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 Sierra conversations into Agent Analytics
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。
The Sierra integration forwards finished Sierra conversations into Agent Analytics. Sierra delivers conversations to a handler you run, through a webhook, Amazon EventBridge, or Google Pub/Sub, or your scheduled job pulls them from an export. The handler maps each conversation to [Agent] events and sends them to the Amplitude HTTP API. Amplitude then builds sessions, turns, and tool calls, and runs built-in signals.
Set up with your AI coding agent (recommended)
Paste this prompt into your AI coding agent, such as Cursor, Claude Code, Windsurf, GitHub Copilot, or Codex. The agent fetches the guide, builds the job, and starts with a dry run.
Connect our Sierra conversations to Amplitude Agent Analytics.
Fetch https://raw.githubusercontent.com/amplitude/Amplitude-AI-Node/main/docs/integrations/sierra.md
and follow "Part 2: Coding agent procedure". Start with a dry run.
The agent stops and asks for values it can't infer, such as which field holds your user ID. Review its changes, then verify with the steps in Get started.
What this means for you
- You run: A handler for Sierra's delivery channel, or a scheduled export job.
- You need: Sierra's payload format, from Sierra's customer documentation. Request access through your Sierra account team. Amplitude built the guide's mapping from Sierra's public materials, so confirm field names against a sample from your account before you rely on it.
- Your conversations must carry: A user ID that matches your product analytics.
What carries over
| Data | Carries over |
|---|---|
| Turns and session grouping | Yes |
| Tool calls with inputs and outputs | Yes, when your feed includes them |
| CSAT | Yes, as [Agent] Score events, when your feed includes it |
| Model, tokens, and cost | Generally not available in Sierra's feed, so these stay empty |
Freshness and limits
- Push delivery: Conversations arrive as Sierra delivers them.
- Scheduled export: Each run re-reads one hour before its watermark to catch late records. Amplitude deduplicates repeat events.
- Rate limits: Respect Sierra's rate limits on any export API.
Get started
Follow the Sierra integration guide. Start with a dry run on a sample payload, check Live Events and the session viewer, then re-send the same conversations to confirm they add no duplicates.
Guide last verified on October 6, 2026, against Sierra's public materials. Sierra is a trademark of its owner. Amplitude isn't affiliated with or endorsed by Sierra.
これは役に立ちましたか？