Module quiz

17 questions · pass bar 80% · retry as often as you like — your best score counts toward the gate.

  1. 1.Per Anthropic's taxonomy, what distinguishes a workflow from an agent?
  2. 2.You must translate a 200-page document into 6 languages, and each translation is independent. Which workflow pattern fits best?
  3. 3.What distinguishes orchestrator-workers from plain parallelization?
  4. 4.Why is a max-iterations cap insufficient as your only hard termination guard?
  5. 5.Your agent keeps calling the same failing tool with the same arguments. Which set of defenses addresses this directly?
  6. 6.What is ReAct, and how does modern native tool calling differ from the original technique?
  7. 7.Which trio of techniques keeps context from exploding across a 15-iteration run?
  8. 8.When does adding an upfront 'plan first' step help, and when does it hurt?
  9. 9.What belongs in an agent's trace log, and what's the right format?
  10. 10.A high-volume task (100k runs/day) currently uses an agent that works. Why argue for converting it to a workflow?
  11. 11.In an evaluator-optimizer loop, what failure mode must you actively defend against?
  12. 12.Why add an explicit finish(answer, citations) tool instead of just accepting the model's end_turn text as the final answer?
  13. 13.An agent loop returns its final answer with resp.content[0].text. It works today. Why is this a latent bug, and what's the robust version?
  14. 14.You add context compaction that rewrites old tool results into stubs before every API call. Context shrinks, but per-run cost goes UP. What happened?
  15. 15.What's the correct relationship between telling the model its remaining budget ('~4 tool calls left, start converging') and enforcing the budget in your loop?
  16. 16.Your loop bails out mid-iteration when the budget trips — right after an assistant response containing tool_use blocks — and the final wrap-up call returns a 400. Why, and what's the fix?
  17. 17.A user asks about a topic with no matches, search returns an empty list, and the agent confidently summarizes notes that don't exist. What's the highest-leverage fix?