Knowledge

Add knowledge

Ingests a text document into the org-shared knowledge base. Content is chunked (~1500-token paragraphs) and embedded so it becomes retrievable via search_knowledge / GET /api/public/knowledge/search. Not a way to draft posts.

POST/api/public/knowledge

cURLPOST /api/public/knowledge

curl -X POST https://postiv.ai/api/public/knowledge \
  -H "Authorization: Bearer pk_postiv_..." \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Launch lessons",
    "content": "Three things we learned from launch week..."
  }'

200Response

{
  "success": true,
  "asset": {
    "id": "b1c2...",
    "title": "Q3 Positioning Notes",
    "kind": "document",
    "category": "positioning",
    "chunkCount": 3,
    "createdAt": "2026-07-19T09:00:00.000Z"
  }
}

Authorization

Requires an organization API key with the knowledge:write scope, sent as Authorization: Bearer or x-api-key.

Body parameters

titlestringrequired

Short title, 1-240 chars (trimmed).

contentstringrequired

The text to ingest, 1-300000 chars (trimmed).

Response

The created knowledge asset.

asset.iduuid

assets.id of the new knowledge document.

asset.titlestring

Stored title.

asset.kindstring

Auto-classified asset kind (via classifyIntake).

asset.categorystring

Auto-classified category.

asset.chunkCountint

Number of embedded chunks created.

asset.createdAttimestamp

Creation time.

Errors

400	validation_error: missing/empty title or content, or over length limits

Good to know

Asset is stored owner_id=null, is_shared=true, shared_with_org_id=<caller's org>: org-wide, not tied to the calling user. Tagged meta.source = 'public-api' (or 'mcp' when called through the MCP tool).