Next Steps

You have a deployed agent platform with two reference agents, evals, and JWT auth. The sections below cover the moves that turn it into a real product: teams and workflows, scheduled tasks, and connecting to Slack.

Going beyond agents

Rule of thumb: agents for open questions, teams for routing, workflows for processes. Most of your platform will be agents. A few will be teams or workflows.

Pattern	Use it when	Reference
Agent	A single LLM with tools and instructions can handle the request.	Agents overview
Team	The right specialist isn’t known up front. A leader routes or coordinates.	Teams overview
Workflow	The process needs to run the same way every time. Determinism matters.	Workflows overview

Teams come in three 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; you aggregate.

Scheduled tasks

The scheduler is on by default in app/main.py:

agent_os = AgentOS(
    name="AgentOS",
    scheduler=True,
    ...
)

Schedule any agent or workflow on a cron. Common patterns:

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.
Catch regressions	Run `python -m evals` weekly against production agents.

See scheduling for the cron API.

Connect to interfaces

Your agents should be available where your users are. Slack threads. Discord channels. Telegram for the field team. Or a custom UI inside your product. The pattern is the same for each. Expose the agent via an interface in app/main.py:

from agno.os.interfaces.slack import Slack

interfaces: list = []
if SLACK_BOT_TOKEN and SLACK_SIGNING_SECRET:
    interfaces.append(
        Slack(
            agent=code_search,
            streaming=True,
            token=SLACK_BOT_TOKEN,
            signing_secret=SLACK_SIGNING_SECRET,
            resolve_user_identity=True,
        )
    )

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

resolve_user_identity=True ties the Slack user to the same user_id they have in the AgentOS UI, so sessions follow the person across surfaces.

Interface	Reference
Slack	Slack interface
Telegram	Telegram interface
WhatsApp	WhatsApp interface
Custom UI / AG-UI	AG-UI interface
Agent-to-agent	A2A interface
All interfaces	Interfaces overview

Add tools to an agent

Agno ships 100+ toolkit integrations. See the full toolkit reference.

from agno.tools.slack import SlackTools
from agno.tools.googlesheets import GoogleSheetsTools

my_agent = Agent(
    ...
    tools=[
        SlackTools(),
        GoogleSheetsTools(),
    ],
)

Each toolkit reads its credentials from environment variables. Add them to .env for local and to .env.production for Railway, then ./scripts/railway/env-sync.sh.

Swap model providers

Switch from OpenAI to Anthropic:

Set ANTHROPIC_API_KEY in .env and .env.production.
Add anthropic to pyproject.toml.
Update the agent’s model=.
Run ./scripts/generate_requirements.sh && docker compose up -d --build.

from agno.models.anthropic import Claude

my_agent = Agent(
    ...
    model=Claude(id="claude-sonnet-4-5"),
)

The same pattern works for Google (google-genai), Mistral (mistralai), and the other supported providers.

Keep the repo coherent

As you ship more agents, configuration drifts, env vars rot, and new agents miss imports. The template repo ships a fourth Claude Code prompt for the recurring sweep:

Run docs/review-and-improve.md

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.

Going deeper

To learn	See
The full AgentOS feature set	Demo OS
How knowledge and Agentic RAG work	Knowledge
How MCP integrates with Agno	MCP
Comparable templates	Scout, Dash, Coda
Building a fully custom AgentOS app	Build a product

Welcome

Tutorials

Runtime

Demo OS

Going beyond agents

Scheduled tasks

Connect to interfaces

Add tools to an agent

Swap model providers

Keep the repo coherent

Going deeper

​Going beyond agents

​Scheduled tasks

​Connect to interfaces

​Add tools to an agent

​Swap model providers

​Keep the repo coherent

​Going deeper

Going beyond agents

Scheduled tasks

Connect to interfaces

Add tools to an agent

Swap model providers

Keep the repo coherent

Going deeper