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

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.

post/v1/projects/{project_id}/agent-analytics/datasets

Authorizations

Authorizationstringrequired

http

Path parameters

project_idstringrequired

Amplitude project identifier, backed by the canonical app ID.

Example:12345
Constraints:pattern: ^[0-9]+$

Header parameters

Idempotency-Keystringrequired

Unique idempotency key used to safely retry write operations.

Constraints:min length: 8max length: 255

Body

application/json
namestringrequired
Constraints:min length: 1max length: 255
descriptionstring
Constraints:nullable
agent_namestring

Scope the dataset to one agent. Omit for a project-level dataset.

Constraints:nullable

Response

application/json
201· Dataset created.
dataobjectrequired
Show child attributes
idstringrequired

Stable dataset identifier (ULID).

objectstringrequired
project_idstringrequired
namestringrequired
Constraints:min length: 1
descriptionstringrequired
Constraints:nullable
agent_namestringrequired

Agent the dataset is scoped to. Null for project-level datasets.

Constraints:nullable
source_typestringrequired

How the dataset was assembled, such as manual.

session_countintegerrequired

Sessions currently in the dataset.

reviewed_countintegerrequired

Sessions in the dataset that carry a human review.

created_atstringrequired
Constraints:format: date-time
created_bystring
Constraints:nullable

Was this helpful?