Skip to main content
Create Custom Analysis Category
A group runs as one extraction over the conversation, so items that belong together should share a group — it is cheaper and the answers stay consistent with each other. conditions skips the group when a call was too short to have said anything: a skipped group costs nothing and is reported as skipped rather than failed. Leave model unset and the group uses the agent’s own model. Attach it by adding its id to an agent’s analysis_group_ids.

Authorizations

Authorization
string
header
required

Your API key as a Bearer token, e.g. Authorization: Bearer vk_….

Body

application/json
name
string
required

What to call this group. It becomes part of the key values arrive under — custom_analysis["Lead QA"][…] — so renaming it later changes your payload shape.

Required string length: 1 - 255
description
string | null

Your own note about what the group is for.

model
string | null

Which LLM runs the extraction. Defaults to the agent's own.

Maximum string length: 128
temperature
number | null

Randomness for the extraction. Lower is more repeatable, which is usually what you want here.

Required range: 0 <= x <= 2
max_tokens
integer | null

Cap on the extraction response.

Required range: 50 <= x <= 10000
conditions
CustomAnalysisConditions · object

When this group runs at all. A group that does not run costs nothing.

Response

The created group.

id
string
name
string
description
string | null
model
string | null
temperature
number | null
max_tokens
integer | null
conditions
object
is_default
boolean
items
object[]
created_at
string<date-time>
updated_at
string<date-time>