---
title: "Capture Copilot Soul"
method: POST
path: "/copilot/memory/soul-capture"
tags: ["Copilot"]
---

# Capture Copilot Soul

`POST /copilot/memory/soul-capture`

## Request

- Base URL: `https://be.graph8.com/api/v1`
- URL: `https://be.graph8.com/api/v1/copilot/memory/soul-capture`
- Auth: HTTP bearer

Set the organisation's and the user's foundational documents in one call.

The onboarding shortcut: it is how a new workspace tells the assistant who
it works for before there is any history to learn from. Every field is
optional and sending one does not clear the others.

## Headers

- `Authorization` string, nullable
- `X-Target-Org-Id` string, nullable

## Request body

- SoulCaptureRequest: Mirror of `SoulCaptureRequest`. Every field optional: this is used to fill in whichever of the three documents the caller has, and sending one does not clear the others.
  - `org_soul` string, nullable: Who the organisation is.
  - `org_memory` string, nullable: Durable org-level facts.
  - `user_memory` string, nullable: Durable facts about this person.

## Response `200`

Successful Response

- ApiResponseCopilotMemoryPayload
  - `data` CopilotMemoryPayload, required: An open envelope for one memory, wiki or sharing answer. Open because the personal wiki is a DOCUMENT whose sections follow what has been learned about a person, and because each fact carries provenance - which mailbox or meeting it came from - that grows as new sources are connected. Pinning the shape would silently drop the provenance on the newest source, and on a "what do you know about me" surface a fact with no visible origin is worse than no fact.
  - `pagination` PaginationMeta
    - `page` integer, required: Current page number (1-indexed)
    - `limit` integer, required: Items per page
    - `total` integer, required: Total number of items
    - `has_next` boolean, required: Whether there are more pages
    - `next_cursor` string, nullable: Opaque cursor for the next page; null when there are no more items. Pass it back as the `cursor` query param to fetch the following page without computing page numbers.
    - `total_available` integer, nullable: Search endpoints only: how many records really match, when known. Can be larger than `total`, which is capped at the 10,000 results that can be paged. For company search this is a distinct-company estimate. Null when unknown; absent outside search.
    - `total_is_lower_bound` boolean, nullable: Search endpoints only: true when more records match than `total` shows (the result set is larger than the 10,000 results that can be paged). Absent outside search.
    - `notes` string[], nullable: Search endpoints only: plain-language notes about the result, e.g. that more records match than can be paged, or that a reversed `between` range was put in order.

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/graph8/apis/graph8-developer-api.md) · [All operations](https://skmtc.dev/graph8/apis/graph8-developer-api/llms.txt) · [OpenAPI document](https://skmtc.dev/graph8/apis/graph8-developer-api/revisions/89fc11143b70?raw)