---
title: "Start Comparison"
method: POST
path: "/run_sets/compare/start"
---

# Start Comparison

`POST /run_sets/compare/start`

Start an async comparison job and return job ID immediately.

This endpoint starts a comparison in the background and returns immediately
with a job ID. Use GET /run_sets/compare/{job_id} to poll for progress and results.

The comparison may take several minutes depending on the number of incidents
and sessions to compare.

## Request body

- CompareRunSetsRequestBody — Request body for comparing two run sets.
  - `run_set_a_id` string, required — First run set ID to compare
  - `run_set_b_id` string, required — Second run set ID to compare
  - `evaluation_type` string, nullable — Evaluation type to use. Defaults to five_whys.
  - `num_runs` integer — Number of judgment runs per dimension (1-10, recommend 3 for stability)

## Response `200`

Successful Response

- StartComparisonResponse — Response when starting an async comparison job.
  - `job_id` string, required
  - `message` string

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/traversal/apis/fastapi.md) · [All operations](https://skmtc.net/traversal/apis/fastapi/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/traversal/fastapi/revisions/2134ebffd1ef/schema)