diff --git a/agent-quickstart/elixir.mdx b/agent-quickstart/elixir.mdx
new file mode 100644
index 000000000..297780888
--- /dev/null
+++ b/agent-quickstart/elixir.mdx
@@ -0,0 +1,189 @@
+---
+title: "Elixir Agent Quickstart"
+description: "Canonical Firecrawl Elixir quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Elixir Agent Quickstart
+
+Canonical quickstart for external agents. Generated from SDK source (`firecrawl` hex package **1.9.1**) and the v2 OpenAPI spec. Function names are auto-generated from the OpenAPI spec and match the SDK exactly.
+
+## Install
+
+```elixir
+# mix.exs
+defp deps do
+  [
+    {:firecrawl, "~> 1.9"}
+  ]
+end
+```
+
+## Authenticate
+
+```elixir
+# Option 1: Application config
+config :firecrawl, api_key: "fc-your-api-key"
+
+# Option 2: Per-request in opts
+Firecrawl.scrape_and_extract_from_url([url: "https://example.com"], api_key: "fc-...")
+```
+
+All functions accept `api_key` and `base_url` (default `"https://api.firecrawl.dev/v2"`) in the trailing `opts` keyword list.
+
+## When To Use What
+
+- `search_and_scrape`: use when you start with a query and need discovery.
+- `scrape_and_extract_from_url`: use when you already have a URL and want page content.
+- `interact_with_scrape_browser_session`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK function
+
+`Firecrawl.search_and_scrape(params, opts \\ [])` → `{:ok, Req.Response.t()} | {:error, Exception.t()}`
+
+Bang variant: `Firecrawl.search_and_scrape!(params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, response} = Firecrawl.search_and_scrape(
+  query: "site:docs.firecrawl.dev webhook retries",
+  limit: 5,
+  scrape_options: [formats: ["markdown"]]
+)
+
+results = response.body
+for hit <- results["web"] || [] do
+  IO.puts("#{hit["url"]}: #{String.slice(hit["markdown"] || "", 0..199)}")
+end
+```
+
+### Parameters
+
+| Parameter | Type | JSON key | Description |
+|---|---|---|---|
+| `query` | `:string` (required) | `query` | Search query. Use `site:example.com` to limit to a domain. |
+| `sources` | `{:list, :any}` | `sources` | Which sources: `"web"`, `"news"`, `"images"`. |
+| `categories` | `{:list, :any}` | `categories` | Filter by category: `"github"`, `"research"`, `"pdf"`. |
+| `include_domains` | `{:list, :string}` | `includeDomains` | Only include these domains. |
+| `exclude_domains` | `{:list, :string}` | `excludeDomains` | Exclude these domains. |
+| `limit` | `:integer` | `limit` | Max number of results. |
+| `tbs` | `:string` | `tbs` | Time-based filter (e.g. `qdr:d`). |
+| `location` | `:string` | `location` | Localized results. |
+| `ignore_invalid_urls` | `:boolean` | `ignoreInvalidURLs` | Drop invalid URLs. |
+| `timeout` | `:integer` | `timeout` | Timeout in milliseconds. |
+| `highlights` | `:boolean` | `highlights` | Generate highlights. |
+| `scrape_options` | `:keyword_list` | `scrapeOptions` | Scrape each result (see Scrape parameters). |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK function
+
+`Firecrawl.scrape_and_extract_from_url(params, opts \\ [])` → `{:ok, Req.Response.t()} | {:error, Exception.t()}`
+
+Bang variant: `Firecrawl.scrape_and_extract_from_url!(params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, response} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://docs.firecrawl.dev",
+  formats: ["markdown"],
+  only_main_content: true
+)
+
+doc = response.body["data"]
+IO.puts(doc["markdown"])
+```
+
+### Parameters
+
+| Parameter | Type | JSON key | Description |
+|---|---|---|---|
+| `url` | `:string` (required) | `url` | Target URL. |
+| `formats` | `{:list, :any}` | `formats` | Output formats: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, etc. |
+| `headers` | `:any` | `headers` | Custom HTTP headers. |
+| `include_tags` | `{:list, :string}` | `includeTags` | Only include these HTML tags. |
+| `exclude_tags` | `{:list, :string}` | `excludeTags` | Exclude these HTML tags. |
+| `only_main_content` | `:boolean` | `onlyMainContent` | Strip nav, footer, and boilerplate. |
+| `timeout` | `:integer` | `timeout` | Timeout in milliseconds. |
+| `wait_for` | `:integer` | `waitFor` | Wait for page to render (milliseconds). |
+| `mobile` | `:boolean` | `mobile` | Use a mobile viewport. |
+| `parsers` | `{:list, :any}` | `parsers` | File parsing controls. |
+| `actions` | `{:list, :any}` | `actions` | Pre-scrape browser actions. |
+| `location` | `:keyword_list` | `location` | `[country: ..., languages: [...]]` for geo-aware scraping. |
+| `skip_tls_verification` | `:boolean` | `skipTlsVerification` | Skip TLS verification. |
+| `remove_base64_images` | `:boolean` | `removeBase64Images` | Drop base64 images from markdown output. |
+| `block_ads` | `:boolean` | `blockAds` | Block ads and cookie popups. |
+| `proxy` | `:basic \| :enhanced \| :auto` | `proxy` | Proxy control. |
+| `max_age` | `:integer` | `maxAge` | Use cached data up to this age (milliseconds). |
+| `min_age` | `:integer` | `minAge` | Use cached data only if at least this old (milliseconds). |
+| `store_in_cache` | `:boolean` | `storeInCache` | Cache the result. |
+| `lockdown` | `:boolean` | `lockdown` | Serve from cache only. |
+| `profile` | `:keyword_list` | `profile` | Persistent browser profile. |
+
+## Interact
+
+### Why use it
+
+Use `interact` to run code in the browser session tied to a scrape job. The Elixir SDK accepts `code` (required) and does not support `prompt` — use code-based interaction.
+
+### Preferred SDK function
+
+`Firecrawl.interact_with_scrape_browser_session(job_id, params, opts \\ [])` → `{:ok, Req.Response.t()} | {:error, Exception.t()}`
+
+Bang variant: `Firecrawl.interact_with_scrape_browser_session!(job_id, params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, scrape_response} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com",
+  formats: ["markdown"]
+)
+
+job_id = get_in(scrape_response.body, ["data", "metadata", "scrapeId"])
+
+{:ok, result} = Firecrawl.interact_with_scrape_browser_session(job_id,
+  code: "console.log(await page.title());"
+)
+
+IO.puts(result.body["stdout"])
+```
+
+### Parameters
+
+| Parameter | Type | JSON key | Description |
+|---|---|---|---|
+| `job_id` | `String.t()` (path) | — | Scrape job ID from scrape response metadata. |
+| `code` | `:string` (required) | `code` | Code to execute in the browser session. |
+| `language` | `:python \| :node \| :bash` | `language` | Execution runtime. Default: `"node"` (server-side). |
+| `timeout` | `:integer` | `timeout` | Execution timeout in seconds. |
+
+### Stop session
+
+`Firecrawl.stop_interactive_scrape_browser_session(job_id, opts \\ [])` → `{:ok, Req.Response.t()} | {:error, Exception.t()}`
+
+## Notes
+
+- The Elixir SDK is **auto-generated from the OpenAPI spec** (`generate.exs`). Function names are long and OpenAPI-derived — do not rename them.
+- No deprecated aliases exist in the Elixir SDK.
+- `interact` does not support `prompt` — only code-based interaction is available.
+- The SDK uses `Req` under the hood. Extra `opts` are passed through to `Req`.
+- The proxy parameter accepts atoms (`:basic`, `:enhanced`, `:auto`), not strings.
+- Errors return `{:error, Firecrawl.Error.t()}` with `status` and `body` fields.
+
+## 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 000000000..6bd8d686b
--- /dev/null
+++ b/agent-quickstart/java.mdx
@@ -0,0 +1,221 @@
+---
+title: "Java Agent Quickstart"
+description: "Canonical Firecrawl Java quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Java Agent Quickstart
+
+Canonical quickstart for external agents. Generated from SDK source (`firecrawl-java` **1.14.0**) and the v2 OpenAPI spec. Method names, parameters, and types match `FirecrawlClient`.
+
+## Install
+
+**Gradle (Kotlin DSL):**
+
+```kotlin
+implementation("com.firecrawl:firecrawl-java:1.14.0")
+```
+
+**Maven:**
+
+```xml
+<dependency>
+    <groupId>com.firecrawl</groupId>
+    <artifactId>firecrawl-java</artifactId>
+    <version>1.14.0</version>
+</dependency>
+```
+
+## Authenticate
+
+```java
+import com.firecrawl.client.FirecrawlClient;
+
+FirecrawlClient client = FirecrawlClient.builder()
+    .apiKey(System.getenv("FIRECRAWL_API_KEY"))
+    .build();
+
+// Or read from env automatically:
+FirecrawlClient client = FirecrawlClient.fromEnv();
+```
+
+Builder options: `apiKey` (falls back to `FIRECRAWL_API_KEY` env var, then `firecrawl.apiKey` system property), `apiUrl` (default `"https://api.firecrawl.dev"`, falls back to `FIRECRAWL_API_URL`), `timeoutMs` (default `300000`), `maxRetries` (default `3`), `backoffFactor` (default `0.5`).
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`client.search(query, options)` → `SearchData`
+
+### Example
+
+```java
+import com.firecrawl.models.SearchOptions;
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.SearchData;
+import java.util.List;
+
+SearchData results = client.search(
+    "site:docs.firecrawl.dev webhook retries",
+    SearchOptions.builder()
+        .limit(5)
+        .scrapeOptions(ScrapeOptions.builder()
+            .formats(List.of("markdown"))
+            .onlyMainContent(true)
+            .build())
+        .build()
+);
+
+if (results.getWeb() != null) {
+    for (var hit : results.getWeb()) {
+        System.out.println(hit);
+    }
+}
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `String` | Search query. Use `site:example.com` to limit to a domain. |
+| `options.sources` | `List<Object>` | Which sources: `"web"`, `"news"`, `"images"`. |
+| `options.categories` | `List<Object>` | Filter by category: `"github"`, `"research"`, `"pdf"`. |
+| `options.includeDomains` | `List<String>` | Only include these domains. |
+| `options.excludeDomains` | `List<String>` | Exclude these domains. |
+| `options.limit` | `Integer` | Max number of results. |
+| `options.tbs` | `String` | Time-based filter (e.g. `qdr:d`). |
+| `options.location` | `String` | Localized results. |
+| `options.ignoreInvalidURLs` | `Boolean` | Drop invalid URLs. |
+| `options.timeout` | `Integer` | Timeout in milliseconds. |
+| `options.highlights` | `Boolean` | Generate highlights. Defaults to true. |
+| `options.scrapeOptions` | `ScrapeOptions` | Scrape each result (see Scrape parameters). |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`client.scrape(url, options)` → `Document`
+
+### Example
+
+```java
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.Document;
+import java.util.List;
+
+Document doc = client.scrape(
+    "https://docs.firecrawl.dev",
+    ScrapeOptions.builder()
+        .formats(List.of("markdown"))
+        .onlyMainContent(true)
+        .build()
+);
+
+System.out.println(doc.getMarkdown());
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `String` | Target URL. |
+| `options.formats` | `List<Object>` | Output formats. Strings: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"json"`, `"audio"`, `"video"`. Maps for structured formats like JSON extraction. |
+| `options.headers` | `Map<String, String>` | Custom HTTP headers. |
+| `options.includeTags` | `List<String>` | Only include these HTML tags. |
+| `options.excludeTags` | `List<String>` | Exclude these HTML tags. |
+| `options.onlyMainContent` | `Boolean` | Strip nav, footer, and boilerplate. |
+| `options.timeout` | `Integer` | Timeout in milliseconds. |
+| `options.waitFor` | `Integer` | Wait for page to render (milliseconds). |
+| `options.mobile` | `Boolean` | Use a mobile viewport. |
+| `options.parsers` | `List<Object>` | File parsing controls (e.g. `"pdf"` or PDF config map). |
+| `options.actions` | `List<Map<String, Object>>` | Pre-scrape browser actions. |
+| `options.location` | `LocationConfig` | `{ country, languages }` for geo-aware scraping. |
+| `options.skipTlsVerification` | `Boolean` | Skip TLS verification. |
+| `options.removeBase64Images` | `Boolean` | Drop base64 images from markdown output. |
+| `options.blockAds` | `Boolean` | Block ads and cookie popups. |
+| `options.proxy` | `String` | Proxy control: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`. |
+| `options.maxAge` | `Long` | Use cached data up to this age (milliseconds). |
+| `options.storeInCache` | `Boolean` | Cache the result. |
+| `options.lockdown` | `Boolean` | Serve from cache only, never make outbound request. |
+| `options.redactPII` | `Boolean` | Redact PII from content. |
+| `options.auditMetadata` | `AuditMetadata` | User attribution for SIEM logging. `username` is required. |
+
+## Interact
+
+### Why use it
+
+Use `interact` to run code in the browser session tied to a scrape job. The Java SDK accepts `code` (required) and does not support `prompt` — use code-based interaction.
+
+### Preferred SDK method
+
+`client.interact(jobId, code)` → `BrowserExecuteResponse`
+
+Overloads: `interact(jobId, code, language, timeout)` and `interact(jobId, code, language, timeout, origin)`.
+
+### Example
+
+```java
+import com.firecrawl.models.Document;
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.BrowserExecuteResponse;
+import java.util.List;
+
+Document doc = client.scrape("https://example.com",
+    ScrapeOptions.builder().formats(List.of("markdown")).build());
+
+String jobId = (String) doc.getMetadata().get("scrapeId");
+
+BrowserExecuteResponse result = client.interact(jobId,
+    "console.log(await page.title());");
+
+System.out.println(result.getStdout());
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `String` | Scrape job ID from `document.getMetadata().get("scrapeId")`. |
+| `code` | `String` | Code to execute in the browser session. |
+| `language` | `String` | Execution runtime: `"python"`, `"node"`, `"bash"`. Default: `"node"`. |
+| `timeout` | `Integer` | Execution timeout in seconds (1-300). Default: `30`. |
+| `origin` | `String` | Optional origin label for telemetry. |
+
+### Stop session
+
+`client.stopInteractiveBrowser(jobId)` → `BrowserDeleteResponse`
+
+### Async variants
+
+All methods have `*Async` variants returning `CompletableFuture<...>`:
+- `scrapeAsync(url, options)`
+- `searchAsync(query, options)`
+- `interactAsync(jobId, code, ...)`
+- `stopInteractiveBrowserAsync(jobId)`
+
+## Notes
+
+- Java uses `camelCase` parameter names matching the API directly.
+- `interact` does not support `prompt` — only code-based interaction is available. Use `code` with Playwright page commands.
+- Deprecated aliases: `scrapeExecute` → `interact`; `deleteScrapeBrowser` → `stopInteractiveBrowser`.
+- `FirecrawlClient.fromEnv()` reads `FIRECRAWL_API_KEY` from the environment.
+
+## 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-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/node.mdx b/agent-quickstart/node.mdx
new file mode 100644
index 000000000..423b3d59d
--- /dev/null
+++ b/agent-quickstart/node.mdx
@@ -0,0 +1,177 @@
+---
+title: "Node.js Agent Quickstart"
+description: "Canonical Firecrawl Node.js quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Node.js Agent Quickstart
+
+Canonical quickstart for external agents. Generated from SDK source (`firecrawl` **4.34.0**) and the v2 OpenAPI spec. Method names, parameters, and types match the SDK public API.
+
+## Install
+
+```bash
+npm install firecrawl
+```
+
+## Authenticate
+
+```ts
+import { Firecrawl } from "firecrawl";
+
+const client = new Firecrawl({
+  apiKey: process.env.FIRECRAWL_API_KEY,
+});
+```
+
+Constructor options: `apiKey` (string, falls back to `FIRECRAWL_API_KEY` env var), `apiUrl` (string, falls back to `FIRECRAWL_API_URL` or `https://api.firecrawl.dev`), `timeoutMs` (number), `maxRetries` (number), `backoffFactor` (number).
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or other browser actions after a scrape has created a session.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`client.search(query, options?)` → `Promise<SearchData>`
+
+### Example
+
+```ts
+const results = await client.search("site:docs.firecrawl.dev webhook retries", {
+  limit: 5,
+  scrapeOptions: {
+    formats: ["markdown"],
+    onlyMainContent: true,
+  },
+});
+
+for (const hit of results.web ?? []) {
+  console.log(hit.url, hit.markdown?.slice(0, 200));
+}
+```
+
+### Return value
+
+`SearchData` has optional arrays: `web`, `news`, `images`, `developer`. Each entry is either a lightweight result or a full `Document` when `scrapeOptions` hydrated the hit. Do **not** access `result.data` — it does not exist.
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `string` | Search query. Use `site:example.com` to limit to a domain. |
+| `options.sources` | `("web" \| "news" \| "images")[]` | Which sources to search. |
+| `options.categories` | `("github" \| "research" \| "pdf" \| "developer")[]` | Filter by category. |
+| `options.includeDomains` | `string[]` | Only include these domains. Cannot combine with `excludeDomains`. |
+| `options.excludeDomains` | `string[]` | Exclude these domains. Cannot combine with `includeDomains`. |
+| `options.limit` | `number` | Max number of results. |
+| `options.tbs` | `string` | Time-based filter (e.g. `qdr:d` for past day, `qdr:w` for past week). |
+| `options.location` | `string` | Localized results (e.g. `"San Francisco,California,United States"`). |
+| `options.ignoreInvalidURLs` | `boolean` | Drop URLs that cannot be scraped. |
+| `options.timeout` | `number` | Request timeout in milliseconds. |
+| `options.highlights` | `boolean` | Generate query-relevant highlights. |
+| `options.scrapeOptions` | `ScrapeOptions` | Scrape each search result (see Scrape parameters). |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`client.scrape(url, options?)` → `Promise<Document>`
+
+### Example
+
+```ts
+const doc = await client.scrape("https://docs.firecrawl.dev", {
+  formats: ["markdown"],
+  onlyMainContent: true,
+});
+
+console.log(doc.markdown);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `string` | Target URL. |
+| `options.formats` | `FormatOption[]` | Output formats. Strings: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"changeTracking"`, `"attributes"`, `"branding"`, `"audio"`, `"video"`. Objects: `{ type: "json", prompt?, schema? }`, `{ type: "question", question }`, `{ type: "highlights", query }`, `{ type: "screenshot", fullPage?, quality?, viewport? }`, `{ type: "changeTracking", modes, schema?, prompt?, tag? }`, `{ type: "attributes", selectors: [{ selector, attribute }] }`. |
+| `options.headers` | `Record<string, string>` | Custom HTTP headers. |
+| `options.includeTags` | `string[]` | Only include these HTML tags. |
+| `options.excludeTags` | `string[]` | Exclude these HTML tags. |
+| `options.onlyMainContent` | `boolean` | Strip nav, footer, and boilerplate. |
+| `options.timeout` | `number` | Timeout in milliseconds. |
+| `options.waitFor` | `number` | Wait for page to render (milliseconds). |
+| `options.mobile` | `boolean` | Use a mobile viewport. |
+| `options.parsers` | `("pdf" \| { type: "pdf", mode?, maxPages? })[]` | File parsing controls. |
+| `options.actions` | `ActionOption[]` | Pre-scrape browser actions: `wait`, `click`, `write`, `press`, `scroll`, `screenshot`, `scrape`, `executeJavascript`, `pdf`. |
+| `options.location` | `{ country?, languages? }` | Geo or language-aware scraping. |
+| `options.skipTlsVerification` | `boolean` | Skip TLS verification. |
+| `options.removeBase64Images` | `boolean` | Drop base64 images from markdown output. |
+| `options.fastMode` | `boolean` | Faster scrapes with reduced fidelity. |
+| `options.blockAds` | `boolean` | Block ads and cookie popups. |
+| `options.proxy` | `string` | Proxy control: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`, or a custom URL. |
+| `options.maxAge` | `number` | Use cached data up to this age (milliseconds). |
+| `options.minAge` | `number` | Use cached data only if at least this old (milliseconds). |
+| `options.storeInCache` | `boolean` | Cache the result. |
+| `options.profile` | `{ name, saveChanges? }` | Persistent browser profile shared across scrapes and interactions. |
+
+## Interact
+
+### Why use it
+
+Use `interact` for code or natural-language control of the browser session tied to a scrape job (via `metadata.scrapeId`). The SDK requires at least one of `code` or `prompt`.
+
+### Preferred SDK method
+
+`client.interact(jobId, args)` → `Promise<ScrapeExecuteResponse>`
+
+### Example
+
+```ts
+const doc = await client.scrape("https://example.com", { formats: ["markdown"] });
+const jobId = doc.metadata?.scrapeId;
+if (!jobId) throw new Error("Missing scrapeId from scrape response");
+
+const result = await client.interact(jobId, {
+  prompt: "Click the pricing tab and summarize the plans.",
+});
+console.log(result.output);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `string` | Scrape job ID from `document.metadata.scrapeId`. |
+| `args.code` | `string` | Code to execute in the browser session (e.g. Playwright `page` usage). At least one of `code` or `prompt` required. |
+| `args.prompt` | `string` | Natural-language instruction for the browser agent. At least one of `code` or `prompt` required. |
+| `args.language` | `"python" \| "node" \| "bash"` | Execution runtime. Default: `"node"`. |
+| `args.timeout` | `number` | Execution timeout in seconds. |
+
+### Stop session
+
+`client.stopInteraction(jobId)` → `Promise<ScrapeBrowserDeleteResponse>`
+
+## Notes
+
+- The default `Firecrawl` export is the v2 client; v1 is available via `client.v1`.
+- Deprecated aliases: `scrapeExecute` → `interact`; `stopInteractiveBrowser` and `deleteScrapeBrowser` → `stopInteraction`; `scrapeUrl` → `scrape`.
+- Zod schemas passed in `formats` (for `json` or `changeTracking`) are automatically converted to JSON Schema by the SDK.
+- The package declares **Node.js >= 22** in `engines`.
+
+## Source Of Truth
+
+- `firecrawl/apps/js-sdk/firecrawl/src/index.ts`
+- `firecrawl/apps/js-sdk/firecrawl/src/v2/client.ts`
+- `firecrawl/apps/js-sdk/firecrawl/src/v2/types.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 000000000..f06956804
--- /dev/null
+++ b/agent-quickstart/python.mdx
@@ -0,0 +1,175 @@
+---
+title: "Python Agent Quickstart"
+description: "Canonical Firecrawl Python quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Python Agent Quickstart
+
+Canonical quickstart for external agents. Generated from SDK source (`firecrawl-py` **4.22.1**) and the v2 OpenAPI spec. Method names, parameters, and types match the v2 client in `firecrawl/v2/client.py`.
+
+## Install
+
+```bash
+pip install firecrawl-py
+```
+
+## Authenticate
+
+```python
+import os
+from firecrawl import Firecrawl
+
+client = Firecrawl(api_key=os.environ.get("FIRECRAWL_API_KEY"))
+```
+
+Constructor parameters: `api_key` (str, falls back to `FIRECRAWL_API_KEY` env var), `api_url` (str, default `"https://api.firecrawl.dev"`), `timeout` (float), `max_retries` (int, default `3`), `backoff_factor` (float, default `0.5`).
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`client.search(query, **options)` → `SearchData`
+
+### Example
+
+```python
+results = client.search(
+    "site:docs.firecrawl.dev webhook retries",
+    limit=5,
+    scrape_options={"formats": ["markdown"], "only_main_content": True},
+)
+
+for hit in results.web or []:
+    print(hit.url, (hit.markdown or "")[:200])
+```
+
+### Return value
+
+`SearchData` has optional lists: `web`, `news`, `images`, `developer`. Each entry is either a lightweight result or a full `Document` when `scrape_options` hydrated the hit. Do **not** access `result.data` — it does not exist.
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `str` | Search query. Use `site:example.com` to limit to a domain. |
+| `sources` | `list[str \| Source]` | Which sources to search: `"web"`, `"news"`, `"images"`. |
+| `categories` | `list[str \| Category]` | Filter by category: `"github"`, `"research"`, `"pdf"`. |
+| `include_domains` | `list[str]` | Only include these domains. Cannot combine with `exclude_domains`. |
+| `exclude_domains` | `list[str]` | Exclude these domains. Cannot combine with `include_domains`. |
+| `limit` | `int` | Max number of results. |
+| `tbs` | `str` | Time-based filter (e.g. `qdr:d` for past day, `qdr:w` for past week). |
+| `location` | `str` | Localized results. |
+| `ignore_invalid_urls` | `bool` | Drop URLs that cannot be scraped. |
+| `timeout` | `int` | Request timeout in milliseconds. |
+| `highlights` | `bool` | Generate query-relevant highlights. |
+| `scrape_options` | `ScrapeOptions` | Scrape each search result (see Scrape parameters). |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`client.scrape(url, **options)` → `Document`
+
+### Example
+
+```python
+doc = client.scrape(
+    "https://docs.firecrawl.dev",
+    formats=["markdown"],
+    only_main_content=True,
+)
+
+print(doc.markdown)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `str` | Target URL. |
+| `formats` | `list[FormatOption]` | Output formats. Strings: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"changeTracking"`, `"attributes"`, `"branding"`, `"audio"`, `"video"`. Dicts: `{"type": "json", "prompt": ..., "schema": ...}`, `{"type": "question", "question": ...}`, `{"type": "highlights", "query": ...}`, `{"type": "screenshot", "fullPage": ..., "quality": ..., "viewport": ...}`, `{"type": "changeTracking", "modes": [...], "schema": ..., "prompt": ..., "tag": ...}`, `{"type": "attributes", "selectors": [{"selector": ..., "attribute": ...}]}`. |
+| `headers` | `dict[str, str]` | Custom HTTP headers. |
+| `include_tags` | `list[str]` | Only include these HTML tags. |
+| `exclude_tags` | `list[str]` | Exclude these HTML tags. |
+| `only_main_content` | `bool` | Strip nav, footer, and boilerplate. |
+| `timeout` | `int` | Timeout in milliseconds. |
+| `wait_for` | `int` | Wait for page to render (milliseconds). |
+| `mobile` | `bool` | Use a mobile viewport. |
+| `parsers` | `list[str \| PDFParser]` | File parsing controls. `"pdf"` or `{"type": "pdf", "mode": ..., "max_pages": ...}`. |
+| `actions` | `list[Action]` | Pre-scrape browser actions: `wait`, `click`, `write`, `press`, `scroll`, `screenshot`, `scrape`, `executeJavascript`, `pdf`. |
+| `location` | `Location` | `{"country": ..., "languages": [...]}` for geo-aware scraping. |
+| `skip_tls_verification` | `bool` | Skip TLS verification. |
+| `remove_base64_images` | `bool` | Drop base64 images from markdown output. |
+| `fast_mode` | `bool` | Faster scrapes with reduced fidelity. |
+| `block_ads` | `bool` | Block ads and cookie popups. |
+| `proxy` | `str` | Proxy control: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`, or a custom URL. |
+| `max_age` | `int` | Use cached data up to this age (milliseconds). |
+| `store_in_cache` | `bool` | Cache the result. |
+| `profile` | `dict` | `{"name": ..., "save_changes": ...}` for persistent browser profile. |
+
+## Interact
+
+### Why use it
+
+Use `interact` for code or natural-language control of the browser session tied to a scrape job (via `metadata.scrape_id`). The SDK requires at least one of `code` or `prompt`.
+
+### Preferred SDK method
+
+`client.interact(job_id, code=None, *, prompt=None, language="node", timeout=None)` → `BrowserExecuteResponse`
+
+### Example
+
+```python
+doc = client.scrape("https://example.com", formats=["markdown"])
+job_id = doc.metadata.get("scrapeId") if doc.metadata else None
+if not job_id:
+    raise ValueError("Missing scrapeId from scrape response")
+
+result = client.interact(
+    job_id,
+    prompt="Click the pricing tab and summarize the plans.",
+)
+print(result.output)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `str` | Scrape job ID from `document.metadata["scrapeId"]`. |
+| `code` | `str` | Code to execute in the browser session. At least one of `code` or `prompt` required. |
+| `prompt` | `str` | Natural-language instruction for the browser agent. At least one of `code` or `prompt` required. |
+| `language` | `"python" \| "node" \| "bash"` | Execution runtime. Default: `"node"`. |
+| `timeout` | `int` | Execution timeout in seconds. |
+
+### Stop session
+
+`client.stop_interaction(job_id)` → `BrowserDeleteResponse`
+
+## Notes
+
+- `Firecrawl` is the v2 client. `FirecrawlApp` is a deprecated alias for `Firecrawl`.
+- `AsyncFirecrawl` (alias `AsyncFirecrawlApp`) provides async versions of all methods.
+- Deprecated aliases: `scrape_execute` → `interact`; `stop_interactive_browser` and `delete_scrape_browser` → `stop_interaction`; `scrape_url` → `scrape`.
+- Python uses `snake_case` parameter names. The SDK converts them to `camelCase` for the API.
+
+## Source Of Truth
+
+- `firecrawl/apps/python-sdk/firecrawl/client.py`
+- `firecrawl/apps/python-sdk/firecrawl/v2/client.py`
+- `firecrawl/apps/python-sdk/firecrawl/v2/types.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 000000000..497259672
--- /dev/null
+++ b/agent-quickstart/rust.mdx
@@ -0,0 +1,218 @@
+---
+title: "Rust Agent Quickstart"
+description: "Canonical Firecrawl Rust quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Rust Agent Quickstart
+
+Canonical quickstart for external agents. Generated from SDK source (`firecrawl` crate **2.14.0**) and the v2 OpenAPI spec. Method names, parameters, and types match the v2 client.
+
+## Install
+
+```toml
+[dependencies]
+firecrawl = "2"
+```
+
+## Authenticate
+
+```rust
+use firecrawl::Client;
+
+// Cloud client
+let client = Client::new("fc-your-api-key")?;
+
+// Self-hosted (API key optional for keyless free tier)
+let client = Client::new_selfhosted("https://your-instance.com", Some("fc-..."))?;
+```
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`client.search(query, options)` → `Result<SearchResponse, FirecrawlError>`
+
+### Example
+
+```rust
+use firecrawl::{Client, SearchOptions, ScrapeOptions, Format};
+
+let client = Client::new(std::env::var("FIRECRAWL_API_KEY")?)?;
+
+let response = client.search(
+    "site:docs.firecrawl.dev webhook retries",
+    SearchOptions {
+        limit: Some(5),
+        scrape_options: Some(ScrapeOptions {
+            formats: Some(vec![Format::Markdown]),
+            ..Default::default()
+        }),
+        ..Default::default()
+    },
+).await?;
+
+if let Some(web_results) = &response.data.web {
+    for hit in web_results {
+        println!("{:?}", hit);
+    }
+}
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `impl AsRef<str>` | Search query. Use `site:example.com` to limit to a domain. |
+| `options.limit` | `Option<u32>` | Max number of results. Default: 5, max: 20. |
+| `options.sources` | `Option<Vec<SearchSource>>` | Which sources: `Web`, `News`, `Images`. |
+| `options.categories` | `Option<Vec<SearchCategory>>` | Filter by category: `Github`, `Research`, `Pdf`. |
+| `options.include_domains` | `Option<Vec<String>>` | Only include these domains. |
+| `options.exclude_domains` | `Option<Vec<String>>` | Exclude these domains. |
+| `options.tbs` | `Option<String>` | Time-based filter (e.g. `qdr:d`). |
+| `options.location` | `Option<String>` | Geographic location string. |
+| `options.ignore_invalid_urls` | `Option<bool>` | Drop invalid URLs. |
+| `options.timeout` | `Option<u32>` | Timeout in milliseconds. |
+| `options.highlights` | `Option<bool>` | Generate highlights. Defaults to true. |
+| `options.scrape_options` | `Option<ScrapeOptions>` | Scrape each result (see Scrape parameters). |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`client.scrape(url, options)` → `Result<Document, FirecrawlError>`
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, Format};
+
+let client = Client::new(std::env::var("FIRECRAWL_API_KEY")?)?;
+
+let doc = client.scrape(
+    "https://docs.firecrawl.dev",
+    ScrapeOptions {
+        formats: Some(vec![Format::Markdown]),
+        only_main_content: Some(true),
+        ..Default::default()
+    },
+).await?;
+
+if let Some(md) = &doc.markdown {
+    println!("{}", md);
+}
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `impl AsRef<str>` | Target URL. |
+| `options.formats` | `Option<Vec<Format>>` | Output formats: `Markdown`, `Html`, `RawHtml`, `Links`, `Images`, `Screenshot`, `Summary`, `ChangeTracking`, `Json`, `Attributes`, `Branding`, `Audio`, `Video`. |
+| `options.headers` | `Option<HashMap<String, String>>` | Custom HTTP headers. |
+| `options.include_tags` | `Option<Vec<String>>` | Only include these HTML tags. |
+| `options.exclude_tags` | `Option<Vec<String>>` | Exclude these HTML tags. |
+| `options.only_main_content` | `Option<bool>` | Strip nav, footer, and boilerplate. |
+| `options.timeout` | `Option<u32>` | Timeout in milliseconds. |
+| `options.wait_for` | `Option<u32>` | Wait for page to render (milliseconds). |
+| `options.mobile` | `Option<bool>` | Use a mobile viewport. |
+| `options.parsers` | `Option<Vec<ParserConfig>>` | File parsing controls. |
+| `options.actions` | `Option<Vec<Action>>` | Pre-scrape browser actions. |
+| `options.location` | `Option<LocationConfig>` | `{ country, languages }` for geo-aware scraping. |
+| `options.skip_tls_verification` | `Option<bool>` | Skip TLS verification. |
+| `options.remove_base64_images` | `Option<bool>` | Drop base64 images from markdown output. |
+| `options.fast_mode` | `Option<bool>` | Faster scrapes with reduced fidelity. |
+| `options.block_ads` | `Option<bool>` | Block ads and cookie popups. |
+| `options.proxy` | `Option<ProxyType>` | Proxy control: `Basic`, `Stealth`, `Enhanced`, `Auto`. |
+| `options.max_age` | `Option<u32>` | Use cached data up to this age. |
+| `options.min_age` | `Option<u32>` | Use cached data only if at least this old. |
+| `options.store_in_cache` | `Option<bool>` | Cache the result. |
+| `options.profile` | `Option<ProfileConfig>` | Persistent browser profile. |
+| `options.json_options` | `Option<JsonOptions>` | JSON extraction options (prompt, schema). |
+| `options.screenshot_options` | `Option<ScreenshotOptions>` | Screenshot options (full_page, quality, viewport). |
+| `options.change_tracking_options` | `Option<ChangeTrackingOptions>` | Change tracking options (modes, schema, prompt, tag). |
+| `options.attribute_selectors` | `Option<Vec<AttributeSelector>>` | Attribute extraction selectors. |
+
+### Convenience method
+
+`client.scrape_with_schema(url, schema, prompt)` → `Result<Value, FirecrawlError>`
+
+Calls `scrape()` with `formats: [Json]` and the provided JSON schema and optional prompt. Returns the extracted JSON directly.
+
+## Interact
+
+### Why use it
+
+Use `interact` for code or natural-language control of the browser session tied to a scrape job. The SDK requires at least one of `code` or `prompt`.
+
+### Preferred SDK method
+
+`client.interact(job_id, options)` → `Result<ScrapeExecuteResponse, FirecrawlError>`
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, ScrapeExecuteOptions, Format};
+
+let client = Client::new(std::env::var("FIRECRAWL_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.get("scrapeId"))
+    .and_then(|v| v.as_str())
+    .expect("Missing scrapeId");
+
+let result = client.interact(job_id, ScrapeExecuteOptions {
+    code: Some("console.log(await page.title());".to_string()),
+    ..Default::default()
+}).await?;
+
+println!("{:?}", result.output);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `impl AsRef<str>` | Scrape job ID from document metadata. |
+| `options.code` | `Option<String>` | Code to execute in the browser session. At least one of `code` or `prompt` required. |
+| `options.prompt` | `Option<String>` | Natural-language instruction for the browser agent. At least one of `code` or `prompt` required. |
+| `options.language` | `Option<ScrapeExecuteLanguage>` | Execution runtime: `Python`, `Node`, `Bash`. Default: `Node`. |
+| `options.timeout` | `Option<u32>` | Execution timeout in seconds. |
+
+### Stop session
+
+`client.stop_interaction(job_id)` → `Result<ScrapeBrowserDeleteResponse, FirecrawlError>`
+
+## Notes
+
+- Rust uses `snake_case` field names. The SDK serializes them to `camelCase` for the API.
+- All options structs derive `Default`, so use `..Default::default()` for unset fields.
+- Deprecated aliases: `scrape_execute` → `interact`; `stop_interactive_browser` and `delete_scrape_browser` → `stop_interaction`.
+- The SDK auto-sets `origin` to `"rust-sdk@{version}"` if not provided.
+
+## Source Of Truth
+
+- `firecrawl/apps/rust-sdk/src/client.rs`
+- `firecrawl/apps/rust-sdk/src/scrape.rs`
+- `firecrawl/apps/rust-sdk/src/search.rs`
+- `firecrawl/apps/rust-sdk/src/types.rs`
+- `firecrawl-docs/api-reference/v2-openapi.json`