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/cohere.md

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

Cohere AI Observability installation

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

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 and Python examples on GitHub.

    Install the PostHog SDK and the OpenAI SDK.

    Python

    pip install posthog openai
    

    Node

    npm install @posthog/ai posthog-node openai
    

    Go

    PostHog doesn't have a Go wrapper for this SDK yet. Use the [OpenTelemetry integration](https://posthog.com/docs/ai-observability/installation/opentelemetry) instead.
    
  2. 2

    Configure PostHog

    Required

    Create a PostHog client, then swap in PostHog's OpenAI wrapper, pointed at Cohere.

    Python

    from posthog import Posthog
    from posthog.ai.openai import OpenAI
    import time, uuid, json
    
    posthog = Posthog("<ph_project_token>", host="https://us.i.posthog.com")
    
    client = OpenAI(
        base_url="https://api.cohere.ai/compatibility/v1",
        api_key="<cohere_api_key>",
        posthog_client=posthog,
    )
    

    Node

    import { OpenAI } from '@posthog/ai/openai'
    import { PostHog } from 'posthog-node'
    
    const posthog = new PostHog('<ph_project_token>', { host: 'https://us.i.posthog.com' })
    
    const client = new OpenAI({
      baseURL: 'https://api.cohere.ai/compatibility/v1',
      apiKey: '<cohere_api_key>',
      posthog,
    })
    
  3. 3

    Call Cohere

    Required

    When you use the wrapped client to call Cohere, PostHog automatically captures an $ai_generation event.

    Python

    trace_id = str(uuid.uuid4())
    
    response = client.chat.completions.create(
        model="command-a-03-2025",
        messages=[{"role": "user", "content": "What's the weather in Paris?"}],
        tools=tools,
        posthog_distinct_id="user_123",
        posthog_trace_id=trace_id,
        posthog_properties={
            "$ai_session_id": "conversation-abc",
            "$ai_provider": "cohere",
        },
    )
    

    Node

    const traceId = crypto.randomUUID()
    
    const response = await client.chat.completions.create({
      model: 'command-a-03-2025',
      messages: [{ role: 'user', content: "What's the weather in Paris?" }],
      tools,
      posthogDistinctId: 'user_123',
      posthogTraceId: traceId,
      posthogProperties: {
        $ai_session_id: 'conversation-abc',
        $ai_provider: 'cohere',
      },
    })
    

    Note: If you want to capture LLM events anonymously, omit posthog_distinct_id from the call. 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. 4

    Capture tool calls as spans

    Optional

    For standard responses, the posthog client captures it as a generation. For all tool calls, you must manually capture them as $ai_span events.

    Python

    for call in response.choices[0].message.tool_calls or []:
        start = time.time()
        result = run_tool(call.function.name, json.loads(call.function.arguments))
    
        posthog.capture(
            distinct_id="user_123",
            event="$ai_span",
            properties={
                "$ai_trace_id": trace_id,
                "$ai_session_id": "conversation-abc",
                "$ai_span_id": str(uuid.uuid4()),
                "$ai_span_name": call.function.name,
                "$ai_input_state": call.function.arguments,
                "$ai_output_state": result,
                "$ai_latency": time.time() - start,
            },
        )
    

    Node

    for (const call of response.choices[0].message.tool_calls ?? []) {
      const start = Date.now()
      const result = await runTool(call.function.name, JSON.parse(call.function.arguments))
    
      posthog.capture({
        distinctId: 'user_123',
        event: '$ai_span',
        properties: {
          $ai_trace_id: traceId,
          $ai_session_id: 'conversation-abc',
          $ai_span_id: crypto.randomUUID(),
          $ai_span_name: call.function.name,
          $ai_input_state: call.function.arguments,
          $ai_output_state: result,
          $ai_latency: (Date.now() - start) / 1000,
        },
      })
    }
    

    See spans for the full list of span properties.

  5. 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

  6. 5

    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. |