Skip to content
All paths
Build agentsIntermediateFor developers8 chapters195 min

Agent systems and standards

MCP, A2A, AG-UI and friends, orchestration, context, tracing and testing, with the real protocol code.

For developers who can already build a single agent. You connect agents to tools, to other agents, to interfaces and to payments with the open standards, orchestrate several agents in one graph, decide what goes into each context, trace runs and test them against attacks. The protocol libraries run for real in your browser; you can hold, drop and tamper with every message.

Chapters

  1. Chapter 2Locked

    A2A: agents that delegate to agents

    How one agent finds another through its Agent Card and hands it a task it can follow to the end.

    25 min
  2. Chapter 3Locked

    Agents and interfaces: AG-UI and A2UI

    Streaming an agent's work to an app with AG-UI, and letting an agent describe safe interface components with A2UI.

    25 min
  3. Chapter 4Locked

    Agents that pay: UCP and AP2

    How an agent checks out with a merchant over UCP, and how AP2 mandates bind the payment to what the person signed.

    25 min
  4. Chapter 5Locked

    Orchestration: supervisors, fan-out, subgraphs

    Patterns for several agents in one LangGraph graph: a supervisor that routes, Send for parallel work, subgraphs, and the checkpoint each superstep saves.

    25 min
  5. Chapter 6Locked

    Context engineering and retrieval

    Choosing what each model call reads: grep or vector search, offloading large results, a first look at subagents, and memory that lasts across threads.

    25 min
  6. Chapter 7Locked

    Observability: traces and runs

    Recording every model call, tool call and step as a tree of runs, and reading it to find what is slow or broken.

    20 min
  7. Chapter 8Locked

    Evaluation and safety

    Testing an agent system with cases and checks, attacking it with injection and tampering, and mapping the failures to the OWASP agentic risks.

    25 min