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.
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, 100 sessions, and a sample size of 100.
/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-KeystringrequiredUnique idempotency key used to safely retry write operations.
min length: 8max length: 255Body
application/jsonevaluator_idsstring[]requiredEvaluators to run. Stable evaluator identifiers.
dataset_idstringEvaluate 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_sizeintegerMaximum sessions to evaluate from the target. Defaults to the 100-session cap, so omitting it evaluates as much of the target as the cap allows.The API always sends an explicit value upstream. The upstream default of 1 is deliberately never relied on, because omitting the field would otherwise evaluate a single session while appearing to evaluate the whole target.
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?