Docs cleanup

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)
 
 
 

docs/Data-insights/Features/Integrations/Chat/opspilot-mcp.md

@@ -2,15 +2,15 @@
 
 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**.
 
 ---
 
 ## 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.
 

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.
 
 ---

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 |

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.
 
 ---
 

docs/Data-insights/Features/OpsPilot/Coworker/Settings/budget-cost.md

@@ -6,15 +6,15 @@ 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 |
 
 !!! 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.
 
 ---
 

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 |
 |---|---|

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 |
 

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.