Skip to content

:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.

2.9 KB
Raw Blame

CORRECT usage pattern:

User: How many weekly active users do we have? Assistant: A weekly count is a governed shape, so the catalog comes first. [Runs posthog:exec({ "command": "call metric-list {\"limit\": 100}" })] Assistant: No approved metric covers weekly active users, so I fall through to the query tools and confirm the schema. [Runs posthog:exec({ "command": "search query-trends" }) and posthog:exec({ "command": "search read-data" }) in parallel] Assistant: Let me check the tool descriptions and schemas. [Runs posthog:exec({ "command": "info query-trends" }) and posthog:exec({ "command": "info read-data-schema" }) in parallel] Assistant: I see query-trends needs `series` (array with hint). Let me get the full field schema and discover events. [Runs posthog:exec({ "command": "schema query-trends series" }) and posthog:exec({ "command": "call read-data-schema {\"query\": {\"kind\": \"events\"}}" }) in parallel] Assistant: Now I know the exact series structure and available events. Let me construct the query. [Runs posthog:exec({ "command": "call query-trends {...}" })] User: Create a dashboard for our key revenue metrics Assistant: I'll need dashboard and query tools. Let me search for them. [Runs posthog:exec({ "command": "search dashboard" }) and posthog:exec({ "command": "search execute-sql" }) in parallel] Assistant: Let me check the schemas for the tools I'll need. [Runs posthog:exec({ "command": "info dashboard-create" }) and posthog:exec({ "command": "info execute-sql" }) in parallel] Assistant: Now I have both schemas. Let me start by searching for existing revenue insights. [Makes call commands with correct parameters]

INCORRECT usage patterns — NEVER do this:

User: Show me our feature flags Assistant: [Directly calls posthog:exec({ "command": "call feature-flag-get-all {}" }) with guessed parameters] WRONG: Run `info feature-flag-get-all` once when its schema is missing. User: Query our events Assistant: [Calls three tools in parallel without any `info` calls first] WRONG: Run `info` once for each missing schema. User: Show me a trends chart of signups Assistant: [Runs info query-trends, sees summary with hints, then immediately calls query-trends with guessed series structure] WRONG — info returned a summary with hint: "DO NOT GUESS – run `schema query-trends series` before populating this field". You MUST follow the hint and run `schema` before constructing the series field. User: query pageviews for the last 7 days Assistant: [Runs `info query-trends`, then `call query-trends` with `event: "$pageview"` from the prompt] WRONG — skipped `call read-data-schema {"query": {"kind": "events"}}`. Never query an event name taken or inferred from the prompt — canonical-looking (`$pageview`) or guessed (`downloaded_file`) names still need per-team confirmation.