Endpoint

Get draft qa

GET/api/public/v1/campaigns/{campaign_id}/qaread

Machine-readable QA state for drafts. Pass speaker_id alone to inspect one speaker, or campaign_id for the whole campaign. Returns per-message qa_score, qa_evaluated_at, hard-fail codes, actionable fix hints ({code, action, hint}), needs_human / needs_redo, approvable flag, plus per-speaker buckets (ready_to_send | needs_rewrite | needs_human | awaiting_qa | skipped | sent) and a rollup of the most common fail codes. Use this to decide what to rewrite (request_rewrite) before pushing. Filter with only_failing=true. Paginated: pass next_cursor while has_more is true.

Request

curl "https://sayintel.com/api/public/v1/campaigns/<campaign_id>/qa" \
  -H "Authorization: Bearer $SAYINTEL_TOKEN"

Try it out

Try it outGET/api/public/v1/campaigns/{campaign_id}/qaread

API key

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.

campaign_id path

speaker_id optional

only_failing optional

limit optional

cursor optional

Paste an API key to run.

Path parameters

Name	In	Type	Required	Description
campaign_id	path	string	yes	Required unless speaker_id is given.

Query parameters

Name	In	Type	Required	Description
speaker_id	query	string	no	—
only_failing	query	boolean	no	Only return unsent drafts that are not approvable (hard fail, low score, or unevaluated).
limit	query	number	no	—
cursor	query	string	no	Opaque cursor from a previous call's next_cursor. Omit for the first page.

Response

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

Notes

Scope required: read. How scopes work.
Paginated. Pass the returned next_cursor while has_more is true.
Same capability over MCP as the tool get_draft_qa. MCP setup.