You will be able to
- Define an agent by its environment and the actions its tools allow.
- Sort tools into knowledge augmentation, capability extension and write actions, and explain why write actions need the most care.
- Describe the agent loop (think, act, observe) and both ways it ends.
- Read an agent trace and count model calls, tool calls and write actions.
- Separate what the model decides from what the harness enforces.
- Explain compound errors over many steps and the levers that reduce them.
Topics
Your review
Sign in to keep your quick-check answers. The ones you miss come back for review after 1, 3 and 7 days, until they stick.
Sign in freeSources
AI Engineering · Chip Huyen, 2025
Chip Huyen. O'Reilly. Used: Ch. 6 "RAG and Agents": "Agents" > "Agent Overview", "Tools", "Planning" > "Plan generation", "Function calling", "Reflection and error correction".
ReAct: Synergizing Reasoning and Acting in Language Models · Shunyu Yao et al., 2022
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan & Yuan Cao. arXiv:2210.03629 (ICLR 2023). Used: Abstract (fetched 2026-10-23). Open source
Building effective agents · Erik Schluntz & Barry Zhang (Anthropic), 2024
Erik Schluntz & Barry Zhang (Anthropic). Used: "When (and when not) to use agents", "Agents" (fetched 2026-10-23). Open source