Skip to main content
GET
JavaScript
All the feedback submitted on any objective this agent has run, newest first. Where List objective feedback scopes to one run, this is the agent-wide roll-up.
Each entry carries a score on [-1.0, 1.0], an optional comment, and info.submittedBy, the profile that left it.

It is flat: no per-variation attribution

This is the one thing to know. An entry tells you the score, the note, and who left it, but not which objective or variation earned it. There is no objectiveId or variationId on the row. So this endpoint answers “how is this agent doing overall?”, not “which variation is winning?”. For attribution, reach for a different read:

Search the comments

The query param does a free-text search over the comment text, so you can pull the feedback that mentions a theme:
limit and cursor page the results the usual way.

Submit feedback

Add a score to an objective, which surfaces here.

List variations

The per-variation score this flat stream cannot give you.

List objective feedback

The scores on a single run.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

workspaceId
string
required
Example:

"workspace_01HXKD2E5NQM3T9AYWCF133E3Q"

agentId
string
required

The ID of the agent. Supports "external_id:" prefix for external IDs.

Example:

"agent_01HXKD2E5NQM3T9AYWCFMGWT9Y"

Query Parameters

limit
integer<int32>

Maximum number of results to return.

cursor
string

Pagination cursor from previous response.

query
string

Free-text search applied to the feedback comment. Case-insensitive substring match.

sentiment
enum<string>

Filter by sentiment. UNSPECIFIED returns feedback regardless of score.

Available options:
FEEDBACK_SENTIMENT_UNSPECIFIED,
FEEDBACK_SENTIMENT_POSITIVE,
FEEDBACK_SENTIMENT_NEGATIVE
agentVariationId
string

Optional filter to limit results to feedback on objectives run by a single agent variation. Supports "external_id:" prefix for external IDs.

createdAfter
string<date-time>

Inclusive lower bound on feedback creation time.

createdBefore
string<date-time>

Exclusive upper bound on feedback creation time.

labels
string

Filters by metadata labels. Comma-separated key=value pairs, e.g. "env=prod,team=ai". A resource matches only if every pair matches exactly (AND semantics).

includeInfo
boolean

When set to true you may use more of your alloted API rate-limit

Response

OK

Response for listing feedback across an agent.

items
object[]
pagination
object

Page carries cursor-based pagination state. There is no total: the cursor walks the result set without ever counting it, and a count would cost a second query on every list.