All Tutorials¶
Step-by-step paths through the documentation, from a first agent to multi-agent systems. Each step links to the page with the full details and code.
1. Your First Agent¶
Build, run and deploy an agent that answers tasks.
- Prepare an environment: Install & Setup.
- Write the agent class with
on_preprocessandon_data: Writing the Agent Code. - Unit-test it, then run it locally and send it a task over WebSocket: Testing Agents.
- Register its specification: Agent Registration.
- Deploy it to a cluster and check it with
/healthzand/dryRun: Agent Deployment and Smoke-Testing.
2. Give the Agent a Brain and Tools¶
- Connect a model: Agent × AI Model Interface.
- Add tools and functions: Agentic Function & Tool Calling.
- Add memory: Agentic Memory.
- Stream tokens and tool calls to a UI while it works: Live Task Streams.
3. A Multi-Agent Pipeline¶
- Learn the workflow types: Introduction to Workflows.
- Build, register and run the five-agent Legal Contract Review Pipeline.
- Make it adaptive with a router agent: Dynamic Workflows.
4. Agents That Check and Improve Their Work¶
- Describe a good result as an expectation and evaluate outputs: Evaluation.
- Let the agent iterate until it passes: Self-Evaluation Loops.
- Add a human approval step for risky answers: Human-in-the-Loop.
- Turn outcomes into lessons: Loop Improvement.
5. Agents That Organise Other Agents¶
- Choose between synchronous and asynchronous collaboration: Agentic Patterns.
- Spawn dedicated sub-agents for a task, then remove them: Spawning Sub-Agents.
- Let an LLM plan a workflow from a goal and replan on failure: Prebuilt Operators.
- Recruit specialists from a market: Task Exchange & Bidding.
6. Skills and Generated Code¶
- Write a subjective skill and load it on demand: Subjective Skills.
- Write an objective skill and run it with the interpreter: Objective Skills.
- Generate, test and reuse code as a tool: Running Generated Code in the Ecosystem.
7. Bring an Existing Agent¶
Run a LangChain, LangGraph or other framework agent on the platform: Plural Agentic Backends.
8. Production¶
- Attach governance and guardrail policies: Agentic Governance.
- Auto-scale and survive failures: Scaling.
- Checkpoint long-running tasks: Persistence, Checkpointing & Recovery.
- Watch it run: Observability.
Complete Examples¶
| Example | Shows |
|---|---|
| Legal Contract Review Pipeline | A multi-agent static workflow, end to end |
| Advanced Memory End-to-End Example | Memories, the Learner and the Incorporator working together |