Agent Engineering
Workflows versus agents, tool design, MCP and its security model, memory, human-in-the-loop, long-running agents, multi-agent systems, agent archetypes, voice agents, and choosing a framework.
- Chapters
- 13
- Hours
- 3
- Difficulty
- Intermediate to Advanced
- 7.0intermediate
Workflow vs agent
If you can write the control flow in Python, it's a workflow. If the model decides at runtime, it's an agent. Most production wins are workflows.
- 7.1intermediate
The five workflow patterns
Chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer: each with code, a use case, and the failure mode that bites in production.
- 7.2intermediate
The agent loop
Think, act, observe, and the part nobody talks about: how the loop ends. Stop conditions, reflection that actually works, and why production agents look nothing like the demo.
- 7.3intermediate
Tool design
The agent-engineering skill: schemas that make invalid calls impossible, descriptions the model can't misread, errors it can recover from, and the right number of tools.
- 7.4intermediate
MCP: Model Context Protocol
How to expose tools, data, and prompts to any AI host through one open protocol; build a server and client end-to-end.
- 7.5intermediate
MCP security
The four attack classes MCP creates: tool poisoning, cross-server shadowing, rug pulls, and injection via tool results, and the architectural defenses that actually stop them.
- 7.6intermediate
Agent memory and task state
The four places an agent can put information, why most teams use the wrong one, and how to design state that survives a pod restart mid-task.
- 7.7intermediate
Human-in-the-loop
Approval gates as tool calls, confidence-based escalation, and handoff design: the three independent things you have to engineer for selective human oversight to actually work.
- 7.8advanced
Long-running agents
Budgets, kill switches, checkpoints, replay, and the sync vs async choice: the harness work that keeps a multi-minute agent from burning a month's API spend.
- 7.9advanced
Multi-agent systems
When multi-agent topology earns its 15x token cost, when it doesn't, and the single-writer pattern that handles most production work.
- 7.10intermediate
Agent archetypes
Research, Coding, Browser, and Computer Use agents differ in one thing that cascades into everything else: what the model sees at each step.
- 7.11intermediate
Voice agents
The 800ms budget that defines voice agents, the cascaded vs native trade-off, and why barge-in is the hardest correctness problem in the stack.
- 7.12intermediate
Choosing a framework
Frameworks buy state, retries, and tracing. Most teams don't need them. The decision rule for plain SDK, light structure, and full graph runtime.