Agentic Engineering: How Autonomous Agents Are Built

The center of the certification. An agent is a model in a loop with tools, state and a stopping rule. You build that loop by hand, then add planning, memory, permissions, multi-agent structure, evaluation and a cost model, and learn the protocols that let it plug into anything. Nothing here depends on one vendor product; the applied course after it uses Claude as the worked example.

1. 1What an agent is, and is not3 q
2. 2The loop, by hand3 q
3. 3Tools as contracts3 q
4. 4Environments and side effects3 q
5. 5Planning and control3 q
6. 6State, memory and context management3 q
7. 7Permissions, human-in-the-loop and reversibility3 q
8. 8Protocols: MCP and what comes after it3 q
9. 9Multi-agent systems3 q
10. 10Evaluating agents3 q
11. 11Observability, cost and latency of loops3 q
12. 12Running agents in production, and the capstone3 q
13. 13Appendix: the same loop, in TypeScript2 q