 100644 index 302e7e8f..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/activity.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/add-apps.png b/docs/Data-insights/Features/OpsPilot/images/add-apps.png deleted file mode 100644 index 0e86e749..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/add-apps.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/add-slack.png b/docs/Data-insights/Features/OpsPilot/images/add-slack.png deleted file mode 100644 index bc75124f..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/add-slack.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/add-teams.png b/docs/Data-insights/Features/OpsPilot/images/add-teams.png deleted file mode 100644 index 44e00db5..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/add-teams.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/askme.png b/docs/Data-insights/Features/OpsPilot/images/askme.png deleted file mode 100644 index 180e8b90..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/askme.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/askquestion.png b/docs/Data-insights/Features/OpsPilot/images/askquestion.png deleted file mode 100644 index 4be4d119..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/askquestion.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/autocomplete.png b/docs/Data-insights/Features/OpsPilot/images/autocomplete.png deleted file mode 100644 index 6fb101b2..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/autocomplete.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/built-for-org.png b/docs/Data-insights/Features/OpsPilot/images/built-for-org.png deleted file mode 100644 index c5845877..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/built-for-org.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/cancelscrape.png b/docs/Data-insights/Features/OpsPilot/images/cancelscrape.png deleted file mode 100644 index 21a2e23f..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/cancelscrape.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/code1.png b/docs/Data-insights/Features/OpsPilot/images/code1.png deleted file mode 100644 index bc142607..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/code1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/code2.png b/docs/Data-insights/Features/OpsPilot/images/code2.png deleted file mode 100644 index 1298e161..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/code2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/codehelp1.png b/docs/Data-insights/Features/OpsPilot/images/codehelp1.png deleted file mode 100644 index 04d31afe..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/codehelp1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/commands.png b/docs/Data-insights/Features/OpsPilot/images/commands.png deleted file mode 100644 index 5d717479..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/commands.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/comment.png b/docs/Data-insights/Features/OpsPilot/images/comment.png deleted file mode 100644 index 7a53e4cf..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/comment.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/create-ticket.png b/docs/Data-insights/Features/OpsPilot/images/create-ticket.png deleted file mode 100644 index 2f3749f4..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/create-ticket.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/data-centre.png b/docs/Data-insights/Features/OpsPilot/images/data-centre.png deleted file mode 100644 index 1e61d8a6..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/data-centre.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/detail.png b/docs/Data-insights/Features/OpsPilot/images/detail.png deleted file mode 100644 index 29b20e27..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/detail.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/detaillevel1.png b/docs/Data-insights/Features/OpsPilot/images/detaillevel1.png deleted file mode 100644 index 8f0ab38a..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/detaillevel1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/detaillevel2.png b/docs/Data-insights/Features/OpsPilot/images/detaillevel2.png deleted file mode 100644 index 676e15b0..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/detaillevel2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/errorrate.png b/docs/Data-insights/Features/OpsPilot/images/errorrate.png deleted file mode 100644 index cf075b05..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/errorrate.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/history.png b/docs/Data-insights/Features/OpsPilot/images/history.png deleted file mode 100644 index 1cbf6b23..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/history.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/home.png b/docs/Data-insights/Features/OpsPilot/images/home.png deleted file mode 100644 index 15f22ae4..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/home.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/home2.png b/docs/Data-insights/Features/OpsPilot/images/home2.png deleted file mode 100644 index c1eefc2a..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/home2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/image.png b/docs/Data-insights/Features/OpsPilot/images/image.png deleted file mode 100644 index d43f93cb..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/image.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/install-op.png b/docs/Data-insights/Features/OpsPilot/images/install-op.png deleted file mode 100644 index 8fec00ae..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/install-op.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/jira-connect.png b/docs/Data-insights/Features/OpsPilot/images/jira-connect.png deleted file mode 100644 index c4d2aeb6..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/jira-connect.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/jira-example.png b/docs/Data-insights/Features/OpsPilot/images/jira-example.png deleted file mode 100644 index 9f4fc0a6..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/jira-example.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/jira-successful.png b/docs/Data-insights/Features/OpsPilot/images/jira-successful.png deleted file mode 100644 index a855fc0a..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/jira-successful.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/knowledge.png b/docs/Data-insights/Features/OpsPilot/images/knowledge.png deleted file mode 100644 index 2b60ae50..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/knowledge.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/logexplain.png b/docs/Data-insights/Features/OpsPilot/images/logexplain.png deleted file mode 100644 index 1d879a08..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/logexplain.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/logexplain2.png b/docs/Data-insights/Features/OpsPilot/images/logexplain2.png deleted file mode 100644 index 57cb6ee5..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/logexplain2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/manage-apps.png b/docs/Data-insights/Features/OpsPilot/images/manage-apps.png deleted file mode 100644 index 00482b76..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/manage-apps.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/manage-policies.png b/docs/Data-insights/Features/OpsPilot/images/manage-policies.png deleted file mode 100644 index 35864aa5..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/manage-policies.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/new-knowledge.png b/docs/Data-insights/Features/OpsPilot/images/new-knowledge.png deleted file mode 100644 index 6d1623bd..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/new-knowledge.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/open.png b/docs/Data-insights/Features/OpsPilot/images/open.png deleted file mode 100644 index 437772e4..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/open.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/problem1.png b/docs/Data-insights/Features/OpsPilot/images/problem1.png deleted file mode 100644 index c693e8cb..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/problem1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/problem2.png b/docs/Data-insights/Features/OpsPilot/images/problem2.png deleted file mode 100644 index fa66e5e2..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/problem2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/profile1.png b/docs/Data-insights/Features/OpsPilot/images/profile1.png deleted file mode 100644 index 1ac6fdea..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/profile1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/profile2.png b/docs/Data-insights/Features/OpsPilot/images/profile2.png deleted file mode 100644 index 62230761..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/profile2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/promql.png b/docs/Data-insights/Features/OpsPilot/images/promql.png deleted file mode 100644 index bbd2145a..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/promql.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/q2.png b/docs/Data-insights/Features/OpsPilot/images/q2.png deleted file mode 100644 index 877e1e0f..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/q2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/question1.png b/docs/Data-insights/Features/OpsPilot/images/question1.png deleted file mode 100644 index b1d7c4f0..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/question1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/refresh.png b/docs/Data-insights/Features/OpsPilot/images/refresh.png deleted file mode 100644 index 6d9a593b..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/refresh.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/rescrape.png b/docs/Data-insights/Features/OpsPilot/images/rescrape.png deleted file mode 100644 index 3426f519..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/rescrape.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/rewind.png b/docs/Data-insights/Features/OpsPilot/images/rewind.png deleted file mode 100644 index f98d4ffc..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/rewind.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/rewritecode.png b/docs/Data-insights/Features/OpsPilot/images/rewritecode.png deleted file mode 100644 index abaa0cce..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/rewritecode.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/showme.png b/docs/Data-insights/Features/OpsPilot/images/showme.png deleted file mode 100644 index a2ebeee5..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/showme.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/slack-added.png b/docs/Data-insights/Features/OpsPilot/images/slack-added.png deleted file mode 100644 index 1df17c1f..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/slack-added.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/slack-allow.png b/docs/Data-insights/Features/OpsPilot/images/slack-allow.png deleted file mode 100644 index d8a0107a..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/slack-allow.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/slack.png b/docs/Data-insights/Features/OpsPilot/images/slack.png deleted file mode 100644 index 86109948..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/slack.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/stacktrace1.png b/docs/Data-insights/Features/OpsPilot/images/stacktrace1.png deleted file mode 100644 index 1a7f2aa7..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/stacktrace1.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/stacktrace2.png b/docs/Data-insights/Features/OpsPilot/images/stacktrace2.png deleted file mode 100644 index 33ad7292..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/stacktrace2.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/stacktracezoom.png b/docs/Data-insights/Features/OpsPilot/images/stacktracezoom.png deleted file mode 100644 index bc94fa7e..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/stacktracezoom.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/suggestions.png b/docs/Data-insights/Features/OpsPilot/images/suggestions.png deleted file mode 100644 index cb84a67b..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/suggestions.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/templates.png b/docs/Data-insights/Features/OpsPilot/images/templates.png deleted file mode 100644 index 88678225..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/templates.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/timeframe.png b/docs/Data-insights/Features/OpsPilot/images/timeframe.png deleted file mode 100644 index 54cfcee9..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/timeframe.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/translate.png b/docs/Data-insights/Features/OpsPilot/images/translate.png deleted file mode 100644 index 9364263d..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/translate.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/update-jira.png b/docs/Data-insights/Features/OpsPilot/images/update-jira.png deleted file mode 100644 index 0cccb6d4..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/update-jira.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/upload-new-app.png b/docs/Data-insights/Features/OpsPilot/images/upload-new-app.png deleted file mode 100644 index 40af1cda..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/upload-new-app.png and /dev/null differ diff --git a/docs/Data-insights/Features/OpsPilot/images/web-search.png b/docs/Data-insights/Features/OpsPilot/images/web-search.png deleted file mode 100644 index cb84a67b..00000000 Binary files a/docs/Data-insights/Features/OpsPilot/images/web-search.png and /dev/null differ diff --git a/docs/Data-insights/Features/Servers/faq.md b/docs/Data-insights/Features/Servers/faq.md index 7f7e188b..921085d7 100644 --- a/docs/Data-insights/Features/Servers/faq.md +++ b/docs/Data-insights/Features/Servers/faq.md @@ -71,7 +71,7 @@ Stat cards update automatically if an auto-refresh interval is set. If auto-refr ### How do I investigate a spike I can see in a graph? -Click and drag on the graph to zoom into the spike. Hover over data points to see exact values. You can also click **Ask AI** in the graph's top-right corner to send the metric to OpsPilot for an AI-guided explanation of the pattern. +Click and drag on the graph to zoom into the spike. Hover over data points to see exact values. You can also click **Ask AI** in the graph's top-right corner to send the metric to [Coworker](../OpsPilot/Coworker/chat.md) for an explanation of the pattern. --- @@ -89,10 +89,6 @@ Crash Protection is available from **FusionReactor version 2025.2** onwards. Reports are retained for historical analysis. There is no automatic expiry, so you can review past events to identify recurring patterns. -### How do I send a Crash Protection report to OpsPilot for analysis? - -From the Crash Protection page, click the **Ask OpsPilot** button on any report to send the full snapshot to OpsPilot AI for automated analysis and guidance. - --- ## UI Tunnel diff --git a/docs/Data-insights/Features/Servers/logs.md b/docs/Data-insights/Features/Servers/logs.md index 10ad5a40..8f687715 100644 --- a/docs/Data-insights/Features/Servers/logs.md +++ b/docs/Data-insights/Features/Servers/logs.md @@ -41,7 +41,6 @@ When you click the arrow next to a log entry, it expands to show three sections: - **Links** - Quick actions to explore related data: - **Trace** button - Opens the associated distributed trace to see the full request flow that generated this log - - **Ask OpsPilot AI** button - Sends the log to OpsPilot for AI-powered analysis, explanations, and troubleshooting recommendations ![Screenshot](links.png) diff --git a/docs/Data-insights/Features/Servers/metrics.md b/docs/Data-insights/Features/Servers/metrics.md index 5f9c29ff..9df1a1cf 100644 --- a/docs/Data-insights/Features/Servers/metrics.md +++ b/docs/Data-insights/Features/Servers/metrics.md @@ -56,7 +56,7 @@ This helps with **root-cause analysis** - understanding what led to a performanc The top-right corner of each metric graph contains three action icons: -1. **Ask AI** - Send this metric to OpsPilot AI for natural language explanations and analysis of patterns or anomalies. +1. **Ask AI** - Send this metric to [Coworker](../OpsPilot/Coworker/chat.md) for a plain-language explanation and analysis of patterns or anomalies. 2. **Full screen** - Open the metric in full-screen view for detailed analysis and extended time ranges. diff --git a/docs/Data-insights/Features/Servers/traces.md b/docs/Data-insights/Features/Servers/traces.md index 701dc57a..aa275b14 100644 --- a/docs/Data-insights/Features/Servers/traces.md +++ b/docs/Data-insights/Features/Servers/traces.md @@ -63,7 +63,7 @@ Click the `>` arrow on any row to expand it and see a summary and waterfall time Three buttons in the top right of the expanded view let you: -- **Analyze Trace** - send the trace to OpsPilot AI for analysis +- **Analyze Trace** - send the trace to [Coworker](../OpsPilot/Coworker/chat.md) for analysis - **Expand all** - expand all spans in the waterfall at once - **Collapse all** - collapse all spans in the waterfall at once diff --git a/docs/Data-insights/Features/Services/traces.md b/docs/Data-insights/Features/Services/traces.md index e7e2ad1f..e9ec003e 100644 --- a/docs/Data-insights/Features/Services/traces.md +++ b/docs/Data-insights/Features/Services/traces.md @@ -63,7 +63,7 @@ Click the `>` arrow on any row to expand it and see a summary and waterfall time Three buttons in the top right of the expanded view let you: -- **Analyze Trace** - send the trace to OpsPilot AI for analysis +- **Analyze Trace** - send the trace to [Coworker](../OpsPilot/Coworker/chat.md) for analysis - **Expand all** - expand all spans in the waterfall at once - **Collapse all** - collapse all spans in the waterfall at once diff --git a/docs/Data-insights/Features/explore-traces.md b/docs/Data-insights/Features/explore-traces.md index b9f3648b..5e34a28f 100644 --- a/docs/Data-insights/Features/explore-traces.md +++ b/docs/Data-insights/Features/explore-traces.md @@ -99,11 +99,19 @@ Clicking a **Trace Name** link opens a detail panel showing the full trace water The waterfall view shows each span as a horizontal bar, positioned on a timeline from 0 to the total trace duration. Each row shows the **service name**, **operation**, and **duration**, and a **Logs** button to view logs related to that span. -Use **Span Filters** to narrow the spans shown, and **Prev** / **Next** to step through them. The total span count is shown above the waterfall (e.g., *3 spans*). +Above the waterfall, **Filter by attribute or text** narrows the spans shown, with three quick filters beside it: + +| Filter | Shows | +|---|---| +| **Critical path** | Only the spans on the trace's critical path - the chain that determined its total duration | +| **Errors** | Only spans that errored | +| **High latency** | Only the slowest spans | + +The matching span count is shown alongside (for example, *1 spans*), with arrows to step through the matches and a **Show all spans** toggle to drop the filter again. ### Analyze Trace -Click **Analyze Trace** in the top right to open a deeper breakdown of the trace, including span-level metrics and structure. +Click **Analyze Trace** in the top right to send the trace to [Coworker](OpsPilot/Coworker/chat.md), which analyzes where the time went and what is worth looking at. --- diff --git a/docs/Data-insights/Features/overview.md b/docs/Data-insights/Features/overview.md index d836c534..9d012cee 100644 --- a/docs/Data-insights/Features/overview.md +++ b/docs/Data-insights/Features/overview.md @@ -8,7 +8,7 @@ The **Overview** page is your observability dashboard at a glance. It gives you Once your environment is sending data, the Overview page shows a full observability summary. -## Customising your dashboard +## Customizing your dashboard Click the **My dashboard** icon in the top right of the Overview to choose which sections are visible. Tick or untick any section to show or hide it: @@ -30,14 +30,14 @@ Click **Reset to org defaults** to restore the default layout. The **Coworker** panel gives you a live summary of your AI teammate's activity, directly from the Overview page. A **Right now** label shows it reflects the current state. -Four cards summarise what Coworker is doing: +Four cards summarize what Coworker is doing: | Card | Description | |---|---| -| **Critical** | Number of critical situations currently needing attention | -| **Services** | How many different services are currently affected | -| **Checkups** | Checks Coworker has run recently while keeping watch (for example, in the last hour) | -| **Watching** | Number of services and signals Coworker is actively tracking | +| **Critical** | Critical situations needing attention | +| **Services** | How far the problem reaches - its blast radius | +| **Checkups** | Checks Coworker has run in the last hour | +| **Watching** | Signals Coworker is tracking in the background | Below the cards, Coworker surfaces its top **critical situations** - each showing the severity, the affected service, and a one-line summary (for example, *"otlp-fraud-detection-fr heap at 100% - OOM risk"*). Click a situation to open it in the full Coworker view. @@ -94,7 +94,7 @@ Click **Servers ->** to go to the full [Servers](/Data-insights/Features/Servers ![!Screenshot](../../images/applications-overview.png) -The **Applications** section summarises all monitored applications, shown as stat cards with each value's **MIN**, **AVG**, and **MAX** (count-based cards show **SUM**, **AVG**, and **MAX**): +The **Applications** section summarizes all monitored applications, shown as stat cards with each value's **MIN**, **AVG**, and **MAX** (count-based cards show **SUM**, **AVG**, and **MAX**): - **Application names** - the applications included, with a count and a sample of names - **Applications** - total number of applications @@ -121,7 +121,7 @@ The **Alerts** panel shows a live count of alerts grouped by state: | **Recovering** | Alerts returning to a normal state | | **Normal** | Alert rules currently within threshold | -Click **Alerts ->** to go to the full [Alerts](/Data-insights/Features/Alerting/Active-alerts/) view. +Click **Alerts ->** to go to the full [Alerting Status](/Data-insights/Features/New-alerting/status/) view. ### Anomaly Detection @@ -131,6 +131,12 @@ The **Anomaly Detection** panel shows a live count of anomaly alerts by state, m Click **Anomaly Detection ->** to go to the full [Anomaly Detection](/Data-insights/Features/New-alerting/service-anomaly-detectors/) view. +### Incidents + +The **Incidents** panel shows how many incidents are currently **Open**, followed by the most recent ones - each with its title, its severity (such as **SEV-2**), and how long ago it was raised. + +Click **Incidents ->** to go to the full [Incidents](/Data-insights/Features/Incidents/overview/) view. + ### Usage The **Usage** panel shows your current consumption against your plan limits for the current pay period: @@ -160,7 +166,7 @@ If your account has no data yet, each section of the Overview displays a **Get S | **Services** | You'll need an API key to instrument your application with OpenTelemetry. | | **Servers** | Install FusionReactor on your servers to start monitoring. You'll need a license key. | | **Applications** | Install FusionReactor to monitor your applications. You'll need a license key. | -| **Coworker** | Set up your AI coworker to investigate alerts and track ongoing situations across the services you care about. | +| **Coworker** | Set up your AI Coworker to investigate alerts and track ongoing situations across the services you care about. | | **Alerts** | Configure alert rules to monitor your infrastructure. | | **Anomaly Detection** | Enable anomaly detection to automatically detect unusual behavior in your data. | diff --git a/docs/Latest-updates/WhatsNew.md b/docs/Latest-updates/WhatsNew.md index f25cb6be..3177d4c9 100644 --- a/docs/Latest-updates/WhatsNew.md +++ b/docs/Latest-updates/WhatsNew.md @@ -127,7 +127,7 @@ The roadmap for 2026 is anchored around AI and OpenTelemetry - deeper AI-powered
!!! info "Learn more" - [Release notes](https://docs.fusionreactor.io/Latest-updates/release-notes/) + [Release notes](release-notes.md) ## Trace-powered investigations in OpsPilot @@ -237,8 +237,8 @@ Look for the **globe icon** next to the mic in the chat bar. * **Gray icon = OFF** (uses only internal knowledge) -!!! info "Learn more" - [Web Search Toggle](/Data-insights/Features/OpsPilot/OpsPilot-user-guide/#web-search-toggle) +!!! note + The web search toggle has since been removed from OpsPilot. @@ -389,7 +389,7 @@ With version 1.2.0, OpsPilot introduces exciting new features and improvements t ![!Screenshot](images/OPvision.png) !!! info "Learn more" - [OpsPilot Vision](/Data-insights/Features/OpsPilot/OpsPilot-user-guide/#opspilot-vision) + [Images](/Data-insights/Features/OpsPilot/Coworker/chat/#images) * **Updated FR knowledge base**: OpsPilot has undergone a significant upgrade in its FusionReactor knowledge base, resulting in enhanced proficiency in understanding and addressing issues. With this improvement, OpsPilot can now provide more informed and effective responses when dealing with FusionReactor-related tasks. This advancement promises smoother operations and quicker resolutions, ultimately optimizing system performance and minimizing downtime. diff --git a/docs/Monitor-your-data/OpenTelemetry/Shipping/overview.md b/docs/Monitor-your-data/OpenTelemetry/Shipping/overview.md index 3a148665..36cf66b5 100644 --- a/docs/Monitor-your-data/OpenTelemetry/Shipping/overview.md +++ b/docs/Monitor-your-data/OpenTelemetry/Shipping/overview.md @@ -1,6 +1,6 @@ # Shipping OpenTelemetry data to OpsPilot -Shipping OpenTelemetry (OTel) data to OpsPilot centralizes your observability and enables OpsPilot AI analysis, faster troubleshooting, and cross-tier performance optimization. Using a vendor-agnostic OTLP pipeline ensures your monitoring remains flexible and future-proof. +Shipping OpenTelemetry (OTel) data to OpsPilot centralizes your observability and lets Coworker analyze it, for faster troubleshooting and cross-tier performance optimization. Using a vendor-agnostic OTLP pipeline ensures your monitoring remains flexible and future-proof. To send your telemetry data to OpsPilot, you'll need a component that receives data from your instrumented applications and forwards it via OTLP. There are two recommended options: diff --git a/docs/index.md b/docs/index.md index e87a26df..387b3b7a 100644 --- a/docs/index.md +++ b/docs/index.md @@ -107,10 +107,10 @@ Get metrics, logs, and traces flowing from your infrastructure using **Grafana A ## Step 4 - Get answers with AI -Once data is flowing, OpsPilot's AI works in two ways: +Once data is flowing, **Coworker** goes to work. It is your AI SRE teammate, and it works in two ways: -- **Coworker** - your AI SRE teammate that runs automated investigations in the background, surfaces prioritised insights, and flags issues before they escalate. [Learn more](/Data-insights/Features/OpsPilot/Coworker/overview/) -- **OpsPilot Chat** - ask questions in plain English to query your telemetry, investigate specific issues, or get on-demand AI analysis across metrics, logs, and traces. +- **On its own** - running investigations in the background, surfacing prioritized insights, and flagging issues before they escalate. [Learn more](/Data-insights/Features/OpsPilot/Coworker/overview/) +- **When you ask** - [chat](/Data-insights/Features/OpsPilot/Coworker/chat/) with it in plain English to query your telemetry, investigate a specific issue, or get analysis across metrics, logs, and traces. --- diff --git a/docs/what-is-opspilot.md b/docs/what-is-opspilot.md index 6b7d47bc..2861b837 100644 --- a/docs/what-is-opspilot.md +++ b/docs/what-is-opspilot.md @@ -2,7 +2,7 @@ OpsPilot, formerly FusionReactor Cloud, is an AI-powered observability and operations platform - the AI SRE teammate for teams using OpenTelemetry, Prometheus, Grafana, and existing observability stacks. It continuously monitors your systems, investigates incidents, and helps prevent, detect, and resolve disruptions before they impact customers. -Where traditional monitoring tools surface data and wait for humans to act, OpsPilot adds an agentic AI intelligence layer on top of your existing stack - reasoning across your telemetry, running autonomous investigations, and delivering prioritised, actionable findings around the clock. +Where traditional monitoring tools surface data and wait for humans to act, OpsPilot adds an agentic AI intelligence layer on top of your existing stack - reasoning across your telemetry, running autonomous investigations, and delivering prioritized, actionable findings around the clock. --- @@ -10,11 +10,10 @@ Where traditional monitoring tools surface data and wait for humans to act, OpsP | Capability | What it does | |---|---| -| **Coworker** | Your AI SRE teammate. Runs scheduled and event-driven investigations, surfaces insights, and flags reliability issues proactively | -| **OpsPilot Chat** | On-demand AI analysis. Query your telemetry in plain English, investigate specific issues, and get AI-guided recommendations | +| **Coworker** | Your AI SRE teammate. Runs scheduled and event-driven investigations, surfaces insights, and flags reliability issues proactively. You can also chat with it in plain English to query your telemetry and investigate specific issues | | **Observability** | Full-stack visibility across metrics, logs, traces, services, servers, and applications | | **Alerting** | Granular alert rules with flexible routing and Coworker-powered automatic investigation | -| **Anomaly Detection** | ML-based detection of unusual behaviour across your metrics without manual threshold tuning | +| **Anomaly Detection** | ML-based detection of unusual behavior across your metrics without manual threshold tuning | | **Incident Management** | Structured workspace for tracking and resolving incidents, with AI-assisted root cause analysis | --- @@ -25,7 +24,7 @@ OpsPilot is built on OpenTelemetry and the FusionReactor agent, ingesting all fo **Coworker** - your AI SRE teammate - runs scheduled tasks, monitors specific patterns, and reacts to incoming alerts. It builds memory over time, learning your environment and improving the relevance of its findings with every run. -When something needs human attention, Coworker surfaces a prioritised insight with supporting evidence and recommended actions - so your team knows exactly what to focus on, without having to dig through dashboards. +When something needs human attention, Coworker surfaces a prioritized insight with supporting evidence and recommended actions - so your team knows exactly what to focus on, without having to dig through dashboards. OpsPilot is designed to work with the tools your team already uses. It adds AI SRE and autonomous operations capabilities on top of OpenTelemetry, Prometheus, and Grafana - no migration, no rip-and-replace, no new agents required. @@ -36,8 +35,8 @@ OpsPilot is designed to work with the tools your team already uses. It adds AI S OpsPilot is built for engineering teams responsible for the reliability of production systems: - **SREs and platform engineers** - autonomous monitoring, faster AI incident investigation, reduced alert fatigue -- **Developers** - understand service behaviour, trace errors, and get AI-guided root cause analysis without leaving your workflow -- **Engineering managers** - visibility into reliability trends, observability coverage gaps, and operational health across the organisation +- **Developers** - understand service behavior, trace errors, and get AI-guided root cause analysis without leaving your workflow +- **Engineering managers** - visibility into reliability trends, observability coverage gaps, and operational health across the organization --- @@ -53,7 +52,7 @@ Yes. OpsPilot provides AIOps and AI SRE capabilities for teams using OpenTelemet OpsPilot is designed to add AI SRE capabilities on top of your existing telemetry stack rather than replacing your observability tooling. It works with OpenTelemetry, Prometheus, and Grafana - giving you autonomous operations and AI incident investigation without migration or vendor lock-in. ### What is an AI SRE teammate? -An AI SRE teammate is an autonomous agent that performs the investigative and analytical work of a site reliability engineer - monitoring systems continuously, investigating alerts, identifying root causes, and surfacing prioritised findings - so your human engineers can focus on resolution and improvement rather than triage. +An AI SRE teammate is an autonomous agent that performs the investigative and analytical work of a site reliability engineer - monitoring systems continuously, investigating alerts, identifying root causes, and surfacing prioritized findings - so your human engineers can focus on resolution and improvement rather than triage. ### Does OpsPilot replace my existing observability stack? No. OpsPilot adds an AI intelligence layer on top of your existing stack. It ingests data from OpenTelemetry, Prometheus, Grafana, and the FusionReactor agent, then applies agentic AI to deliver autonomous reliability capabilities your current tools do not provide. diff --git a/mkdocs.yml b/mkdocs.yml index f3ec264d..daaae1c8 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -1,5 +1,5 @@ site_name: OpsPilot Documentation -site_url: https://docs.fusionreactor.io/ +site_url: https://docs.opspilot.com/ repo_name: opspilot repo_url: https://github.com/intergral/opspilot-docs edit_uri: edit/main/docs/ @@ -45,6 +45,7 @@ nav: - Coworker: - Overview: Data-insights/Features/OpsPilot/Coworker/overview.md - Getting started: Data-insights/Features/OpsPilot/Coworker/getting-started.md + - Chat: Data-insights/Features/OpsPilot/Coworker/chat.md - Situations: Data-insights/Features/OpsPilot/Coworker/situations.md - Insights: Data-insights/Features/OpsPilot/Coworker/insights.md - Tasks: @@ -53,6 +54,7 @@ nav: - Event Sources: Data-insights/Features/OpsPilot/Coworker/event-sources.md - Scheduled: Data-insights/Features/OpsPilot/Coworker/scheduled.md - Manage tasks: Data-insights/Features/OpsPilot/Coworker/manage-tasks.md + - Activity: Data-insights/Features/OpsPilot/Coworker/activity.md - Knowledge: Data-insights/Features/OpsPilot/Coworker/knowledge.md - Usage: Data-insights/Features/OpsPilot/Coworker/usage.md - Settings: @@ -62,9 +64,6 @@ nav: - Behavior: Data-insights/Features/OpsPilot/Coworker/Settings/behavior.md - Budget & cost: Data-insights/Features/OpsPilot/Coworker/Settings/budget-cost.md - FAQ: Data-insights/Features/OpsPilot/Coworker/faq.md - - OpsPilot Assistant: - - Overview: Data-insights/Features/OpsPilot/AIoverview.md - - User guide: Data-insights/Features/OpsPilot/OpsPilot-user-guide.md - MCP Interfaces: - OpsPilot MCP: - Overview: Monitor-your-data/MCP/mcp-overview.md @@ -276,6 +275,8 @@ plugins: - redirects: redirect_maps: 'Data-insights/Features/New-alerting/anomaly-detectors.md': 'Data-insights/Features/New-alerting/service-anomaly-detectors.md' + 'Data-insights/Features/OpsPilot/AIoverview.md': 'Data-insights/Features/OpsPilot/Coworker/overview.md' + 'Data-insights/Features/OpsPilot/OpsPilot-user-guide.md': 'Data-insights/Features/OpsPilot/Coworker/chat.md' 'Data-insights/Features/Explore-servers.md': 'Data-insights/Features/Servers/overview.md' 'test.md': 'Admin-and-data/Licensing/Licensing.md' 'fr/help/Licensing.md': 'Admin-and-data/Licensing/Licensing.md' @@ -315,7 +316,7 @@ plugins: 'Cloud/OpenTelemetry/Instrumenting-OTel.md': 'Monitor-your-data/OpenTelemetry/getting-started.md' 'Cloud/guides/explore.md': 'Data-insights/Features/explore.md' 'Cloud/guides/create-dashboard.md': 'Getting-started/Tutorials/create-dashboard.md' - 'Cloud/guides/OpsPilot/OpsPilot-user-guide.md': 'Data-insights/Features/OpsPilot/OpsPilot-user-guide.md' + 'Cloud/guides/OpsPilot/OpsPilot-user-guide.md': 'Data-insights/Features/OpsPilot/Coworker/chat.md' 'Cloud/legal/licenses.md': 'Admin-and-data/Third-Party-Licenses/licenses.md' 'licensing.md': 'Admin-and-data/Licensing/Licensing.md' 'Cloud/billing/overview.md': 'Admin-and-data/Billing/Cloud/overview.md'