otel.agnost.ai. Any framework that emits OpenTelemetry spans can ship them straight to Agnost AI: no SDK required.
Quick Setup
Set two environment variables before starting your app:https://otel.agnost.ai/v1/traces.
Framework Guides
Custom Tool Spans
If your stack doesn’t have a framework integration, wrap each agent / tool call in an OTel span. Name the span with atool. prefix so Agnost AI classifies it as a tool call.
1. Install
Already have an OTel SDK and the OTLP exporter installed? Skip. No OTel yet?2. Wire the OTLP exporter pointing at Agnost AI
Already have an OTel TracerProvider? Append Agnost AI as an additional span processor:3. Wrap each agent turn in a span with userId / sessionId
What appears in Agnost AI
- Events: every received span/event.
- Conversations: spans grouped by
agnost.session_id,session.id, or framework-specific session metadata. - Tool calls: spans named with
tool.*or framework tool-call attributes. - Errors: spans marked failed or exceptions recorded on spans.
Verify
- Start your app with the OTel exporter configured.
- Run one agent turn or tool call.
- Open app.agnost.ai.
- Check Events first, then Conversations or Tool calls.
Troubleshooting
- No data: confirm the endpoint is
https://otel.agnost.ai/v1/traceswhen your SDK expects a trace URL. - Wrong org: confirm
X-Agnost-Org-IDis attached to the OTLP exporter. - No input/output text: your framework may not export message content by default, or you may have disabled it.
Next steps
- Events: verify the spans Agnost AI received.
- Tool calls: inspect tool reliability and latency.
- Intents: organize production conversations by what users wanted.