Agent Analytics taxonomy

Early Access

This feature is in Early Access. During this time, aspects of the functionality may still be developed, and this documentation may not always be up to date. If you have any questions, contact Amplitude Support.

This page is the reference for the data Agent Analytics produces: every [Agent] event, the properties on the enrichment events, and the default signals. To read these results in the UI, go to Analyze agent results. To emit the events from your code, go to the Agent Analytics SDK.

The taxonomy is configurable and still evolving during Open Beta. Treat the lists below as the default shape, and confirm the live set against your own event stream.

Data hierarchy

Agent Analytics models each agent interaction as a hierarchy:

Session: One job a user hands the agent, from start to finish. Amplitude identifies a session with the [Agent] Session ID property. The agent session differs from Amplitude's standard-analytics session ($session_id), which is the user's app or web visit.
Turn: A single back-and-forth exchange within a session: a user message, the agent's tool calls, and the AI response.
Span: A sub-turn step, such as a tool call, vector search, rerank, or guardrail.

Every user message, AI response, and tool call lands as an independent Amplitude event, so you can use agent data in funnels, cohorts, and retention charts without decomposing a trace first.

Event inventory

Agent Analytics produces these events. Your SDK instrumentation produces the first seven. The server enrichment pipeline produces the rest after a session closes.

Event	Producer	SDK method
`[Agent] User Message`	SDK	`track_user_message()`
`[Agent] AI Response`	SDK	`track_ai_message()`
`[Agent] Tool Call`	SDK	`track_tool_call()`
`[Agent] Embedding`	SDK	`track_embedding()`
`[Agent] Span`	SDK	`track_span()`
`[Agent] Session End`	SDK	`track_session_end()`
`[Agent] Session Enrichment`	SDK	`track_session_enrichment()`
`[Agent] Session Record`	Server enrichment pipeline	Internal
`[Agent] Evaluator Result`	Server enrichment pipeline	Internal
`[Agent] Score`	SDK, or server for feedback	`score()`

SDK events

Your instrumentation produces these events as the agent runs. The [Agent] AI Response event carries the per-response model, provider, token, latency, and cost properties.

[Agent] User Message: a message the user sends to the agent.
[Agent] AI Response: the agent's response, with model, provider, tokens, latency, and cost.
[Agent] Tool Call: a function or tool the agent invokes.
[Agent] Embedding: an embedding or vector-search step.
[Agent] Span: any other pipeline step, such as a rerank or guardrail.
[Agent] Session End: marks the end of a session.
[Agent] Session Enrichment: your own session labels, sent in customer_enriched privacy mode.

Server enrichment events

After a session closes, the enrichment pipeline assesses it and writes two events back to your event stream.

Session Record

[Agent] Session Record lands once per session. It carries the session rollups, the always-on signal results, and quality flags.

Property	Type	Description
`[Agent] Turn Count`	number	Number of turns in the session.
`[Agent] Session Total Tokens`	number	Total LLM tokens across all turns.
`[Agent] Session Avg Latency Ms`	number	Average AI response latency in milliseconds across the session.
`[Agent] Models Used`	string[]	The LLM models used in the session.
`[Agent] Has Negative Feedback`	boolean	Whether the user expressed dissatisfaction during the session.
`[Agent] Has Technical Failure`	boolean	Whether technical errors occurred, such as tool timeouts or API failures.
`[Agent] Technical Error Count`	number	Count of technical errors in the session.
`[Agent] Has Data Quality Issues`	boolean	Whether the AI output had data quality problems, such as wrong data or hallucinations.
`[Agent] Root Agent Name`	string	The entry-point agent in a multi-agent flow.
`[Agent] Agent Chain Depth`	number	Number of agents in the delegation chain.

Evaluator Result

[Agent] Evaluator Result lands once per evaluator per session. It is the unified event for every server-side evaluation: signal detectors, topic classifiers, and rubric scorers.

Property	Type	Description
`[Agent] Evaluator Name`	string	The evaluator that produced this result.
`[Agent] Output Type`	string	The result shape: `binary`, `classification`, or `score`.
`[Agent] Detected`	boolean	For binary evaluators, whether the condition was detected.
`[Agent] Primary Label`	string	For classification evaluators, the primary label assigned.
`[Agent] Selection Mode`	string	Whether the topic model assigns a `single` label (MECE) or `multiple`.
`[Agent] Topic`	string	Which topic model the classification is for, such as `product_area`.
`[Agent] Rationale`	string	The model's explanation for the result.
`[Agent] Evidence`	string	Supporting evidence the model cited.
`[Agent] Evaluator Model`	string	The LLM that ran the evaluation.
`[Agent] Evaluation Source`	string	Where the evaluation came from: `ai`, `user`, or `reviewer`.
`[Agent] Taxonomy Version`	string	The taxonomy config version that produced this result.
`[Agent] Evaluated At`	number	Epoch milliseconds when the result was computed.

User feedback scores

[Agent] Score records explicit user feedback, such as a thumbs up or down on a response. Scores come from your application through the SDK's score() method, not from the enrichment pipeline. To send scores, go to Send user feedback (scores).

Signals

Signals are the default, always-on evaluators that Amplitude runs on every closed session. They land as [Agent] Evaluator Result events. You don't configure them, and Amplitude refines them over time, so treat them as directional.

Signal	Output	What it measures
Task completion	binary	Whether the agent completed the user's task.
Response quality	score (0.0 to 1.0)	Whether responses were accurate and well-formed.
User friction	binary	Whether the user expressed dissatisfaction.
User intent	classification	The user's intent for the session.
Session safety	classification	Classifies the session as `normal`, `off_topic`, `prompt_injection`, `abuse`, or `probing`.
Data quality	code-based check	Flags wrong data or hallucination patterns. Returns a clear result rather than a generated rationale.

Topics and custom evaluators

Beyond the default signals, you define your own topic models and evaluators. The enrichment taxonomy is fully configurable: topic model names such as query_intent and product_area, and evaluator names such as task_completion, come from configuration and differ per project. To create and refine your own evaluators, go to Create and refine custom evaluators.

Deprecated events

[Agent] Topic Classification is deprecated. Topic classifications now land as [Agent] Evaluator Result events with an output type of classification. Rubric scores also moved off [Agent] Score onto [Agent] Evaluator Result with an output type of score. [Agent] Score now carries user feedback only.

Was this helpful?