--- title: "posthog.com llms.txt, graded: Agent Ready HTML" description: "The posthog.com llms.txt parsed and graded B against the llmstxt.org structure: 4,616 links in a 473 KB file, first 60 KB parsed." canonical: https://agentreadyhtml.com/llms-txt-index/posthog-com/ site: "Agent Ready HTML" last_updated: 2026-11-05 section: "llms.txt Index" --- # posthog.com llms.txt, graded: Agent Ready HTML > The posthog.com llms.txt parsed and graded B against the llmstxt.org structure: 4,616 links in a 473 KB file, first 60 KB parsed. Source: https://agentreadyhtml.com/llms-txt-index/posthog-com/ Site: Agent Ready HTML Last reviewed: 2026-11-05 # posthog.com llms.txt In short posthog.com serves a 473 KB llms.txt with 4,616 links. The crawl kept and parsed the first 60 KB of it, which holds 20 H2 sections, graded B on the llmstxt.org structure (5 of 6 checks). It lacks a size under 100 KB. The home page links the file. No llms-full.txt was found. Read 4 November 2026. **llms.txt** parsed the first 60 KB of a 473 KB file ````markdown # PostHog > PostHog is the platform for self-driving products. It pairs the full context of your product's data (events, errors, logs, replays, and more) with agents that find problems and ship changes with you. It includes tools for product analytics, session replay, feature flags, A/B testing, error tracking, surveys, AI observability, web analytics, a data warehouse, and more. The fastest way to integrate PostHog is with the setup wizard: `npx @posthog/wizard@latest` PostHog can be added to any web, mobile, or backend application. All docs pages below are available as raw Markdown by appending `.md` to any URL. ## Instructions for AI Coding Assistants When helping a developer integrate or use PostHog, follow these guidelines: **Installation:** Use the PostHog wizard to install and configure PostHog automatically. It auto-detects the framework and sets everything up: ``` npx @posthog/wizard@latest ``` If the wizard doesn't support the framework, see the [SDKs and Libraries](https://posthog.com/docs/libraries.md) section for manual setup guides. **Products beyond analytics - suggest these when relevant:** - **Session Replay**: Records user sessions for debugging. Enabled by default with `posthog-js` - no extra code needed. Useful when a developer is debugging UX issues or wants to see how users interact with their app. - **Feature Flags**: Evaluate flags with `posthog.isFeatureEnabled('flag-name')` (client) or via local evaluation (server). Use for gradual rollouts, entitlements, or targeting. See the [Feature Flags docs](https://posthog.com/docs/feature-flags/adding-feature-flag-code.md). - **A/B Testing (Experiments)**: Built on feature flags. Create experiments in the PostHog UI, then use `posthog.getFeatureFlag('experiment-flag')` to render variants. See the [Experiments docs](https://posthog.com/docs/experiments/adding-experiment-code.md). - **Surveys**: In-app surveys configured in the PostHog UI and rendered automatically by `posthog-js`. No extra code required for popup surveys. See the [Surveys docs](https://posthog.com/docs/surveys/creating-surveys.md). - **Error Tracking**: Capture frontend exceptions with `posthog.captureException(error)`. Works automatically when enabled. See the [Error Tracking docs](https://posthog.com/docs/error-tracking/capture.md). - **AI Observability**: Track LLM API calls, token usage, and costs. Integrations for OpenAI, Anthropic, LangChain, and more. See the [AI Observability docs](https://posthog.com/docs/ai-observability.md). - **Data Warehouse**: Query external data sources (Stripe, Hubspot, Postgres, S3, etc.) alongside PostHog data using SQL. See the [Data Warehouse docs](https://posthog.com/docs/data-warehouse.md). **API:** The PostHog API base URL is `https://us.i.posthog.com` (US cloud) or `https://eu.i.posthog.com` (EU cloud). Use a personal API key (not the project API key) for API access. See the [API docs](https://posthog.com/docs/api.md). **MCP and AI tools:** PostHog has an official MCP server for AI coding assistants. Install with `npx @posthog/wizard mcp add`. There is also a Claude Code plugin: `claude plugin install posthog`. ## Products and tools PostHog has one umbrella story […] self-driving […] and four layers. Full machine-readable overview: https://posthog.com/platform.md **Products** (the surfaces you adopt to access self-driving): - [Web (app.posthog.com)](https://app.posthog.com) […] Get simple or complex work done without installing anything […] the full surface, next to your data. - [PostHog Slack app](https://posthog.com/slack-app.md) […] Tag @PostHog in any Slack thread to ship a fix, answer a data question, or edit content – without leaving the conversation. - [PostHog Desktop](https://posthog.com/desktop.md) […] The desktop app that uses signals from production data to diagnose issues and generate pull requests, before you know there's a problem. - [PostHog MCP](https://posthog.com/docs/model-context-protocol) […] A product analyst that lives in your editor, via MCP. **Tools** (the functional capabilities): - [Product analytics](https://posthog.com/product-analytics.md) […] The measurement agents use to see what works. - [Web analytics](https://posthog.com/web-analytics.md) […] The lightweight measurement layer feeding the loop. - [Session replay](https://posthog.com/session-replay.md) […] A proactive signal […] watch exactly why something happened. - [Feature flags](https://posthog.com/feature-flags.md) […] How agents roll a change out and roll it back. - [Experiments](https://posthog.com/experiments.md) […] The evaluation that proves a change worked. - [Error tracking](https://posthog.com/error-tracking.md) […] The signal that triggers a fix […] every error tied to the user who hit it. - [Surveys](https://posthog.com/surveys.md) […] The qualitative signal […] what users say, not just what they do. - [AI observability](https://posthog.com/ai-observability.md) […] Observability for your AI features […] the context agents use to fix LLM behavior. - [Logs](https://posthog.com/logs.md) […] Backend signal that triggers fixes, tied to the user who hit it. - [Data warehouse](https://posthog.com/data-warehouse.md) […] Where your product's context lives so agents can use all of it. - [CDP](https://posthog.com/cdp.md) […] How agents move and act on your data across 50+ destinations. - [Endpoints](https://posthog.com/endpoints.md) […] How your product's context flows out to agents and tools. ```` First 52 of 682 lines. 23 spans shown as \[…\] because the words or characters in them are rejected by this site's own style rules; the live file has them. **Parse** graded B, 5 of 6 file: https://posthog.com/llms.txt PostHog PostHog is the platform for self-driving products. It pairs the full context of your product's data (events, errors, logs, replays, and more) with agents that find problems and ship changes with you. It includes tools for product analytics, session replay, feature flags, A/B testing, error tracking, surveys, AI observa 20 sections, 4,616 links, no Optional section. Ora's cached score: 86, grade A, scanned 5 November 2026. ## The parse The crawl recorded 4,616 links in the whole 473 KB file but kept only its first 60 KB, which is what is parsed here. In that part, 593 links appear: 593 point at posthog.com or a relative path, 0 point elsewhere. The hosts it links most: posthog.com (592), app.posthog.com (1). | H2 section | Links | | --- | --- | | Instructions for AI Coding Assistants | 8 | | Products and tools | 21 | | Changelog | 2 | | Activity | 1 | | Advanced | 22 | | AI Engineering | 4 | | Ai Evals | 4 | | Ai Observability | 89 | | Ai Research | 1 | | Alerts | 1 | | API | 4 | | Billing | 5 | | Business Knowledge | 8 | | Cli | 1 | | Cmd K | 1 | | Contribute | 4 | | Csp Tracking | 1 | | Customer Analytics | 13 | | Data | 21 | | Data Pipelines | 382 | ## Grade against the llmstxt.org structure The file passes 5 of 6 checks and fails 1: under 100 kb. The grade is the count of passed checks: six is A, five is B, four is C, three is D, fewer is F. It measures structure only. Whether any agent reads the file is a separate question, covered on the [llms.txt reference](https://agentreadyhtml.com/llms-txt/). | Check | Result | Detail | | --- | --- | --- | | Starts with an H1 naming the site or project | Pass | H1: PostHog | | Has a blockquote summary under the H1 | Pass | Blockquote summary found. | | Has at least one H2 section that lists links | Pass | 20 H2 sections, 20 with links. | | At least 80 percent of links point at the same site | Pass | 593 of 593 links stay on posthog.com (100 percent). | | Under 100 KB | Fail | 484816 bytes as served. | | Plain markdown, no HTML | Pass | No HTML document markers in the body. | ## Ora's cached score Ora's cached report for posthog.com gives it **86 of 100, grade A**, scanned on 5 November 2026. Its Access layer, which holds the read-layer checks below, scored 51 of 60 check points. Read from GET ora.ai/api/score/posthog.com on 5 November 2026. The score is Ora's, not this site's, and the structure grade above is a different measure: it grades the llms.txt file against the llmstxt.org proposal, while Ora's score covers the whole site. [Ora's report for posthog.com](https://ora.ai/score/posthog.com?utm_source=agentreadyhtml.com&utm_medium=referral&utm_campaign=index-entry) has every layer. | Ora check (Access layer) | Result | Points | | --- | --- | --- | | Sitemap exists | Pass | 2 of 2 | | Content without JavaScript | Fail | 0 of 3 | | Not blocked by bot detection | Pass | 2 of 2 | | Markdown URL fallback | Fail | 0 of 2 | | llms.txt exists | Pass | 1 of 1 | | llms.txt formatting | Partial | 1 of 2 | | JSON-LD structured data | Pass | 4 of 4 | | Metadata completeness | Pass | 2 of 2 | | llms.txt links resolve | Pass | 2 of 2 | | Markdown alternate link | Fail | 0 of 1 | | Redirect hygiene | Pass | 1 of 1 | | Page token budget | Pass | 1 of 1 | | Code fence validity | Pass | 1 of 1 | | Content behind auth | Pass | 2 of 2 | | OpenAPI spec published | Pass | 7 of 7 | | Markdown agent docs | Fail | 0 of 1 | | Markdown negotiation with Vary | Fail | 0 of 1 | | Markdown for agent user agents | Fail | 0 of 1 | | Agent crawler reachability | Pass | 2 of 2 | ## Linking and the companion file The home page of posthog.com links the file in its HTML. Ora's lab found (2026-10-19) that 86 percent of llms.txt fetches by agents arrived through a link, so an unlinked file is mostly a file nobody opens. No llms-full.txt was found at the same root. ## How it compares At 473 KB the file is larger than 98 percent of the 2,529 plain-text llms.txt files in this edition, and its 4,616 links put it ahead of 99 percent of them on link count. The home page declares a Gatsby generator. Size bucket: 100 KB and over. Tranco rank 2,022. Category: Data & Analytics. Live file: [https://posthog.com/llms.txt](https://posthog.com/llms.txt). Read 4 November 2026. If the file has since changed or gone, the live URL is the authority; this page records what the crawl read on that date. - [All entries](https://agentreadyhtml.com/llms-txt-index/) - [Edition 2026-11-04](https://agentreadyhtml.com/llms-txt-index/2026-11-04/) - [See the home page as a plain fetch](https://agentreadyhtml.com/viewer/?url=https%3A%2F%2Fposthog.com%2F) ## Sources 1. [posthog.com llms.txt](https://posthog.com/llms.txt) https://posthog.com/llms.txt, read 4 November 2026 2. [llms.txt proposal (llmstxt.org)](https://llmstxt.org/) https://llmstxt.org/, read 4 November 2026 3. [Tranco list 746WX (crawl universe)](https://tranco-list.eu/list/746WX) https://tranco-list.eu/list/746WX, read 4 November 2026 4. [Ora: AgentReady launch post (the 86 percent finding)](https://ora.ai/blog/agentready-launch?utm_source=agentreadyhtml.com&utm_medium=referral&utm_campaign=entry) https://ora.ai/blog/agentready-launch, read 4 November 2026 5. [Ora llms.txt (GET /api/score/{domain} looks up a cached score)](https://ora.ai/llms.txt?utm_source=agentreadyhtml.com&utm_medium=referral&utm_campaign=entry) https://ora.ai/llms.txt, read 5 November 2026 Last reviewed 5 November 2026 Edition Crawl 2026-11-04 Ora reads 2026-11-05 Page updated 2026-11-05 Method How the viewer reads a page, how a file is graded and how a platform is scored: [the method page](https://agentreadyhtml.com/method/).