---
title: "Run a company-locked full-agent Tally sandbox replay"
method: POST
path: "/admin/tally/flight-recorder/sandbox-replays"
tags: ["Administration"]
---

# Run a company-locked full-agent Tally sandbox replay

`POST /admin/tally/flight-recorder/sandbox-replays`

## Request

- Base URL: `https://ledgerhq.pro/api/v1`
- URL: `https://ledgerhq.pro/api/v1/admin/tally/flight-recorder/sandbox-replays`
- Auth: one of:
  - HTTP bearer and API key in header `x-organization-id`
  - HTTP bearer and API key in header `x-organization-id`

Runs a human-approved redacted benchmark only inside a selected disposable demo company. The source firm and company are forbidden, firm-level tools are denied, raw response and tool payloads are not persisted, and the advisory grader cannot override deterministic or human gates. Requires admin:tally-quality:write.

## Headers

- `Idempotency-Key` string, required

## Request body

- object
  - `benchmarkId` string, uuid, required
  - `targetCompanyOrganizationId` string, uuid, required
  - `provider` 'anthropic' | 'openai_codex' | 'openrouter', required
  - `model` string, required
  - `graderProvider` 'anthropic' | 'openai_codex' | 'openrouter', required
  - `graderModel` string, required
  - `strategy` 'single_agent' | 'specialist_guided', required
  - `baselineReplayId` string, uuid, nullable
  - `confirmed` true, required

## Response `200`

Idempotent existing replay

## Other responses

- `201`: Completed sanitized sandbox replay
- `409`: Benchmark or demo target safety gate failed
- `429`: Evaluation budget reached
- `default`: Error response

---

[API](https://skmtc.dev/ledgerhq-pro/apis/ledgerhq-bookkeeping-api.md) · [All operations](https://skmtc.dev/ledgerhq-pro/apis/ledgerhq-bookkeeping-api/llms.txt) · [OpenAPI document](https://skmtc.dev/ledgerhq-pro/apis/ledgerhq-bookkeeping-api/revisions/9a8269f0a586?raw)