---
title: "Start Expert Builder Job"
method: POST
path: "/api/v1/expert/start"
tags: ["grep-public-api"]
---

# Start Expert Builder Job

`POST /api/v1/expert/start`

## Request

- Base URL: `https://api.grep.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.grep.ai/api/v1/expert/start`
- Auth: none declared

Start a new expert builder job.

This endpoint initiates an expert building pipeline with 3 phases:
1. Expert Planning - Analyze domain, identify expertise areas, generate clarification questions
2. Skill Creation - Create skills based on depth (standard: ~3, deep: ~8)
3. Expert Registration - Register expert in DB and GCS

Requires USER or API_KEY authentication with expert access.

Args:
    input_data: Expert parameters including domain, depth, and optional context

Returns:
    ExpertJobResponse with job_id for tracking

Example:
    POST /api/v1/expert/start
    {
        "domain": "Machine learning for fraud detection in payments",
        "depth": "deep",
        "context": "Focus on real-time detection techniques"
    }

## Request body

- ExpertBuilderInput: Request body for starting an expert builder job.
  - `context` string, nullable: Additional context for the expert
  - `depth` 'standard' | 'deep': Depth of expert (standard: ~3 skills, deep: ~8 skills)
  - `domain` string, required: The domain of expertise to build

## Response `200`

Successful Response

- ExpertJobResponse: Response from expert builder job creation.
  - `job_id` string, required: Job ID for tracking
  - `message` string, required: Response message
  - `status` string, required: Job status

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/grep/apis/grep-api.md) - [All operations](https://skmtc.dev/grep/apis/grep-api/llms.txt) - [OpenAPI document](https://skmtc.dev/grep/apis/grep-api/revisions/3719dd7f43ec?raw)