Skip to content

04. Week 9 — Daily Recall

Use this file after reading the explainer. Answer aloud. Then verify with 02_explainer.md and 03_study_material.md.

Monday

  1. Why is one correct calculator call not enough for a multi-step task? (Exp §1.1)
  2. LLM call vs single tool use vs agent — define each in one sentence. (Study §1)
  3. What are the five named placeholders from the handyman analogy? (Exp ELI5)
  4. [W8] When did RAG fail because retrieval was not enough?

Tuesday

  1. ReAct — what are the three core steps? (Exp §2.1)
  2. Why does the ReAct loop work better than chain-of-thought alone for external-state tasks? (Exp §2.2, §2.4)
  3. Write the smallest useful agent loop from memory. What are its stop conditions? (Exp §2.3, §4.4)
  4. [W7] In one sentence, why is exact tool use similar to external memory?

Wednesday

  1. Name 5 tool design rules from memory. (Exp §3.1-§3.6)
  2. Give one example of a bad tool name and a better replacement. (Exp §3.1)
  3. What is idempotency, and why does it matter more for write tools? (Exp §3.5)
  4. Why are schemas necessary even when the model is strong? (Study §3)

Thursday

  1. Infinite loop, wrong tool selection, hallucinated arguments — one guardrail each. (Exp §4.1-§4.3)
  2. Stop rule vs give-up rule — difference? (Exp §4.4)
  3. When should a human-in-the-loop gate appear? Give 3 examples. (Exp §4.5)
  4. [W6] Why do we prefer bounded systems in production?

Friday

  1. Parallel tool calls — when do they reduce latency safely? (Exp §5.1)
  2. Tool chaining — what is a good boundary between tools? (Exp §5.2)
  3. State across turns — messages vs structured state vs memory. (Exp §5.4)
  4. What five basics does module 10 assume from this week? (Exp §5.7)

Saturday

  1. Recreate the failure-fix table headings from memory. (Exp §6.1)
  2. Name 3 metrics you would track for a production agent. (Exp §6.4)
  3. Write one retrieval prompt you would actually use in your hands_on_lab. (Exp §5.5)
  4. Where are agents brittle, and where are they still worth using? (Exp §5.6)

Sunday

  1. Answer all self-check questions from 01_weekly_plan.md without notes.
  2. Explain your hands_on_lab architecture using only the words: think, act, observe, state, stop.
  3. What would break first if module 10 added MCP tomorrow? (Exp §5.7-§5.8)
  4. [Bridge] Why does multi-agent orchestration fail if single-agent loops are weak?