Skip to main content
POST
Rate one message the agent wrote

Authorizations

X-API-Key
string
header
required

Path Parameters

agent_id
string<uuid>
required

Body

application/json

A thumb, a note, or both, on one message the agent wrote.

body
string
default:""

The words rated, when the message they were on is gone.

Maximum string length: 20000
comment
string | null

What the person wants changed.

Maximum string length: 2000
create_only
boolean
default:false

Refuse to replace an existing verdict that was not reviewed.

edited_body
string | null
Required string length: 1 - 20000
edited_subject
string | null
Maximum string length: 500
kind
enum<string>
default:email

What the message was; read from the message itself when one is named.

Available options:
email,
linkedin_connection_note,
linkedin_message,
linkedin_inmail,
reply_email,
reply_linkedin
message_id
string<uuid> | null

The message being rated; null when it is already gone.

rating
enum<string> | null

The thumb.

Available options:
good,
bad
source
enum<string>
default:agent_tab

Where the verdict was given: a sequence's AI writing tab and its Preview (agent_tab), or a task waiting for approval (approval_card). Only a verdict given on the AI writing tab counts as a review of that step's writing.

Available options:
agent_tab,
approval_card

Response

Successful Response

One person's verdict on one message the agent wrote.

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,
sent_message
teaches
boolean
required

Whether it says something needs work: a thumbs down, 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 written included, does not. Either way it is a record: the agent learns only from Needs work, through its learnings.

updated_at
string<date-time>
required
user_id
string
required