How to Find the Actual Prompt and Completion Behind a PostHog LLM Event
Written on July 10, 2026
PostHog's LLM analytics logs every model call your app makes as an $ai_generation event, and most of what you'd want (the model, the cost, the token counts, the latency) sits right on that event as properties you can query like any other. The two fields I actually needed while debugging a bad call, the prompt […]
Read more