> AI agents: this is one page from PostHog's docs. Full index of Markdown docs for LLMs: https://posthog.com/llms.txt

# AI Observability

AI Observability captures every call your AI product makes to an LLM – the prompt, the response, the tokens, the cost, the latency, and the tools it reached for along the way – and stitches them into traces you can actually read. When something goes wrong, you see the whole conversation instead of a single failed request.

Because it runs on the same events as the rest of PostHog, every trace comes with the user who triggered it, their [session replay](/docs/session-replay.md), and any [exceptions](/docs/error-tracking.md) the request threw. Use the trace data in [evaluations](/docs/ai-evals.md).

[Get started](/docs/ai-observability/start-here.md)

## Where you can use it

Explore traces and debug your AI product in the PostHog web app, from an MCP client, or through the API.

PostHog Web

Read traces and sessions, watch cost and latency, cluster failures, and test prompts in the playground.

[Explore traces →](/docs/ai-observability/surfaces/web-app.md)

PostHog MCP

Pull up traces, costs, and errors from any MCP client or AI editor while you're still in the code.

[Query traces →](/docs/ai-observability/surfaces/mcp.md)

API

Send traces in, query them back out, and drive evaluations, reviews, and clustering from your own code.

[Use the API →](/docs/ai-observability/surfaces/api.md)

## Where its data comes from

AI Observability runs on the LLM events your app sends to PostHog. Most of them come from an SDK wrapping your model provider, but you can also forward traces from another observability tool or attach feedback from your users.

Traces and spans

Generations, spans, and traces captured by the PostHog SDKs across every model provider and framework.

[Install an SDK →](/docs/ai-observability/installation.md)

Integrations

Forward traces you already collect in Helicone, Langfuse, Traceloop, or Keywords AI.

[Connect a tool →](/docs/ai-observability/integrations.md)

User feedback

Thumbs up and down, ratings, and comments attached to the exact trace they're about.

[Collect feedback →](/docs/ai-observability/collect-user-feedback.md)

### Still have questions?

Ask PostHog AI

### Was this page useful?

HelpfulCould be better