---
title: "Run Eval"
method: POST
path: "/api/internal/shadow-eval/run"
tags: ["Internal — Shadow Eval", "internal"]
---

# Run Eval

`POST /api/internal/shadow-eval/run`

## Request

- Base URL: `https://api.thebetterhire.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.thebetterhire.ai/api/internal/shadow-eval/run`
- Auth: HTTP bearer

Kick off a shadow-scoring eval as a background asyncio task.

Returns immediately with the job_id; eval continues running even if
the client disconnects (the user's flaky wifi was the whole reason
we built this endpoint).

Query params:
  n: transcripts per persona (default 10 → 40 total)
  llm: "anthropic" or "deepseek" — generator model

## Query parameters

- `n` integer
- `llm` string

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/thebetterhire/apis/interanalysis-b2b-api.md) · [All operations](https://skmtc.dev/thebetterhire/apis/interanalysis-b2b-api/llms.txt) · [OpenAPI document](https://skmtc.dev/thebetterhire/apis/interanalysis-b2b-api/revisions/c8ad03e900ea?raw)