> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usesynth.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Managed Research

> Run hosted AI workers against repos and research goals, then inspect durable evidence.

Managed Research lets you hand a repo and research goal to hosted AI workers. Synth runs the workspace, tracks the run, and returns durable evidence: messages, tasks, logs, checkpoints, artifacts, usage, PRs, and final reports.

Use it when the work should be repeatable and inspectable instead of trapped in a one-off chat.

## Responsibility split

| You provide                                                                      | Synth handles                                                                                                                |
| -------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| Repo, goal, constraints, context, credentials, eval command, and review criteria | Worker orchestration, hosted workspace execution, durable state, logs, checkpoints, artifacts, usage, PRs, and final reports |

## Choose an interface

<CardGroup cols={2}>
  <Card title="Get started (MCP + Codex / Claude)" icon="rocket" href="/managed-research/get-started">
    Install the Managed Research MCP, set `SYNTH_API_KEY`, and verify with `smr_list_projects`.
  </Card>

  <Card title="MCP Quickstart" icon="plug" href="/managed-research/mcp-quickstart">
    Start and steer runs from Codex, Claude Code, Cursor, or another MCP client.
  </Card>

  <Card title="Python SDK quickstart" icon="code" href="/managed-research/sdk-quickstart">
    Script runs, CI, and notebooks with `SynthClient().research`.
  </Card>

  <Card title="Run Configuration" icon="sliders-horizontal" href="/managed-research/launch-fields">
    Learn the launch fields for runbooks, work modes, harnesses, models, providers, and budgets.
  </Card>

  <Card title="Runs and Evidence" icon="file-search" href="/managed-research/runs-and-evidence">
    Inspect messages, task state, actor state, artifacts, checkpoints, usage, and reports.
  </Card>
</CardGroup>

## Public contract

Managed Research and Research Factory are **`SynthClient().research`** products.
Agent clients can use the hosted **Managed Research MCP** (`smr_*` tools). The web
app at `/smr` is for interactive review.

Install `synth-ai[research]` — not a separate `managed-research` package. Direct
`/smr` REST usage is internal and unstable; use MCP or `client.research` for public
integrations.

## Run lifecycle

Most workflows follow the same loop:

1. Create or select a project.
2. Attach repo, context, credentials, data, and constraints.
3. Preflight launch configuration before spending runtime.
4. Start a one-off or project-scoped run.
5. Steer the run with messages when needed.
6. Inspect state, logs, tasks, artifacts, checkpoints, usage, and final report.

## What to read next

* [Get started](/managed-research/get-started) for MCP install with Codex and Claude Code.
* [Quickstart](/managed-research/quickstart) for the shortest product path.
* [Projects and context](/managed-research/projects-and-context#using-projects-in-the-web-app-logged-in) for the logged-in web app.
* [MCP Quickstart](/managed-research/mcp-quickstart) for agent-client setup.
* [Python SDK Quickstart](/managed-research/sdk-quickstart) for scripts.
* [Models and Harnesses](/managed-research/models-and-harnesses) for model IDs, launch access, and reasoning-effort support.