Answer with brain conditioning

curl --request POST \
  --url https://api.get-exo.com/v1/brain/answer \
  --header 'Content-Type: application/json' \
  --header 'X-Exo-API-Key: <api-key>' \
  --data '
{
  "question": "<string>"
}
'

import requests

url = "https://api.get-exo.com/v1/brain/answer"

payload = { "question": "<string>" }
headers = {
    "X-Exo-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-Exo-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({question: '<string>'})
};

fetch('https://api.get-exo.com/v1/brain/answer', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "answer": "<string>",
  "prompt_used": {},
  "retrieval_chunk_ids": [
    "<string>"
  ],
  "brain_signals": {
    "appendix_lines": [
      "<string>"
    ],
    "confidence": 123,
    "contradictions": [
      {}
    ],
    "drift_rate": 123,
    "tier": "<string>",
    "use_system2": true
  }
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

POST

brain

answer

Answer with brain conditioning

curl --request POST \
  --url https://api.get-exo.com/v1/brain/answer \
  --header 'Content-Type: application/json' \
  --header 'X-Exo-API-Key: <api-key>' \
  --data '
{
  "question": "<string>"
}
'

import requests

url = "https://api.get-exo.com/v1/brain/answer"

payload = { "question": "<string>" }
headers = {
    "X-Exo-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-Exo-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({question: '<string>'})
};

fetch('https://api.get-exo.com/v1/brain/answer', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "answer": "<string>",
  "prompt_used": {},
  "retrieval_chunk_ids": [
    "<string>"
  ],
  "brain_signals": {
    "appendix_lines": [
      "<string>"
    ],
    "confidence": 123,
    "contradictions": [
      {}
    ],
    "drift_rate": 123,
    "tier": "<string>",
    "use_system2": true
  }
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

{
  "code": "<string>",
  "detail": "<string>",
  "status": 123,
  "title": "<string>",
  "type": "<string>",
  "documentationUrl": "<string>",
  "errors": [
    {
      "code": "<string>",
      "field": "<string>",
      "message": "<string>",
      "pointer": "<string>"
    }
  ],
  "requestId": "",
  "suggestedAction": "<string>"
}

With arm set to baseline the answer comes from cosine retrieval and the persona prompt alone. With arm set to brain the forward pass runs first: omit tercile_boundaries and the call returns the raw signals and skips generation (answer is an empty string), so a caller can collect signals across a batch of questions before computing boundaries; supply tercile_boundaries and those signals are rendered into the prompt before the answer is generated. Reads the API key owner’s own content, so the X-Exo-Subject selector is not accepted here.

Authorization

This route requires the read scope. A missing or invalid credential returns 401 authentication_error. A valid credential without the scope returns 403 permission_denied, and the problem body names the exact scope required.

Headers

These are request conventions the contract does not declare as parameters, so they do not appear in the schema tables below.

Header	Applies	What it does
`X-Exo-API-Key`	Required	Your Exo API key, `exo_<env>_<token>`. `Authorization: Bearer exo_...` is accepted as an alternate.
`X-Exo-Subject`	Refused	This route scopes data by the key owner. Sending the header returns 400 `subject_not_supported`, rather than silently reading the wrong partition.
`Idempotency-Key`	Not honoured	This route does not replay: reads have no side effect to replay.
`X-Request-Id`	Response	Returned on every response, including `204`s. Quote it in a support request.

Success responses

Status	Meaning
`200`	The generated answer, the prompt that produced it, and the brain signals when the brain arm ran.

Errors

Status	Code	When
`400`	`invalid_request`	Malformed request, for example an invalid cursor.
`401`	`authentication_error`	Missing or invalid credentials.
`403`	`permission_denied`	Missing scope, or an unprovisioned subject selector.
`404`	`not_found`	The resource does not exist, or is not visible to this caller.
`409`	`conflict`	A conflict with the current state of the resource.
`422`	`validation_error`	The request was understood but failed field validation.
`429`	`rate_limit_exceeded`	Rate limit exceeded. Retry after the Retry-After interval.
`503`	`service_degraded`	A dependency is temporarily unavailable. Safe to retry.

Every error is an RFC 9457 application/problem+json body carrying a stable code, a requestId, and a suggestedAction where Exo has one. See Errors.

Authorizations

X-Exo-API-Key

string

header

required

An Exo API key (exo_...) sent as the X-Exo-API-Key header.

Body

application/json

Request for /v1/brain/answer.

arm

enum<string>

required

Available options:

baseline,

brain

question

string

required

Minimum string length: 3

integer

default:8

Required range: 1 <= x <= 50

tercile_boundaries

TercileBoundaries · object | null

Corpus-relative cut points that turn raw ExoBrain signals into prose.

Confidence and drift saturate in absolute terms, so /v1/brain/answer bands them against the caller's own corpus instead of fixed thresholds. Collect the raw signals first (call /v1/brain/answer with arm set to brain and no boundaries), compute the terciles across that batch, then send them back on the generating call.

Doc-only note: each field is a fixed-length pair, which Pydantic renders as JSON Schema 2020-12 prefixItems. The json_schema_extra sibling items is a documentation aid for OpenAPI tooling that predates prefixItems (Spectral's array-items rule); it is accurate (every element is a number) and has no effect on validation.

Show child attributes

Response

The generated answer, the prompt that produced it, and the brain signals when the brain arm ran.

Response for /v1/brain/answer.

answer

string

required

prompt_used

Prompt Used · object

required

retrieval_chunk_ids

string[]

required

brain_signals

BrainSignalsOut · object | null

Raw + rendered ExoBrain signals (brain arm only).

Show child attributes

Query the ExoBrain

Train the ExoBrain

⌘I

​Authorization

​Headers

​Success responses

​Errors

Authorizations

Body

Response

Authorization

Headers

Success responses

Errors