Agent Engineer
Build agents that reason, call tools, and stay reliable across many steps.
This track assumes you already know
- 1
Agent foundations
- What Is an AI Agent? Strip the hype and an agent is three things: a model that can call tools, a loop, and the authority to decide what happens next. Agents
- How Does Tool Calling Work? The model never runs anything. It emits a structured request, your code executes it, and the result goes back as text. Everything follows from that. Agents
- Writing Good Tool Definitions The tool description is a prompt, and it is the one the model relies on most. Vague descriptions cause more agent failures than weak reasoning. Agents
- What Is MCP? A standard protocol for exposing tools to models, so integrations stop being written once per application. Agents
- 2
The loop
- The Agent Loop Think, act, observe, repeat. The cycle is trivial to implement and the hard parts are all about when to stop. Agents
- The ReAct Pattern Interleave reasoning and action instead of separating them. The idea behind the modern agent loop, why it beats reasoning alone, and where it strains. Agents
- Multi-Step Planning Plan upfront or decide as you go? The tradeoff is coherence against adaptability, and the practical answer is usually a shallow plan you revise. Agents
- Agent Architectures: From Rules to Autonomy A spectrum runs from fixed pipelines to fully autonomous loops. Knowing where a task belongs on it is the single most important agent design decision. Agents
- 3
Make it reliable
- How Agents Fail Seven recurring failure modes, what causes each, and the specific guardrail that prevents it. Read this before shipping anything autonomous. Agents
- Human-in-the-Loop Design Where to put a person in an automated system. Gate by reversibility and confidence, not by task importance. Advanced Agents
- Agent Memory Models have no memory between calls. Everything that feels like memory is retrieval, and designing what to store is the actual problem. Advanced Agents
- Context Engineering Deciding what goes into the context window, in what order. The discipline that replaced prompt engineering once systems got complicated. Advanced Agents
- 4
Go further
- Multi-Agent Systems Several agents with different roles, coordinating. Sometimes better than one, often just a more expensive way to fail. Advanced Agents
- Coding Agents The agent application that works best in practice, and the specific properties of software work that make it work. Advanced Agents
- Evaluating Agents Score the outcome, not the path. Agents are nondeterministic and multi-step, which breaks the evaluation habits that work for single calls. Advanced Agents
- Prompt Injection Instructions and data arrive as the same thing. That is the vulnerability, it has no complete fix, and the defense is architectural. Security