> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tai42.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Backends

> Where tools run: background, scheduled, distributed.

A backend is where a tool actually runs when it should not run inline in the
request. It is the execution engine behind background, scheduled, and distributed
tool runs — and it is swappable, so the same tool runs the same way whichever
engine you choose.

## The backend seam

The `Backend` ABC is the contract; the skeleton re-exports it as the registration
seam and ships the callback glue that chains a backend result back into the
runtime. Concrete worker backends — for example ones built on Celery, RQ, or arq —
are external [plugins](/concepts/config-and-secrets) that implement the ABC and
register through `tai42_app.backends.register_backend` when the
[manifest](/concepts/manifest) names the `backend_module`.

The backend runs as its own process:

```bash theme={null}
tai backend
```

A registered backend adds a separate task runtime, so the deployment is now a
fleet of more than one process. Keeping those processes converged on a config
change is **not** the backend's job — it is the app's own
[worker bus](/concepts/worker-bus). Because a backend makes the deployment
multi-process, naming a `backend_module` requires the bus: set `TAI_BUS_REDIS_URL`
or the server refuses to start.

## Three ways a tool runs off the request path

* **Background** — submit a tool run and poll its result, for a run that outlives
  one request. The background tool-runs HTTP surface loads as a router module.
* **Scheduled** — schedule a tool to run later or on a cadence. A schedule names
  the `tool_name`, its `tool_kwargs`, and the schedule parameters the backend's
  scheduling tool consumes.
* **Distributed** — the worker backend spreads runs across workers.

Manage schedules from the CLI:

```bash theme={null}
tai schedules list
tai schedules add report --schedule-kw cron='0 9 * * *'
tai schedules delete <name>
```

## Routing a tool to a backend

A tool is routed to a backend with a `BACKEND`-kind
[extension](/concepts/tools-and-extensions) — the extension kind whose job is to
send a tool's execution through a backend rather than running it inline. The tool's
definition does not change; the extension decides where it runs.

<Warning>
  A tool that depends on a managed `stdio` MCP server's tools runs on the ASGI, arq,
  and RQ execution paths, but not inside a Celery **prefork** worker child: the
  managed server's live stdio subprocess connection does not survive the prefork
  fork, so those tools are unavailable there. Route such a tool to a non-prefork
  engine, or run it inline on the request path.
</Warning>

<Note>
  A specific worker backend's setup — its broker, queues, and concurrency — lives in
  that backend package's own repository, reachable from the
  [catalog](/reference/catalog/index). The platform documents the backend contract,
  not any one engine.
</Note>

See the [schedule-a-tool guide](/guides/schedule-a-tool), the
[backend author guide](/guides/authors/backend), and the
[HTTP API reference](/reference/api/index) for the tool-run and schedule routes.