sayintel
Endpoint

Ask intel

POST/api/public/v1/campaigns/{campaign_id}/askread

Say intel: answer one question about one campaign (room) from its own data. Runs a read-only loop over the room's read tools (people, drafts, signals, decisions, approvals, readiness, the saved brief) with campaign_id pinned to that room and every speaker_id checked against it, and returns the answer with its sources and a confidence that is low whenever no tool stood behind it. Never writes, never sends, makes no outbound request: the only URLs it cites are ones its own tool results carried. Spends model calls.

Request

curl -X POST "https://sayintel.com/api/public/v1/campaigns/<campaign_id>/ask" \
  -H "Authorization: Bearer $SAYINTEL_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"question": "<question>"}'

Try it out

Try it outPOST/api/public/v1/campaigns/{campaign_id}/askread

Sent as a bearer token to this site only, and kept in this tab's session storage. It is never written to disk or sent anywhere else.

Paste an API key to run.

Path parameters

NameInTypeRequiredDescription
campaign_idpathstringyes—

Body

NameInTypeRequiredDescription
questionbodystringyes—

Response

{
  "ok": true,
  "tool": "ask_intel",
  "kind": "read",
  "data": { ... },
  "error": null
}

Notes

  • Scope required: read. How scopes work.
  • Accepts Idempotency-Key. A retry with the same key replays the first result instead of repeating the work.
  • Same capability over MCP as the tool ask_intel. MCP setup.