For AI agents: a documentation index is available at /docs/llms.txt. Append .md to any page URL for markdown, or send Accept: text/markdown.
Import agent conversations from other tools
このページはまだあなたの言語に翻訳されていません。 現在取り組んでいますので、後でもう一度確認してください。
Agent Analytics integrations bring conversations into Amplitude from where they already live, without the AI SDK in your agent code. Each integration turns finished conversations into the same [Agent] events the AI SDK sends, so sessions, built-in signals, evaluators, and charts work the same way.
Use an integration when your agent runs on a hosted platform, when a tracing tool already records it, or when its conversations land in your warehouse. If you can change the agent's Node or Python code, the AI SDK captures the most detail, including cost, tool inputs, and user feedback. Refer to Instrument your agent with the AI SDK.
Set up with your AI coding agent
Amplitude writes each platform, tracing-tool, and warehouse guide for coding agents as well as engineers. Each one has a "Part 2: Coding agent procedure" that an agent follows from start to finish. Give your agent the page for your source from the table in Choose an integration, or point it at the full list:
- Guides index: https://raw.githubusercontent.com/amplitude/Amplitude-AI-Node/main/docs/integrations/README.md
- Machine-readable list: https://raw.githubusercontent.com/amplitude/Amplitude-AI-Node/main/docs/integrations/manifest.json
How integrations work
Most integrations are a small scheduled job that runs in your infrastructure. The job reads finished conversations from the source, maps them to [Agent] events, and sends them to the Amplitude HTTP API. Warehouse import is the exception: Amplitude runs your SQL on the schedule you set, so you run no job for table rows.
Each integration has a step-by-step guide on GitHub, written for engineers and AI coding agents. Hand a coding agent the guide URL and it can build the job. The docs pages here cover what each path captures and what to decide before you start.
Choose an integration
| Source | Integration | Who moves the data | What you lose compared with the AI SDK |
|---|---|---|---|
| Snowflake, BigQuery, or Databricks tables | Warehouse import | Amplitude imports with your SQL on your schedule | Anything your tables don't record |
| OpenTelemetry, OpenInference, or MLflow spans stored in a table | Warehouse import | Your job replays spans to the OTLP endpoint | Anything your spans don't record |
| LangSmith | LangSmith | Your scheduled job pulls threads | LangSmith feedback scores |
| Langfuse | Langfuse | Your scheduled job pulls sessions | Langfuse scores |
| Braintrust | Braintrust | Your scheduled job runs SQL on project logs | Cost and Braintrust scores |
| Sierra | Sierra | Sierra pushes, or your job pulls exports | Model, tokens, and cost |
| Decagon | Decagon | Your scheduled job pulls exports | Model, tokens, cost, and tool calls |
| Fin by Intercom | Fin | Your scheduled job pulls conversations | Model, tokens, cost, and tool inputs and outputs |
| Salesforce Agentforce | Agentforce | Your scheduled job queries Data Cloud | Cost |
| OpenRouter, LiteLLM, Requesty, or Strands | AI gateways and routers | The AI SDK, or the gateway's OTLP export | Depends on the path |
| Ollama, LM Studio, or another local model | Local models | The AI SDK with manual tracking | Cost |
If your agent already emits OpenTelemetry traces, you can skip the job and add Amplitude as a second OTLP exporter. Refer to Send OpenTelemetry traces to Agent Analytics.
Decide before you build
Every integration needs these values in the source data. The guides stop and ask rather than guess them.
- Conversation ID: The ID that groups messages into one session. The job skips and counts conversations without one, rather than sending them.
- User ID: The same user ID you send in product analytics, so agent sessions join your product data. The job skips conversations without one.
Verify an integration
Each guide starts with a dry run that builds events without sending them. The check-agent-events.mjs script in the integration guides repository checks a sample against the event contract. After the first real run, check Live Events and open a session in Agent Analytics, then run the same window again to confirm that it adds no duplicates. Refer to Verify your Agent Analytics instrumentation.
Integration guides were last verified on October 6, 2026.
これは役に立ちましたか？