YOUR SCENARIO
How would you approach this?
An operations team wants a “multi-agent” system to classify requests, look up account status, and draft a response. The steps are usually predictable, but a few requests need investigation. What architecture would you start with?
This is an illustrative practice scenario. State any additional assumptions in your answer.
Make your case first.
Clarify the goal, identify the biggest uncertainty, outline an approach, and explain how you would test it. Spend about 8 minutes before opening the reference.
Your notes are not submitted or saved. Keep a copy before leaving this page.
Reveal reference approach Clarifying questions, decisions, and tradeoffs
Clarify before designing.
- Which decisions genuinely require choosing the next action from new evidence?
- Can investigation be separated from the routine path, and what can each path access?
One defensible approach
- 01
Model the routine path
Write the common process as explicit steps with typed inputs and outputs. Use normal application code for deterministic checks and a bounded model call where interpretation is needed. Keep an operator path for unsupported requests.
- 02
Locate the uncertain decisions
Prototype a single bounded agent for cases that require evidence-driven exploration. Specify allowed tools and terminal states. Compare it against the workflow on the same cases before introducing separate agent roles.
- 03
Justify any split
Add multiple agents only for a demonstrated need such as independent parallel work or distinct access scopes. Define the handoff contract, result validation, and shared-state ownership; measure coordination cost and failure propagation.
Explain the tradeoff
A workflow is easier to inspect but can become brittle when paths multiply. Dynamic investigation adds flexibility while making execution cost and behavior harder to bound.
Common mistakes
- Assigning an agent to every function before measuring a baseline.
- Treating role descriptions as enforced permission boundaries.
KEEP THE CONVERSATION GOING
Try the follow-ups.
- How do you prevent two workers from editing the same record?
- What evidence would persuade you to merge the agents again?
Review your own answer.
Tick the points you covered. This is a reflection checklist, not an automated score or a hiring prediction.
Check the underlying concepts.
The scenario and reference approach were written for SaveMyToken. These sources support the technical concepts; they do not report this question being asked by an employer.
Anthropic: Building effective agents ↗Anthropic: Writing effective tools for agents ↗