Trigger an Agent Analytics eval run
Starts an asynchronous eval run and returns it immediately with a pending
status. Poll the run by id, or read results through the Agent Analytics read
surface once it completes.
Target the run either at a dataset or at a session list, not both. Caps are
enforced server-side: 10 evaluators and 100 targeted sessions per run.
For larger datasets, only the first 100 members are targeted and the
acceptance response includes a truncation warning. This selection warning
is not persisted on the run returned by later get/list calls.
/v1/projects/{project_id}/agent-analytics/eval-runsAuthorizations
Authorizationstringrequiredhttp
Path parameters
project_idstringrequiredAmplitude project identifier, backed by the canonical app ID.
12345pattern: ^[0-9]+$Header parameters
Idempotency-KeystringrequiredRequired on write operations. Keys aren't stored yet, so retrying a write with the same key performs it again; a retried create makes another resource. Check whether the first attempt succeeded before you retry.
min length: 8max length: 255Body
application/jsonevaluator_idsstring[]requiredEvaluator version identifiers returned by create or update. Evaluator updates use stable identifiers instead.
dataset_idstringrequiredEvaluate the sessions in this dataset. Mutually exclusive with session_ids; exactly one of the two is required.
session_idsstring[]Evaluate these sessions. Mutually exclusive with dataset_id; exactly one of the two is required.
sample_sizeintegerRetained for compatibility. This endpoint targets explicit session IDs, including when expanding a dataset, so sample_size does not reduce the selected sessions. All supplied IDs are targeted, with dataset expansion capped at the first 100 members.
100min: 1max: 100Response
application/jsondataobjectrequiredShow child attributes
idstringrequiredStable eval run identifier.
objectstringrequiredproject_idstringrequiredevaluator_idsstring[]requiredrun_typestringrequiredstatusstringrequiredLifecycle state of the run.
target_modestringrequiredHow the run selected its sessions, such as by dataset or by filter.
total_sessionsintegerrequiredcompleted_sessionsintegerrequiredfailed_sessionsintegerrequiredtotal_cost_usdnumbernullableavg_latency_msintegernullablewarningsstring[]requirederrorstringnullablecreated_bystringnullablestarted_atstringformat: date-timenullablecompleted_atstringformat: date-timenullableWas this helpful?
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.