Docs
Get transcript
GET
/api/jobs/:jobId/interviews/:interviewIdThis is the same endpoint as Get screen. The full payload includes a messages field with the ordered back-and-forth between the AI screener and the candidate; this page shows you that field.
Same endpoint, different focus
One round-trip gives you both the scoring and the transcript. We document them as two pages because that matches how most callers think about it: "what did they say?" vs "what was the score?"
Path parameters
| Name | Type | Required | Description |
|---|---|---|---|
jobId | uuid | yes | UUID of the job. |
interviewId | uuid | yes | UUID of the screen. |
Headers
Authorization header required. See Authentication.
Response: messages array
Each message has a role of assistant (the AI) or candidate (the person being screened), plus the question_id the message was tied to (or null for greetings and closing remarks). Messages are ordered by created_at, oldest first.
response.messages
json
[
{
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"interview_id": "7b1d3c0e-4f5a-4f2b-9e8c-5a6b1c2d3e4f",
"role": "assistant",
"content": "Hi Jordan, thanks for applying. To start, can you walk me through your most recent caregiving role?",
"question_id": "1a2b3c4d-5e6f-7a8b-9c0d-1e2f3a4b5c6d",
"created_at": "2026-05-18T17:42:14.301Z"
},
{
"id": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
"interview_id": "7b1d3c0e-4f5a-4f2b-9e8c-5a6b1c2d3e4f",
"role": "candidate",
"content": "Sure. I spent the last 18 months at Maple Grove on the memory-care floor...",
"question_id": "1a2b3c4d-5e6f-7a8b-9c0d-1e2f3a4b5c6d",
"created_at": "2026-05-18T17:42:48.117Z"
}
]Example request
curl
curl https://api.prelim.chat/api/jobs/f4c2a1d8-9b3e-4d6a-b25f-1c0e8a7b3d52/interviews/7b1d3c0e-4f5a-4f2b-9e8c-5a6b1c2d3e4f \
-H "Authorization: Bearer prelim_8s4kZxQv3p2nLw1HfYBgRmTcEsK9aJdN0iUyXoVbPeWzCqA" \
| jq '.messages'