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.
Create an Agent Analytics dataset
이 페이지는 아직 귀하의 언어로 번역되지 않았습니다. 현재 작업 중이므로 곧 다시 확인해 주십시오.
Creates an empty dataset. Add sessions with the dataset sessions endpoint.name is not an identity key, so repeating a create makes another dataset —
retry safely with the same Idempotency-Key instead.
Listing and reading datasets is served by the Agent Analytics MCP read
surface, not by this API.
/v1/projects/{project_id}/agent-analytics/datasetsAuthorizations
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/jsonnamestringrequiredmin length: 1max length: 255descriptionstringnullableagent_namestringScope the dataset to one agent. Omit for a project-level dataset.
nullableResponse
application/jsondataobjectrequiredShow child attributes
idstringrequiredStable dataset identifier (ULID).
objectstringrequiredproject_idstringrequirednamestringrequiredmin length: 1descriptionstringrequirednullableagent_namestringrequiredAgent the dataset is scoped to. Null for project-level datasets.
nullablesource_typestringrequiredHow the dataset was assembled, such as manual.
session_countintegerrequiredSessions currently in the dataset.
reviewed_countintegerrequiredSessions in the dataset that carry a human review.
created_atstringrequiredformat: date-timecreated_bystringnullable이 내용이 도움이 되었나요?