AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

instrument-llm-analytics

Add PostHog AI Observability to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. Also handles initial PostHog SDK setup if not yet installed.

Original source
posthog
License
MIT
Pinned revision
cac7c80a9e5b73484d18eda1bffb47297c938e0c

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

Ask your assistant

Use Agentic Memory skills to read posthog--instrument-llm-analytics at revision cac7c80a9e5b73484d18eda1bffb47297c938e0c, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 40

references/mastra.md

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

Mastra AI Observability installation

Canonical URL: https://posthog.com/docs/ai-observability/installation/mastra

Cloud region: This page uses US Cloud hosts. For an EU Cloud project, use https://eu.i.posthog.com instead of https://us.i.posthog.com (ingestion host), and use https://eu.posthog.com instead of https://app.posthog.com (app host for links).

On this page

Let AI instrument your LLM calls for you

Skip the manual setup — run this in your project and the wizard installs the SDK and wires up AI Observability for you.

npx @posthog/wizard ai-observability

PostHog Wizard hedgehog

Let AI instrument your LLM calls for you

  1. 1

    Install dependencies

    Required

    Full working examples

    See the complete Node.js example on GitHub. If you're using the PostHog SDK wrapper instead, see the Node.js wrapper example.

    Install Mastra with the official @mastra/posthog exporter. Mastra's observability system sends traces to PostHog as $ai_generation events automatically.

    npm install @mastra/core @mastra/observability @mastra/posthog
    
  2. 2

    Configure Mastra with the PostHog exporter

    Required

    Initialize Mastra with an Observability config that uses the PosthogExporter. Pass your PostHog project token and host from your project settings.

    import { Mastra } from '@mastra/core'
    import { Agent } from '@mastra/core/agent'
    import { Observability } from '@mastra/observability'
    import { PosthogExporter } from '@mastra/posthog'
    
    const weatherAgent = new Agent({
      id: 'weather-agent',
      name: 'Weather Agent',
      instructions: 'You are a helpful assistant with access to weather data.',
      model: { id: 'openai/gpt-4o-mini' },
    })
    
    const mastra = new Mastra({
      agents: { weatherAgent },
      observability: new Observability({
        configs: {
          posthog: {
            serviceName: 'my-app',
            exporters: [
              new PosthogExporter({
                apiKey: '<ph_project_token>',
                host: 'https://us.i.posthog.com',
                defaultDistinctId: 'user_123', // fallback if no userId in metadata
              }),
            ],
          },
        },
      }),
    })
    
  3. 3

    Run your agent

    Required

    Use Mastra as normal. The PosthogExporter automatically captures $ai_generation events for each LLM call, including token usage, cost, latency, and the full conversation.

    Pass tracingOptions.metadata to generate() to attach per-request metadata. The userId field maps to PostHog's distinct ID, sessionId maps to $ai_session_id, and any other keys are passed through as custom event properties.

    const agent = mastra.getAgent('weatherAgent')
    
    const result = await agent.generate("What's the weather in Dublin?", {
      tracingOptions: {
        metadata: {
          userId: 'user_123', // becomes distinct_id
          sessionId: 'session_abc', // becomes $ai_session_id
          conversation_id: 'abc-123', // custom property
        },
      },
    })
    
    console.log(result.text)
    

    Note: If you want to capture LLM events anonymously, omit userId from tracingOptions.metadata and don't set defaultDistinctId. See our docs on anonymous vs identified events to learn more.

    You can expect captured $ai_generation events to have the following properties:

    | Property | Description | | --- | --- | | $ai_model | The specific model, like gpt-5-mini or claude-4-sonnet | | $ai_latency | The latency of the LLM call in seconds | | $ai_time_to_first_token | Time to first token in seconds (streaming only) | | $ai_tools | Tools and functions available to the LLM | | $ai_input | List of messages sent to the LLM | | $ai_input_tokens | The number of tokens in the input (often found in response.usage) | | $ai_output_choices | List of response choices from the LLM | | $ai_output_tokens | The number of tokens in the output (often found in response.usage) | | $ai_total_cost_usd | The total cost in USD (input + output) | | [...] | See full list of properties |

  4. Verify traces and generations

    Recommended

    Confirm LLM events are being sent to PostHog

    Let's make sure LLM events are being captured and sent to PostHog. Under AI Observability, you should see rows of data appear in the Traces and Generations tabs.

    LLM generations in PostHog

    Check for LLM events in PostHog

  5. 4

    Next steps

    Recommended

    Now that you're capturing AI conversations, continue with the resources below to learn what else AI Observability enables within the PostHog platform.

    | Resource | Description | | --- | --- | | Basics | Learn the basics of how LLM calls become events in PostHog. | | Generations | Read about the $ai_generation event and its properties. | | Traces | Explore the trace hierarchy and how to use it to debug LLM calls. | | Spans | Review spans and their role in representing individual operations. | | Anaylze LLM performance | Learn how to create dashboards to analyze LLM performance. |