> 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 pocket guide

[](/pocket-guides.md)Aa

[](/pocket-guides.md)[](/pocket-guides/ai-observability/101.md)

Pocket guide to

# AI Observability – AI Observability pocket guide

Your AI features don't fail loudly. They fail plausibly and confidently, with nothing that looks like an error.

This pocket guide is about seeing what your model actually does in the wild, what it costs, and whether the outputs it returns are what users want.

## Where to start

*New to AI Observability?* Start with [AI Observability 101](/pocket-guides/ai-observability/101.md) on the next page – it explains what data is captured on every LLM call and how to interpret it.

*Already instrumented?* The use cases in **Contents** each include a prompt you can run in PostHog AI to build the thing the guide describes.

Either way, they all assume your LLM calls already reach PostHog. If they don't yet, run the wizard command, or [install it yourself](/docs/ai-observability/installation.md):

```
npx @posthog/wizard ai-observability
```

## Contents

-   [AI Observability 101](/pocket-guides/ai-observability/101.md)01
-   [Score your AI's answers with evals](/pocket-guides/ai-observability/quality-output.md)02
-   [Catch a code assistant inventing functions](/pocket-guides/ai-observability/invented-functions.md)03
-   [Attribute AI cost to users and features](/pocket-guides/ai-observability/ai-cost.md)04
-   [Measure whether users keep the answer](/pocket-guides/ai-observability/throw-away-answers.md)05
-   [Debug a wrong answer with traces](/pocket-guides/ai-observability/unexplained-answers.md)06

[‹ Return to bookshelf](/pocket-guides.md)[AI Observability 101 ›](/pocket-guides/ai-observability/101.md)