Skip to main content
GET
List what people told the agent

Authorizations

X-API-Key
string
header
required

Path Parameters

agent_id
string<uuid>
required

Query Parameters

message_id
string<uuid> | null
limit
integer
default:200

How many rows, newest first.

Required range: 1 <= x <= 500
teaching_only
boolean
default:false

Only feedback that teaches the agent: a Needs work, a note or a rewrite. A Looks good alone is a record, and approving a task records one.

source
enum<string> | null

Only feedback given in one place. Where a piece of feedback came from, which says how much it means.

Available options:
approval_card,
inbox_draft,
agent_tab,
approved_unchanged,
positive_reply

Response

Successful Response

comment
string | null
required
consumed_in_version
integer | null
required
created_at
string<date-time>
required
edited_body
string | null
required
edited_subject
string | null
required
id
string<uuid>
required
kind
enum<string>
required

What one written message is, which decides its rules, its length and its channel.

Available options:
email,
linkedin_connection_note,
linkedin_message,
linkedin_inmail,
reply_email,
reply_linkedin
message_id
string<uuid> | null
required
original_body
string
required
original_subject
string | null
required
rating
enum<string> | null
required

The human verdict on one message: a thumb, not a scale.

Available options:
good,
bad
slot_key
string | null
required
source
enum<string>
required

Where a piece of feedback came from, which says how much it means.

Available options:
approval_card,
inbox_draft,
agent_tab,
approved_unchanged,
positive_reply
teaches
boolean
required

Whether the writer and a prompt rewrite learn from it: a Needs work, a note given without a Looks good, or a rewrite. A Looks good with no rewrite, a note on it and an approval kept as approved as written included, is a record and never teaches.

updated_at
string<date-time>
required
user_id
string
required