diff --git a/agent-quickstart/elixir.mdx b/agent-quickstart/elixir.mdx
new file mode 100644
index 00000000..6e6ca43d
--- /dev/null
+++ b/agent-quickstart/elixir.mdx
@@ -0,0 +1,234 @@
+---
+title: "Elixir Agent Quickstart"
+description: "Canonical Firecrawl Elixir quickstart for external agents using search, scrape, and interact."
+og:title: "Elixir Agent Quickstart | Firecrawl"
+og:description: "Canonical Firecrawl Elixir quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Elixir Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl using the official Elixir SDK. It is generated from SDK source and OpenAPI spec.
+
+## Install
+
+Add to your `mix.exs`:
+
+```elixir
+defp deps do
+  [
+    {:firecrawl, "~> 1.9"}
+  ]
+end
+```
+
+Then run:
+
+```bash
+mix deps.get
+```
+
+## Authenticate
+
+Configure via application config:
+
+```elixir
+# config/config.exs
+config :firecrawl, api_key: "fc-YOUR_API_KEY"
+```
+
+Or pass the API key per-request via the `opts` keyword:
+
+```elixir
+Firecrawl.search_and_scrape([query: "example"], api_key: "fc-YOUR_API_KEY")
+```
+
+For self-hosted instances, set the base URL:
+
+```elixir
+config :firecrawl,
+  api_key: "fc-YOUR_API_KEY",
+  base_url: "https://your-firecrawl-instance.com/v2"
+```
+
+The default base URL is `"https://api.firecrawl.dev/v2"`. Omitting the API key enables the keyless free tier (rate-limited per IP).
+
+## When To Use What
+
+- **`search_and_scrape`** -- Use when you start with a query and need to discover relevant URLs and their content. Returns categorized results from web, news, and images.
+- **`scrape_and_extract_from_url`** -- Use when you already have a URL and want to extract page content in structured formats (markdown, HTML, JSON, screenshots, etc.).
+- **`interact_with_scrape_browser_session`** -- Use when the page needs post-scrape browser actions: running code in the live browser session.
+
+## Search
+
+### Why use it
+
+Search finds relevant pages across the web for a given query, optionally scraping the results. It returns results grouped by source type.
+
+### Preferred SDK function
+
+```elixir
+Firecrawl.search_and_scrape(params, opts \\ [])
+Firecrawl.search_and_scrape!(params, opts \\ [])
+```
+
+### Example
+
+```elixir
+{:ok, results} = Firecrawl.search_and_scrape(
+  query: "firecrawl web scraping API",
+  limit: 5,
+  highlights: true
+)
+
+IO.inspect(results)
+```
+
+The bang variant raises `Firecrawl.Error` on failure:
+
+```elixir
+results = Firecrawl.search_and_scrape!(
+  query: "firecrawl web scraping API",
+  limit: 5
+)
+```
+
+### Parameters
+
+All parameters are passed as a keyword list. Only `query` is required.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `:string` | The search query (required). |
+| `limit` | `:integer` | Maximum number of results to return. |
+| `sources` | `{:list, :any}` | Source types to search. Defaults to `["web"]`. |
+| `categories` | `{:list, :any}` | Filter results by category. |
+| `include_domains` | `{:list, :string}` | Only include results from these domains. |
+| `exclude_domains` | `{:list, :string}` | Exclude results from these domains. |
+| `tbs` | `:string` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `:string` | Geographic location for search results (e.g. `"San Francisco,California,United States"`). |
+| `country` | `:string` | ISO country code for geo-targeting (e.g. `"US"`). |
+| `ignore_invalid_urls` | `:boolean` | Exclude invalid URLs from results. |
+| `timeout` | `:integer` | Timeout in milliseconds. |
+| `highlights` | `:boolean` | Generate query-relevant highlights. Defaults to `true`. |
+| `scrape_options` | `:keyword_list` | Options for scraping search results. Accepts the same parameters as scrape. |
+| `enterprise` | `{:list, :string}` | Enterprise ZDR options: `["zdr"]` or `["anon"]`. |
+
+## Scrape
+
+### Why use it
+
+Scrape extracts content from a single URL and returns it in one or more formats: markdown, HTML, raw HTML, JSON (via schema), screenshots, links, images, audio, video, and more.
+
+### Preferred SDK function
+
+```elixir
+Firecrawl.scrape_and_extract_from_url(params, opts \\ [])
+Firecrawl.scrape_and_extract_from_url!(params, opts \\ [])
+```
+
+### Example
+
+```elixir
+{:ok, doc} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com",
+  formats: ["markdown", "links"]
+)
+
+IO.puts(doc["data"]["markdown"])
+```
+
+### Parameters
+
+All parameters are passed as a keyword list. Only `url` is required.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `:string` | The URL to scrape (required). |
+| `formats` | `{:list, :any}` | Output formats: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"json"`, `"audio"`, `"video"`, etc. |
+| `headers` | `:any` | Custom HTTP headers (cookies, user-agent, etc.). |
+| `include_tags` | `{:list, :string}` | Only include content from these HTML tags. |
+| `exclude_tags` | `{:list, :string}` | Exclude content from these HTML tags. |
+| `only_main_content` | `:boolean` | Only return main content, excluding navbars, footers, etc. |
+| `timeout` | `:integer` | Timeout in milliseconds. Default: `60000`, Min: `1000`, Max: `300000`. |
+| `wait_for` | `:integer` | Wait time in milliseconds before scraping. |
+| `mobile` | `:boolean` | Scrape as a mobile device. |
+| `parsers` | `{:list, :any}` | File processing control (e.g. PDF settings). |
+| `actions` | `{:list, :any}` | Actions to execute before content extraction. |
+| `location` | `:keyword_list` | Geolocation settings. Defaults to US. |
+| `skip_tls_verification` | `:boolean` | Skip TLS certificate verification. |
+| `remove_base64_images` | `:boolean` | Remove base64-encoded images from markdown output. |
+| `block_ads` | `:boolean` | Block advertisements and cookie popups. |
+| `proxy` | `{:in, [:basic, :enhanced, :auto]}` | Proxy type. |
+| `max_age` | `:integer` | Use cached result if younger than this many milliseconds. Defaults to 2 days. |
+| `min_age` | `:integer` | Cache-only mode; minimum age in milliseconds. |
+| `store_in_cache` | `:boolean` | Whether to cache the result. |
+| `lockdown` | `:boolean` | Only serve previously cached results. |
+| `redact_pii` | `:boolean` | Redact personally identifiable information. |
+| `audit_metadata` | `:keyword_list` | User attribution for SIEM logging. Keys: `username` (required). |
+| `profile` | `:keyword_list` | Persistent browser storage across sessions. |
+| `zero_data_retention` | `:boolean` | Enable zero data retention. |
+
+## Interact
+
+### Why use it
+
+Interact lets you execute code in a live browser session that was opened by a prior scrape call. Use it for clicking buttons, filling forms, navigating multi-step flows, or extracting dynamic content.
+
+### Preferred SDK function
+
+```elixir
+Firecrawl.interact_with_scrape_browser_session(job_id, params, opts \\ [])
+Firecrawl.interact_with_scrape_browser_session!(job_id, params, opts \\ [])
+```
+
+### Example
+
+```elixir
+{:ok, doc} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com",
+  formats: ["markdown"]
+)
+
+job_id = doc["data"]["metadata"]["jobId"]
+
+{:ok, result} = Firecrawl.interact_with_scrape_browser_session(job_id,
+  code: "document.querySelector('button.load-more').click()",
+  language: :node,
+  timeout: 30
+)
+
+IO.inspect(result)
+```
+
+### Parameters
+
+The `job_id` is passed as the first positional argument. Remaining parameters are a keyword list.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `String.t()` | The scrape job ID from a prior scrape call (required, first argument). |
+| `code` | `:string` | Code to execute in the browser sandbox (required). |
+| `language` | `{:in, [:python, :node, :bash]}` | Language for code execution. |
+| `timeout` | `:integer` | Execution timeout in seconds. |
+| `origin` | `:string` | Origin label for telemetry. |
+
+### Stopping a session
+
+```elixir
+{:ok, result} = Firecrawl.stop_interactive_scrape_browser_session(job_id)
+```
+
+## Notes
+
+- **Naming style:** Function names and parameters use snake_case, matching Elixir conventions. The SDK converts to camelCase for the API automatically.
+- **OpenAPI-generated:** The Elixir SDK is auto-generated from the OpenAPI spec. Function names match the OpenAPI operation IDs directly (e.g. `scrape_and_extract_from_url` rather than just `scrape`).
+- **Return values:** Regular functions return `{:ok, response}` or `{:error, %Firecrawl.Error{}}`. Bang variants (`!`) return the response directly or raise.
+- **No deprecated aliases:** The Elixir SDK does not have deprecated method aliases.
+- **Per-request options:** The trailing `opts` keyword list can include `api_key:` and `base_url:` to override the application config for a single request.
+- **Origin:** The SDK automatically injects `"elixir-sdk@{version}"` as the origin in every request body.
+
+## Source Of Truth
+
+- `/firecrawl/apps/elixir-sdk/lib/firecrawl.ex`
+- `/firecrawl/apps/elixir-sdk/mix.exs`
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/java.mdx b/agent-quickstart/java.mdx
new file mode 100644
index 00000000..1bdb8360
--- /dev/null
+++ b/agent-quickstart/java.mdx
@@ -0,0 +1,264 @@
+---
+title: "Java Agent Quickstart"
+description: "Canonical Firecrawl Java quickstart for external agents using search, scrape, and interact."
+og:title: "Java Agent Quickstart | Firecrawl"
+og:description: "Canonical Firecrawl Java quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Java Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl using the official Java SDK. It is generated from SDK source and OpenAPI spec.
+
+## Install
+
+**Gradle:**
+
+```kotlin
+implementation("com.firecrawl:firecrawl-java:1.12.1")
+```
+
+**Maven:**
+
+```xml
+<dependency>
+    <groupId>com.firecrawl</groupId>
+    <artifactId>firecrawl-java</artifactId>
+    <version>1.12.1</version>
+</dependency>
+```
+
+## Authenticate
+
+```java
+import com.firecrawl.client.FirecrawlClient;
+
+FirecrawlClient client = FirecrawlClient.builder()
+    .apiKey("fc-YOUR_API_KEY")
+    .build();
+```
+
+Or from environment variables:
+
+```java
+FirecrawlClient client = FirecrawlClient.fromEnv();
+// Reads FIRECRAWL_API_KEY env var, then firecrawl.apiKey system property
+```
+
+Builder options:
+
+```java
+FirecrawlClient client = FirecrawlClient.builder()
+    .apiKey("fc-YOUR_API_KEY")
+    .apiUrl("https://api.firecrawl.dev")  // default; override for self-hosted
+    .timeoutMs(300_000)                    // default: 5 minutes
+    .maxRetries(3)                         // default
+    .backoffFactor(0.5)                    // default
+    .build();
+```
+
+Omitting the API key enables the keyless free tier (rate-limited per IP).
+
+## When To Use What
+
+- **`search`** -- Use when you start with a query and need to discover relevant URLs and their content. Returns categorized results from web, news, and images.
+- **`scrape`** -- Use when you already have a URL and want to extract page content in structured formats (markdown, HTML, JSON, screenshots, etc.).
+- **`interact`** -- Use when the page needs post-scrape browser actions: running code in the live browser session.
+
+## Search
+
+### Why use it
+
+Search finds relevant pages across the web for a given query, optionally scraping the results. It returns results grouped by source type (web, news, images).
+
+### Preferred SDK method
+
+```java
+client.search(query)
+client.search(query, options)
+```
+
+### Example
+
+```java
+import com.firecrawl.models.SearchOptions;
+import com.firecrawl.models.SearchData;
+
+SearchData results = client.search("firecrawl web scraping API",
+    SearchOptions.builder()
+        .limit(5)
+        .highlights(true)
+        .build()
+);
+
+for (var result : results.getWeb()) {
+    System.out.println(result.get("title") + " " + result.get("url"));
+}
+```
+
+Async variant:
+
+```java
+CompletableFuture<SearchData> future = client.searchAsync("firecrawl", options);
+```
+
+### Parameters
+
+All fields on `SearchOptions` are nullable. Uses the builder pattern.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `String` | The search query (required, first positional argument). |
+| `sources` | `List<Object>` | Source types: `"web"`, `"news"`, `"images"` as strings or `{type: "web"}` maps. |
+| `categories` | `List<Object>` | Filter by category: `"github"`, `"research"`, `"pdf"`. |
+| `includeDomains` | `List<String>` | Only include results from these domains. |
+| `excludeDomains` | `List<String>` | Exclude results from these domains. |
+| `limit` | `Integer` | Maximum number of results to return. |
+| `tbs` | `String` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `String` | Geographic location for search results. |
+| `ignoreInvalidURLs` | `Boolean` | Exclude invalid URLs from results. |
+| `timeout` | `Integer` | Timeout in milliseconds. |
+| `highlights` | `Boolean` | Generate query-relevant highlights. Defaults to `true`. |
+| `scrapeOptions` | `ScrapeOptions` | Options applied when scraping search result pages. |
+| `integration` | `String` | Integration identifier. |
+
+## Scrape
+
+### Why use it
+
+Scrape extracts content from a single URL and returns it in one or more formats: markdown, HTML, raw HTML, JSON (via schema), screenshots, links, images, audio, video, and more.
+
+### Preferred SDK method
+
+```java
+client.scrape(url)
+client.scrape(url, options)
+```
+
+### Example
+
+```java
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.Document;
+
+Document doc = client.scrape("https://example.com",
+    ScrapeOptions.builder()
+        .formats(List.of("markdown", "links"))
+        .build()
+);
+
+System.out.println(doc.getMarkdown());
+System.out.println(doc.getLinks());
+```
+
+Async variant:
+
+```java
+CompletableFuture<Document> future = client.scrapeAsync("https://example.com", options);
+```
+
+### Parameters
+
+All fields on `ScrapeOptions` are nullable. Uses the builder pattern.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `String` | The URL to scrape (required, first positional argument). |
+| `formats` | `List<Object>` | Output formats. String values: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"screenshot"`, `"json"`, `"audio"`, `"video"`. Also accepts format config objects (`JsonFormat`, `QuestionFormat`, `HighlightsFormat`). |
+| `headers` | `Map<String, String>` | Custom HTTP headers sent with the request. |
+| `includeTags` | `List<String>` | Only include content from these HTML tags. |
+| `excludeTags` | `List<String>` | Exclude content from these HTML tags. |
+| `onlyMainContent` | `Boolean` | Only return main content, excluding navbars, footers, etc. |
+| `timeout` | `Integer` | Timeout in milliseconds. |
+| `waitFor` | `Integer` | Wait time in milliseconds before scraping. |
+| `mobile` | `Boolean` | Scrape as a mobile device. |
+| `parsers` | `List<Object>` | File processing control (e.g. `"pdf"` or `Map.of("type", "pdf", "maxPages", 10)`). |
+| `actions` | `List<Map<String, Object>>` | Actions to execute before content extraction (click, write, press, scroll, wait, screenshot, scrape, executeJavascript, pdf). |
+| `location` | `LocationConfig` | Geolocation config with `country` and `languages` fields. |
+| `skipTlsVerification` | `Boolean` | Skip TLS certificate verification. |
+| `removeBase64Images` | `Boolean` | Remove base64-encoded images from markdown output. |
+| `blockAds` | `Boolean` | Block advertisements and cookie popups. |
+| `proxy` | `String` | Proxy mode: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`, or custom URL. |
+| `maxAge` | `Long` | Use cached result if younger than this many milliseconds. |
+| `storeInCache` | `Boolean` | Whether to cache the result. |
+| `lockdown` | `Boolean` | Only serve previously cached results. |
+| `redactPII` | `Boolean` | Redact personally identifiable information. |
+| `auditMetadata` | `AuditMetadata` | User attribution for SIEM logging. Constructor takes `username: String`. |
+| `integration` | `String` | Integration identifier. |
+
+## Interact
+
+### Why use it
+
+Interact lets you execute code in a live browser session that was opened by a prior `scrape` call. Use it for clicking buttons, filling forms, navigating multi-step flows, or extracting dynamic content.
+
+### Preferred SDK method
+
+```java
+client.interact(jobId, code)
+client.interact(jobId, code, language, timeout)
+client.interact(jobId, code, language, timeout, origin)
+```
+
+### Example
+
+```java
+import com.firecrawl.models.BrowserExecuteResponse;
+
+Document doc = client.scrape("https://example.com",
+    ScrapeOptions.builder().formats(List.of("markdown")).build()
+);
+
+String jobId = (String) doc.getMetadata().get("jobId");
+
+BrowserExecuteResponse result = client.interact(
+    jobId,
+    "document.querySelector('button.load-more').click()",
+    "node",  // language (default: "node")
+    30       // timeout in seconds (default: 30)
+);
+
+System.out.println(result.getStdout());
+```
+
+Async variant:
+
+```java
+CompletableFuture<BrowserExecuteResponse> future = client.interactAsync(jobId, code);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `String` | The scrape job ID from a prior `scrape` call (required). |
+| `code` | `String` | Code to execute in the browser sandbox (required). |
+| `language` | `String` | Language for code execution: `"python"`, `"node"`, `"bash"`. Defaults to `"node"`. |
+| `timeout` | `Integer` | Execution timeout in seconds (1-300). Defaults to `30`. |
+| `origin` | `String` | Origin label for telemetry. Auto-set to `"java-sdk@{version}"`. |
+
+### Stopping a session
+
+```java
+BrowserDeleteResponse deleteResult = client.stopInteractiveBrowser(jobId);
+System.out.println(deleteResult.getCreditsBilled());
+```
+
+## Notes
+
+- **Naming style:** All parameters use camelCase, matching Java conventions.
+- **Builder pattern:** `ScrapeOptions` and `SearchOptions` use the builder pattern: `ScrapeOptions.builder().formats(...).build()`.
+- **Async:** Every method has an async variant returning `CompletableFuture<T>` (e.g. `scrapeAsync`, `searchAsync`, `interactAsync`).
+- **Deprecated aliases:** The following methods are marked `@Deprecated`:
+  - `scrapeExecute()` → use `interact()`
+  - `deleteScrapeBrowser()` → use `stopInteractiveBrowser()`
+  - `QueryFormat` class → use `QuestionFormat` or `HighlightsFormat`
+- **Format objects:** Use `JsonFormat`, `QuestionFormat`, or `HighlightsFormat` classes for structured format options in `ScrapeOptions.formats`.
+- **Search response:** `SearchData` returns `List<Map<String, Object>>` for `.getWeb()`, `.getNews()`, `.getImages()`.
+
+## Source Of Truth
+
+- `/firecrawl/apps/java-sdk/src/main/java/com/firecrawl/client/FirecrawlClient.java`
+- `/firecrawl/apps/java-sdk/src/main/java/com/firecrawl/models/ScrapeOptions.java`
+- `/firecrawl/apps/java-sdk/src/main/java/com/firecrawl/models/SearchOptions.java`
+- `/firecrawl/apps/java-sdk/build.gradle.kts`
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/node.mdx b/agent-quickstart/node.mdx
new file mode 100644
index 00000000..471d46fe
--- /dev/null
+++ b/agent-quickstart/node.mdx
@@ -0,0 +1,219 @@
+---
+title: "Node.js Agent Quickstart"
+description: "Canonical Firecrawl Node.js quickstart for external agents using search, scrape, and interact."
+og:title: "Node.js Agent Quickstart | Firecrawl"
+og:description: "Canonical Firecrawl Node.js quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Node.js Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl using the official Node.js/TypeScript SDK. It is generated from SDK source and OpenAPI spec.
+
+## Install
+
+```bash
+npm install @mendable/firecrawl-js
+```
+
+## Authenticate
+
+```typescript
+import Firecrawl from "@mendable/firecrawl-js";
+
+const firecrawl = new Firecrawl("fc-YOUR_API_KEY");
+```
+
+Or pass an options object:
+
+```typescript
+const firecrawl = new Firecrawl({
+  apiKey: "fc-YOUR_API_KEY",
+  apiUrl: "https://api.firecrawl.dev", // default; override for self-hosted
+});
+```
+
+The SDK reads `FIRECRAWL_API_KEY` and `FIRECRAWL_API_URL` from environment variables as fallbacks.
+
+## When To Use What
+
+- **`search`** -- Use when you start with a query and need to discover relevant URLs and their content. Returns categorized results from web, news, and images.
+- **`scrape`** -- Use when you already have a URL and want to extract page content in structured formats (markdown, HTML, JSON, screenshots, etc.).
+- **`interact`** -- Use when the page needs post-scrape browser actions: running code, clicking elements, filling forms, or executing prompts in the live browser session.
+
+## Search
+
+### Why use it
+
+Search finds relevant pages across the web for a given query, optionally scraping the results. It returns results grouped by source type (web, news, images, developer).
+
+### Preferred SDK method
+
+```typescript
+firecrawl.search(query, options?)
+```
+
+### Example
+
+```typescript
+const results = await firecrawl.search("firecrawl web scraping API", {
+  limit: 5,
+  scrapeOptions: {
+    formats: ["markdown"],
+  },
+});
+
+for (const result of results.web) {
+  console.log(result.title, result.url);
+}
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `string` | The search query (required, first positional argument). |
+| `limit` | `number` | Maximum number of results to return. |
+| `sources` | `Array<"web" \| "news" \| "images">` | Which source types to search. |
+| `categories` | `Array<"github" \| "research" \| "pdf" \| "developer">` | Filter results by category. |
+| `includeDomains` | `string[]` | Only include results from these domains. Cannot be used with `excludeDomains`. |
+| `excludeDomains` | `string[]` | Exclude results from these domains. Cannot be used with `includeDomains`. |
+| `tbs` | `string` | Time-based search filter (e.g. `"qdr:d"` for past day, `"qdr:w"` for past week). |
+| `location` | `string` | Geographic location for search results. |
+| `ignoreInvalidURLs` | `boolean` | Exclude invalid URLs from results. |
+| `timeout` | `number` | Timeout in milliseconds. |
+| `highlights` | `boolean` | Generate query-relevant highlights. Defaults to `true`. |
+| `scrapeOptions` | `ScrapeOptions` | Options applied when scraping search result pages. Accepts the same parameters as `scrape`. |
+| `enterprise` | `Array<"default" \| "anon" \| "zdr">` | Enterprise options for zero data retention. |
+| `threatProtection` | `ThreatProtectionOptions` | Threat protection configuration. |
+| `integration` | `string` | Integration identifier. |
+| `origin` | `string` | Origin label for telemetry. |
+
+## Scrape
+
+### Why use it
+
+Scrape extracts content from a single URL and returns it in one or more formats: markdown, HTML, raw HTML, JSON (via schema), screenshots, links, images, audio, video, and more.
+
+### Preferred SDK method
+
+```typescript
+firecrawl.scrape(url, options?)
+```
+
+### Example
+
+```typescript
+const doc = await firecrawl.scrape("https://example.com", {
+  formats: ["markdown", "links"],
+});
+
+console.log(doc.markdown);
+console.log(doc.links);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `string` | The URL to scrape (required, first positional argument). |
+| `formats` | `FormatOption[]` | Output formats. String values: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"changeTracking"`, `"json"`, `"attributes"`, `"branding"`, `"product"`, `"menu"`, `"audio"`, `"video"`. Also accepts format config objects for `json`, `question`, `highlights`. |
+| `headers` | `Record<string, string>` | Custom HTTP headers sent with the request. |
+| `includeTags` | `string[]` | Only include content from these HTML tags. |
+| `excludeTags` | `string[]` | Exclude content from these HTML tags. |
+| `onlyMainContent` | `boolean` | Only return main content, excluding navbars, footers, etc. |
+| `timeout` | `number` | Timeout in milliseconds. |
+| `waitFor` | `number` | Wait time in milliseconds before scraping (for JS-rendered pages). |
+| `mobile` | `boolean` | Scrape as a mobile device. |
+| `parsers` | `Array<string \| object>` | File processing control (e.g. `"pdf"` or `{ type: "pdf", mode: "ocr", maxPages: 10 }`). |
+| `actions` | `ActionOption[]` | Actions to execute before content extraction (click, write, press, scroll, wait, screenshot, scrape, executeJavascript, pdf). |
+| `location` | `{ country?: string, languages?: string[] }` | Geolocation configuration. |
+| `skipTlsVerification` | `boolean` | Skip TLS certificate verification. |
+| `removeBase64Images` | `boolean` | Remove base64-encoded images from markdown output. |
+| `fastMode` | `boolean` | Enable fast mode for quicker scraping. |
+| `blockAds` | `boolean` | Block advertisements and cookie popups. |
+| `proxy` | `"basic" \| "stealth" \| "enhanced" \| "auto" \| string` | Proxy mode. |
+| `maxAge` | `number` | Use cached result if younger than this many milliseconds. Set to `0` to bypass cache. |
+| `minAge` | `number` | Minimum cache age in milliseconds. |
+| `storeInCache` | `boolean` | Whether to cache the result. |
+| `lockdown` | `boolean` | Only serve previously cached results; never make an outbound request. |
+| `redactPII` | `boolean \| RedactPIIOptions` | Redact personally identifiable information. |
+| `threatProtection` | `ThreatProtectionOptions` | Threat protection configuration. |
+| `auditMetadata` | `{ username: string }` | User attribution for SIEM logging. |
+| `profile` | `{ name: string, saveChanges?: boolean }` | Persistent browser storage across sessions. |
+| `integration` | `string` | Integration identifier. |
+| `origin` | `string` | Origin label for telemetry. |
+
+## Interact
+
+### Why use it
+
+Interact lets you execute code or natural-language prompts in a live browser session that was opened by a prior `scrape` call. Use it for clicking buttons, filling forms, navigating multi-step flows, or extracting dynamic content that requires browser interaction.
+
+### Preferred SDK method
+
+```typescript
+firecrawl.interact(jobId, args)
+```
+
+### Example
+
+```typescript
+const doc = await firecrawl.scrape("https://example.com", {
+  formats: ["markdown"],
+});
+
+const jobId = doc.metadata?.jobId;
+
+const result = await firecrawl.interact(jobId, {
+  code: "document.querySelector('button.load-more').click()",
+  language: "node",
+  timeout: 30,
+});
+
+console.log(result.output);
+```
+
+Or use a natural-language prompt:
+
+```typescript
+const result = await firecrawl.interact(jobId, {
+  prompt: "Click the 'Load More' button and wait for new content",
+  timeout: 30,
+});
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `string` | The scrape job ID from a prior `scrape` call (required, first positional argument). |
+| `code` | `string` | Code to execute in the browser sandbox. Either `code` or `prompt` must be provided. |
+| `prompt` | `string` | Natural-language instruction for the browser. Either `code` or `prompt` must be provided. |
+| `language` | `"python" \| "node" \| "bash"` | Language for code execution. Defaults to `"node"`. |
+| `timeout` | `number` | Execution timeout in seconds. |
+| `origin` | `string` | Origin label for telemetry. |
+
+### Stopping a session
+
+```typescript
+const deleteResult = await firecrawl.stopInteraction(jobId);
+console.log(deleteResult.creditsBilled);
+```
+
+## Notes
+
+- **Naming style:** All parameters use camelCase.
+- **Deprecated aliases:** The following methods still work but should not be used in new code:
+  - `scrapeExecute()` → use `interact()`
+  - `stopInteractiveBrowser()` / `deleteScrapeBrowser()` → use `stopInteraction()`
+  - `scrapeUrl()` → use `scrape()`
+- **Search response shape:** Results are accessed via `.web`, `.news`, `.images`, `.developer` properties. Accessing `.data` throws a helpful error directing you to these properties.
+- **Async client:** The same `Firecrawl` class is async-native (all methods return Promises).
+
+## Source Of Truth
+
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/client.ts`
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/types.ts`
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/methods/scrape.ts`
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/methods/search.ts`
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/python.mdx b/agent-quickstart/python.mdx
new file mode 100644
index 00000000..f18d869c
--- /dev/null
+++ b/agent-quickstart/python.mdx
@@ -0,0 +1,226 @@
+---
+title: "Python Agent Quickstart"
+description: "Canonical Firecrawl Python quickstart for external agents using search, scrape, and interact."
+og:title: "Python Agent Quickstart | Firecrawl"
+og:description: "Canonical Firecrawl Python quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Python Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl using the official Python SDK. It is generated from SDK source and OpenAPI spec.
+
+## Install
+
+```bash
+pip install firecrawl-py
+```
+
+## Authenticate
+
+```python
+from firecrawl import Firecrawl
+
+firecrawl = Firecrawl(api_key="fc-YOUR_API_KEY")
+```
+
+Or with additional options:
+
+```python
+firecrawl = Firecrawl(
+    api_key="fc-YOUR_API_KEY",
+    api_url="https://api.firecrawl.dev",  # default; override for self-hosted
+    timeout=None,       # request timeout in seconds
+    max_retries=3,      # default
+    backoff_factor=0.5,  # default
+)
+```
+
+The SDK reads `FIRECRAWL_API_KEY` from environment variables as a fallback. Omitting the key enables the keyless free tier (rate-limited per IP).
+
+An async client is also available:
+
+```python
+from firecrawl import AsyncFirecrawl
+
+firecrawl = AsyncFirecrawl(api_key="fc-YOUR_API_KEY")
+```
+
+## When To Use What
+
+- **`search`** -- Use when you start with a query and need to discover relevant URLs and their content. Returns categorized results from web, news, and images.
+- **`scrape`** -- Use when you already have a URL and want to extract page content in structured formats (markdown, HTML, JSON, screenshots, etc.).
+- **`interact`** -- Use when the page needs post-scrape browser actions: running code, clicking elements, filling forms, or executing prompts in the live browser session.
+
+## Search
+
+### Why use it
+
+Search finds relevant pages across the web for a given query, optionally scraping the results. It returns results grouped by source type (web, news, images, developer).
+
+### Preferred SDK method
+
+```python
+firecrawl.search(query, **kwargs)
+```
+
+### Example
+
+```python
+results = firecrawl.search(
+    "firecrawl web scraping API",
+    limit=5,
+    scrape_options=ScrapeOptions(formats=["markdown"]),
+)
+
+for result in results.web:
+    print(result.title, result.url)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `str` | The search query (required, first positional argument). |
+| `limit` | `int` | Maximum number of results to return. Default: `5` in SDK. |
+| `sources` | `list[SourceOption]` | Which source types to search (`"web"`, `"news"`, `"images"`). |
+| `categories` | `list[CategoryOption]` | Filter results by category (`"github"`, `"research"`, `"pdf"`, `"developer"`). |
+| `include_domains` | `list[str]` | Only include results from these domains. Cannot be used with `exclude_domains`. |
+| `exclude_domains` | `list[str]` | Exclude results from these domains. Cannot be used with `include_domains`. |
+| `tbs` | `str` | Time-based search filter (e.g. `"qdr:d"` for past day, `"qdr:w"` for past week). |
+| `location` | `str` | Geographic location for search results. |
+| `ignore_invalid_urls` | `bool` | Exclude invalid URLs from results. |
+| `timeout` | `int` | Timeout in milliseconds. Default: `300000` in SDK. |
+| `highlights` | `bool` | Generate query-relevant highlights. Defaults to `True`. |
+| `scrape_options` | `ScrapeOptions` | Options applied when scraping search result pages. Accepts the same parameters as `scrape`. |
+| `enterprise` | `list[str]` | Enterprise options for zero data retention. |
+| `threat_protection` | `ThreatProtectionOptions` | Threat protection configuration. |
+| `integration` | `str` | Integration identifier. |
+
+## Scrape
+
+### Why use it
+
+Scrape extracts content from a single URL and returns it in one or more formats: markdown, HTML, raw HTML, JSON (via schema), screenshots, links, images, audio, video, and more.
+
+### Preferred SDK method
+
+```python
+firecrawl.scrape(url, **kwargs)
+```
+
+### Example
+
+```python
+doc = firecrawl.scrape(
+    "https://example.com",
+    formats=["markdown", "links"],
+)
+
+print(doc.markdown)
+print(doc.links)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `str` | The URL to scrape (required, first positional argument). |
+| `formats` | `list[FormatOption]` | Output formats. String values: `"markdown"`, `"html"`, `"rawHtml"`, `"raw_html"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"changeTracking"`, `"change_tracking"`, `"json"`, `"attributes"`, `"branding"`, `"product"`, `"menu"`, `"audio"`, `"video"`. Also accepts format config objects. |
+| `headers` | `dict[str, str]` | Custom HTTP headers sent with the request. |
+| `include_tags` | `list[str]` | Only include content from these HTML tags. |
+| `exclude_tags` | `list[str]` | Exclude content from these HTML tags. |
+| `only_main_content` | `bool` | Only return main content, excluding navbars, footers, etc. |
+| `timeout` | `int` | Timeout in milliseconds. |
+| `wait_for` | `int` | Wait time in milliseconds before scraping (for JS-rendered pages). |
+| `mobile` | `bool` | Scrape as a mobile device. |
+| `parsers` | `list[str \| PDFParser]` | File processing control (e.g. `"pdf"` or `PDFParser(mode="ocr", max_pages=10)`). |
+| `actions` | `list[Action]` | Actions to execute before content extraction (WaitAction, ClickAction, WriteAction, PressAction, ScrollAction, ScreenshotAction, ScrapeAction, ExecuteJavascriptAction, PDFAction). |
+| `location` | `Location` | Geolocation configuration with `country` and `languages` fields. |
+| `skip_tls_verification` | `bool` | Skip TLS certificate verification. |
+| `remove_base64_images` | `bool` | Remove base64-encoded images from markdown output. |
+| `fast_mode` | `bool` | Enable fast mode for quicker scraping. |
+| `block_ads` | `bool` | Block advertisements and cookie popups. |
+| `proxy` | `str` | Proxy mode: `"basic"`, `"stealth"`, `"enhanced"`, or `"auto"`. |
+| `max_age` | `int` | Use cached result if younger than this many milliseconds. |
+| `store_in_cache` | `bool` | Whether to cache the result. |
+| `lockdown` | `bool` | Only serve previously cached results; never make an outbound request. |
+| `threat_protection` | `ThreatProtectionOptions` | Threat protection configuration. |
+| `audit_metadata` | `AuditMetadata` | User attribution for SIEM logging. |
+| `profile` | `dict` | Persistent browser storage across sessions. |
+| `integration` | `str` | Integration identifier. |
+
+## Interact
+
+### Why use it
+
+Interact lets you execute code or natural-language prompts in a live browser session that was opened by a prior `scrape` call. Use it for clicking buttons, filling forms, navigating multi-step flows, or extracting dynamic content that requires browser interaction.
+
+### Preferred SDK method
+
+```python
+firecrawl.interact(job_id, code=None, *, prompt=None, language="node", timeout=None)
+```
+
+### Example
+
+```python
+doc = firecrawl.scrape("https://example.com", formats=["markdown"])
+
+job_id = doc.metadata.job_id
+
+result = firecrawl.interact(
+    job_id,
+    code="document.querySelector('button.load-more').click()",
+    language="node",
+    timeout=30,
+)
+
+print(result.output)
+```
+
+Or use a natural-language prompt:
+
+```python
+result = firecrawl.interact(
+    job_id,
+    prompt="Click the 'Load More' button and wait for new content",
+    timeout=30,
+)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `str` | The scrape job ID from a prior `scrape` call (required, first positional argument). |
+| `code` | `str` | Code to execute in the browser sandbox. Either `code` or `prompt` must be provided. |
+| `prompt` | `str` | Natural-language instruction for the browser (keyword-only). Either `code` or `prompt` must be provided. |
+| `language` | `Literal["python", "node", "bash"]` | Language for code execution. Defaults to `"node"`. |
+| `timeout` | `int` | Execution timeout in seconds (1-300). |
+| `origin` | `str` | Origin label for telemetry. |
+
+### Stopping a session
+
+```python
+delete_result = firecrawl.stop_interaction(job_id)
+print(delete_result.credits_billed)
+```
+
+## Notes
+
+- **Naming style:** All parameters use snake_case. The SDK handles conversion to camelCase for the API.
+- **Format strings:** Both snake_case (`"raw_html"`, `"change_tracking"`) and camelCase (`"rawHtml"`, `"changeTracking"`) format strings are accepted.
+- **Deprecated aliases:** The following methods still work but should not be used in new code:
+  - `scrape_execute()` → use `interact()`
+  - `stop_interactive_browser()` / `delete_scrape_browser()` → use `stop_interaction()`
+  - `scrape_url()` → use `scrape()`
+- **Search response shape:** Results are accessed via `.web`, `.news`, `.images`, `.developer` properties. Accessing `.data` raises an `AttributeError` with a helpful message directing you to these properties.
+- **Async client:** Use `AsyncFirecrawl` (aliased as `AsyncFirecrawlApp`) for async/await usage. Same method signatures.
+- **Class aliases:** `FirecrawlApp` is an alias for `Firecrawl`.
+
+## Source Of Truth
+
+- `/firecrawl/apps/python-sdk/firecrawl/v2/client.py`
+- `/firecrawl/apps/python-sdk/firecrawl/v2/types.py`
+- `/firecrawl/apps/python-sdk/firecrawl/client.py`
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/rust.mdx b/agent-quickstart/rust.mdx
new file mode 100644
index 00000000..30a94339
--- /dev/null
+++ b/agent-quickstart/rust.mdx
@@ -0,0 +1,256 @@
+---
+title: "Rust Agent Quickstart"
+description: "Canonical Firecrawl Rust quickstart for external agents using search, scrape, and interact."
+og:title: "Rust Agent Quickstart | Firecrawl"
+og:description: "Canonical Firecrawl Rust quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Rust Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl using the official Rust SDK. It is generated from SDK source and OpenAPI spec.
+
+## Install
+
+Add to your `Cargo.toml`:
+
+```toml
+[dependencies]
+firecrawl = "2"
+```
+
+## Authenticate
+
+```rust
+use firecrawl::Client;
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+```
+
+For self-hosted instances:
+
+```rust
+let client = Client::new_selfhosted(
+    "https://your-firecrawl-instance.com",
+    Some("fc-YOUR_API_KEY"),
+)?;
+```
+
+Omitting the API key enables the keyless free tier (rate-limited per IP).
+
+## When To Use What
+
+- **`search`** -- Use when you start with a query and need to discover relevant URLs and their content. Returns categorized results from web, news, and images.
+- **`scrape`** -- Use when you already have a URL and want to extract page content in structured formats (markdown, HTML, JSON, screenshots, etc.).
+- **`interact`** -- Use when the page needs post-scrape browser actions: running code in the live browser session.
+
+## Search
+
+### Why use it
+
+Search finds relevant pages across the web for a given query, optionally scraping the results. It returns results grouped by source type (web, news, images).
+
+### Preferred SDK method
+
+```rust
+client.search(query, options).await
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, SearchOptions, ScrapeOptions};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let response = client.search("firecrawl web scraping API", SearchOptions {
+    limit: Some(5),
+    scrape_options: Some(ScrapeOptions::default()),
+    ..Default::default()
+}).await?;
+
+if let Some(web_results) = response.data.web {
+    for result in web_results {
+        println!("{:?}", result);
+    }
+}
+```
+
+A convenience method is also available:
+
+```rust
+let docs = client.search_and_scrape("firecrawl web scraping", 5).await?;
+```
+
+### Parameters
+
+All fields on `SearchOptions` are `Option` types. The struct derives `Default`.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `impl AsRef<str>` | The search query (required, first positional argument). |
+| `limit` | `Option<u32>` | Maximum number of results. Default: 5, Max: 20. |
+| `sources` | `Option<Vec<SearchSource>>` | Source types: `SearchSource::Web`, `News`, `Images`. |
+| `categories` | `Option<Vec<SearchCategory>>` | Filter by category: `SearchCategory::Github`, `Research`, `Pdf`. |
+| `include_domains` | `Option<Vec<String>>` | Only include results from these domains. |
+| `exclude_domains` | `Option<Vec<String>>` | Exclude results from these domains. |
+| `tbs` | `Option<String>` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `Option<String>` | Geographic location for search results. |
+| `ignore_invalid_urls` | `Option<bool>` | Exclude invalid URLs from results. |
+| `timeout` | `Option<u32>` | Timeout in milliseconds. |
+| `highlights` | `Option<bool>` | Generate query-relevant highlights. Defaults to `true`. |
+| `scrape_options` | `Option<ScrapeOptions>` | Options applied when scraping search result pages. |
+| `integration` | `Option<String>` | Integration identifier. |
+| `origin` | `Option<String>` | Origin label. Auto-set to `"rust-sdk@{version}"`. |
+
+## Scrape
+
+### Why use it
+
+Scrape extracts content from a single URL and returns it in one or more formats: markdown, HTML, raw HTML, JSON (via schema), screenshots, links, images, audio, video, and more.
+
+### Preferred SDK method
+
+```rust
+client.scrape(url, options).await
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, Format};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let doc = client.scrape("https://example.com", ScrapeOptions {
+    formats: Some(vec![Format::Markdown, Format::Links]),
+    ..Default::default()
+}).await?;
+
+if let Some(markdown) = &doc.markdown {
+    println!("{}", markdown);
+}
+```
+
+For structured JSON extraction with a schema:
+
+```rust
+use serde_json::json;
+
+let result = client.scrape_with_schema(
+    "https://example.com",
+    json!({"type": "object", "properties": {"title": {"type": "string"}}}),
+    Some("Extract the page title"),
+).await?;
+```
+
+### Parameters
+
+All fields on `ScrapeOptions` are `Option` types. The struct derives `Default`. Fields serialize to camelCase for the API.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `impl AsRef<str>` | The URL to scrape (required, first positional argument). |
+| `formats` | `Option<Vec<Format>>` | Output formats: `Markdown`, `Html`, `RawHtml`, `Links`, `Images`, `Screenshot`, `Summary`, `ChangeTracking`, `Json`, `Attributes`, `Branding`, `Product`, `Menu`, `Audio`, `Video`. Also object variants: `Question(QuestionFormat)`, `Highlights(HighlightsFormat)`. |
+| `headers` | `Option<HashMap<String, String>>` | Custom HTTP headers sent with the request. |
+| `include_tags` | `Option<Vec<String>>` | Only include content from these HTML tags. |
+| `exclude_tags` | `Option<Vec<String>>` | Exclude content from these HTML tags. |
+| `only_main_content` | `Option<bool>` | Only return main content, excluding navbars, footers, etc. |
+| `timeout` | `Option<u32>` | Timeout in milliseconds. |
+| `wait_for` | `Option<u32>` | Wait time in milliseconds before scraping. |
+| `mobile` | `Option<bool>` | Scrape as a mobile device. |
+| `parsers` | `Option<Vec<ParserConfig>>` | File processing control. `ParserConfig::Simple("pdf")` or `ParserConfig::Pdf { mode, max_pages }`. |
+| `actions` | `Option<Vec<Action>>` | Actions to execute before content extraction: `Wait`, `Screenshot`, `Click`, `Write`, `Press`, `Scroll`, `Scrape`, `ExecuteJavascript`, `Pdf`. |
+| `location` | `Option<LocationConfig>` | Geolocation with `country` and `languages` fields. |
+| `skip_tls_verification` | `Option<bool>` | Skip TLS certificate verification. |
+| `remove_base64_images` | `Option<bool>` | Remove base64-encoded images from markdown output. |
+| `fast_mode` | `Option<bool>` | Enable fast mode for quicker scraping. |
+| `block_ads` | `Option<bool>` | Block advertisements and cookie popups. |
+| `proxy` | `Option<ProxyType>` | Proxy mode: `Basic`, `Stealth`, `Enhanced`, `Auto`. |
+| `max_age` | `Option<u32>` | Use cached result if younger than this many seconds. |
+| `min_age` | `Option<u32>` | Minimum cache age in seconds. |
+| `store_in_cache` | `Option<bool>` | Whether to cache the result. |
+| `lockdown` | `Option<bool>` | Only serve previously cached results. |
+| `redact_pii` | `Option<bool>` | Redact personally identifiable information. |
+| `audit_metadata` | `Option<AuditMetadata>` | User attribution for SIEM logging. Field: `username: String`. |
+| `profile` | `Option<ProfileConfig>` | Persistent browser storage. Fields: `name: String`, `save_changes: Option<bool>`. |
+| `integration` | `Option<String>` | Integration identifier. |
+| `json_options` | `Option<JsonOptions>` | JSON extraction options: `schema`, `system_prompt`, `prompt`. |
+| `screenshot_options` | `Option<ScreenshotOptions>` | Screenshot config: `full_page`, `quality`, `viewport`. |
+| `change_tracking_options` | `Option<ChangeTrackingOptions>` | Change tracking config: `modes`, `schema`, `prompt`, `tag`. |
+| `attribute_selectors` | `Option<Vec<AttributeSelector>>` | Attribute selectors: `selector`, `attribute`. |
+| `origin` | `Option<String>` | Origin label. Auto-set to `"rust-sdk@{version}"`. |
+
+## Interact
+
+### Why use it
+
+Interact lets you execute code in a live browser session that was opened by a prior `scrape` call. Use it for clicking buttons, filling forms, navigating multi-step flows, or extracting dynamic content.
+
+### Preferred SDK method
+
+```rust
+client.interact(job_id, options).await
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, ScrapeExecuteOptions, Format};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let doc = client.scrape("https://example.com", ScrapeOptions {
+    formats: Some(vec![Format::Markdown]),
+    ..Default::default()
+}).await?;
+
+let job_id = doc.metadata
+    .as_ref()
+    .and_then(|m| m.job_id.as_ref())
+    .expect("job_id required for interact");
+
+let result = client.interact(job_id, ScrapeExecuteOptions {
+    code: Some("document.querySelector('button.load-more').click()".into()),
+    language: None, // defaults to Node
+    timeout: Some(30),
+    ..Default::default()
+}).await?;
+
+println!("{:?}", result.stdout);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `impl AsRef<str>` | The scrape job ID from a prior `scrape` call (required, first positional argument). |
+| `code` | `Option<String>` | Code to execute in the browser sandbox. Either `code` or `prompt` must be provided. |
+| `prompt` | `Option<String>` | Natural-language instruction for the browser. Either `code` or `prompt` must be provided. |
+| `language` | `Option<ScrapeExecuteLanguage>` | Language for code execution: `Python`, `Node`, `Bash`. Defaults to `Node`. |
+| `timeout` | `Option<u32>` | Execution timeout in seconds. |
+| `origin` | `Option<String>` | Origin label. Auto-set to `"rust-sdk@{version}"`. |
+
+### Stopping a session
+
+```rust
+let delete_result = client.stop_interaction(job_id).await?;
+println!("Credits billed: {:?}", delete_result.credits_billed);
+```
+
+## Notes
+
+- **Naming style:** Struct fields use snake_case in Rust. They serialize to camelCase for the API via serde.
+- **Async:** All methods are async and return `Result<T, FirecrawlError>`.
+- **Deprecated aliases:** The following methods still work but are marked `#[deprecated]`:
+  - `scrape_execute()` → use `interact()`
+  - `stop_interactive_browser()` / `delete_scrape_browser()` → use `stop_interaction()`
+- **`max_age` / `min_age` units:** The Rust SDK uses seconds for these fields, unlike JS/Python which use milliseconds.
+- **Search response:** `SearchData.web` contains `Vec<SearchResultOrDocument>`, a custom enum that distinguishes between web result metadata and full scraped documents.
+
+## Source Of Truth
+
+- `/firecrawl/apps/rust-sdk/src/v2/client.rs`
+- `/firecrawl/apps/rust-sdk/src/v2/scrape.rs`
+- `/firecrawl/apps/rust-sdk/src/v2/search.rs`
+- `/firecrawl/apps/rust-sdk/Cargo.toml`
+- `/firecrawl-docs/api-reference/v2-openapi.json`