Agents in a Real Product in Building AI Agents

Lessons in this section

1. Multi-Agent: Subagents, Handoffs, Orchestrators

   When one AI helper has too many tools and a long chat, a front desk can split the work between specialists. Learn handoff notes, lost facts and the scorecard rule.

2. MCP: Tools from Outside the App

   MCP lets an AI helper plug in tools from other services. Learn how an app connects to an MCP server, gets its tool cards, checks who may use them, and copes when the server stops answering.

3. Evaluating Agents

   Test the helper with many sample chats, every time you change it. Each scenario gets three checks: the reply, the tools it used and what really changed in the shop.

4. Observability, Cost and Reliability

   Read a trace to see what every step of an agent costs in coins and time. Cut a bloated prompt, set a budget per message, add timeouts and retries, and send easy questions to a smaller model.

5. Framework Tour: The Same Agent, Five Ways

   Frameworks run the agent loop for you. See what five popular frameworks give, what they hide, and how to choose one by your team's needs.

6. Capstone: An Agent for Your App

   Put every choice from the course on one Agent Card, then test the whole helper with 20 test chats, attacks included. Export the card and a starter file, and fill in the same card for your own app.