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

# Next Steps

> Add teams, workflows, scheduled tasks, and interfaces to your agent platform.

You now have a deployed agent platform with evals, JWT auth, and a set of coding-agent skills that cover the full lifecycle: create → improve → evaluate → maintain.

The sections below cover the next level: teams and workflows for multi-step logic, scheduled tasks for proactive runs, and interfaces that put your agents where your users are.

## Going beyond agents

| Pattern      | Use it when                                                               | Reference                                 |
| ------------ | ------------------------------------------------------------------------- | ----------------------------------------- |
| **Agent**    | A single LLM with tools and instructions can handle the request.          | [Agents overview](/agents/overview)       |
| **Team**     | Multiple specialists should route, coordinate, or collaborate.            | [Teams overview](/teams/overview)         |
| **Workflow** | The process needs explicit steps, branches, loops, or parallel execution. | [Workflows overview](/workflows/overview) |

Teams come in four modes:

| Mode           | Behavior                                                                                                       |
| -------------- | -------------------------------------------------------------------------------------------------------------- |
| **Coordinate** | A leader plans the work, calls the right specialists, synthesizes.                                             |
| **Route**      | A router picks one specialist to handle the request.                                                           |
| **Broadcast**  | Every specialist runs in parallel; the leader synthesizes.                                                     |
| **Tasks**      | A leader breaks the goal into a task list, delegates tasks to members, and loops until every task is complete. |

## Scheduled tasks

The scheduler is on by default in `app/main.py`, and the template prepares two workflows for scheduled runs:

| Workflow             | What it does when enabled                     | Default                                         |
| -------------------- | --------------------------------------------- | ----------------------------------------------- |
| **Deployment check** | Checks daily that AgentOS is wired correctly. | On. Set `ENABLE_DEPLOY_CHECK=False` to disable. |
| **Run evals**        | Runs the `smoke`-tagged eval cases daily.     | Off. Enable it from the AgentOS UI.             |

Schedule your own agents and workflows the same way:

| Use case           | Example                                                            |
| ------------------ | ------------------------------------------------------------------ |
| **Maintenance**    | Purge sessions older than 90 days. Vacuum Postgres tables.         |
| **Proactive runs** | Every weekday morning, summarize overnight news and post to Slack. |

See [Scheduler](/agent-os/scheduler/overview) for the cron API.

## Connect to interfaces

Connect agents to Slack, Telegram, WhatsApp, or a custom UI inside your product.

Expose the agent via an interface in `app/main.py`:

```python theme={null}
interfaces: list = []
if SLACK_BOT_TOKEN and SLACK_SIGNING_SECRET:
    from agno.os.interfaces.slack import Slack

    interfaces.append(
        Slack(
            agent=agent_builder,
            streaming=True,
            token=SLACK_BOT_TOKEN,
            signing_secret=SLACK_SIGNING_SECRET,
            resolve_user_identity=True,
        )
    )

agent_os = AgentOS(
    ...,
    interfaces=interfaces,
)
```

| Interface         | Reference                                                        |
| ----------------- | ---------------------------------------------------------------- |
| Slack             | [Slack interface](/agent-os/interfaces/slack/introduction)       |
| Telegram          | [Telegram interface](/agent-os/interfaces/telegram/introduction) |
| WhatsApp          | [WhatsApp interface](/agent-os/interfaces/whatsapp/introduction) |
| Custom UI / AG-UI | [AG-UI interface](/agent-os/interfaces/ag-ui/introduction)       |
| All interfaces    | [Interfaces overview](/agent-os/interfaces/overview)             |

## Keep the repo coherent

As you ship more agents, configuration drifts, env vars rot, and new agents miss imports. Run the repository review skill for a recurring sweep:

```text theme={null}
/review-and-improve
```

It auto-fixes mechanical drift (stale paths, missing `example.env` entries, agents on disk not registered in `app/main.py`) and surfaces the rest as a punch list. Run it before public releases and periodically during active development.

## You're done

You now have a platform that runs locally and on Railway with JWT auth, persists sessions, memory, and traces in Postgres, supports Postgres-backed knowledge, and includes eight coding-agent skills for setup, development, evals, review, and deployment.