Docs/Observability

Observability

Observability is the foundation of the platform: every call your AI app makes is captured as a trace, broken down into nested observations, and enriched with cost, latency, token usage, and quality scores. From there you can debug a single request, follow a multi-turn conversation, or analyze usage by person.

New here? Start with Sending Data In to instrument your app, then come back to explore your traces.

The data model

ConceptWhat it is
TraceOne end-to-end request or run of your app (e.g. a single chat turn or API call). The top-level unit.
ObservationA step inside a trace. Three kinds: spans (work/tool calls), generations (LLM calls, with model, tokens, cost), and events (point-in-time logs). Observations nest to form a tree.
SessionA group of related traces sharing a sessionId — e.g. a whole conversation.
UserAn end user (userId) attached to traces, enabling per-person analytics.
ScoreA quality/evaluation value attached to a trace or observation — from the API, an evaluator, or human annotation.
text
Session Trace (one request) Span: "retrieve context" Generation: "embed query" (model, tokens, cost) Generation: "answer" (model, tokens, cost, latency) Event: "guardrail checked" + Scores: quality=0.9, helpfulness="good"

In this section

© 2026 ANTS Platform, Inc.Docs v1.0 · Last updated June 2026