Skip to main content

System design answer

A refund agent for an online store

A tool-using agent with task-shaped tools, rules for what it may do alone, human approval above a limit, and full audit.
The question“Design an agent that handles refund requests end to end: checks the order, decides, and issues the refund.”

1Clarify0-5 min

Ask before you draw. These answers change the design.

  • What refund policy applies, and which cases are judgement calls?
  • Up to what amount may it refund without a person?
  • Which systems: orders, payments, courier tracking?
  • How many requests a day?

2Requirements and numbers5-8 min

It must

  • Read the order and delivery status
  • Apply the refund policy and explain the decision
  • Issue refunds within limits; ask a person above them
  • Tell the customer the outcome

And it must be

  • No refund issued twice for the same order
  • Every step logged with its reason
  • A person can stop the agent at once

Numbers to say out loud

Volume
8,000 refund requests a day
Steps per run
4-8 tool calls, under 30 s
Approval share
About 10% need a person

3High-level design8-12 min

  1. Customer request → Agent loop
  2. Agent loop → get_order (read)
  3. Agent loop → get_delivery_status (read)
  4. Agent loop → refund_quote (read)
  5. refund_quote (read) → Within the auto limit?
  6. Within the auto limit? → yes → issue_refund (idempotency key = order id)
  7. Within the auto limit? → no → Human approval card
  8. Human approval card → approved → issue_refund (idempotency key = order id)
  9. issue_refund (idempotency key = order id) → Tell the customer
  10. Tell the customer → Audit log

4Deep dives12-26 min

Tools

Three read tools and one action tool, each with a strict schema. issue_refund takes a quote id, not an amount, so the model cannot invent a figure, and uses the order id as an idempotency key.

Approval

Rules decide what is automatic: under ₹2,000, delivered and within policy. Everything else pauses with a checkpoint and an approval card showing the evidence; no reply in 4 hours escalates.

5Failures26-30 min

What can go wrongWhat stops it
Double refundIdempotency key on the order; the payment API rejects repeats
Agent loopsStep cap of 10 and repeated-call detection
Injected instructions in the messageThe refund amount comes from the quote tool, never from text
Runaway costToken budget per task and a kill switch

6Evals and monitoring30-33 min

  • Sandbox runs with seeded orders: right refund state, approval before large refunds, zero safety violations
  • Success on all of 3 runs per task
  • Human review of a weekly sample of decisions

7Trade-offs33-35 min

  • An agent over a fixed workflow only because cases vary; simple cases could be a workflow
  • A lower auto limit means more approvals but less risk

Follow-ups to expect

  • How do you stop it from being talked into a refund?
  • How would you test it before launch?

Practise out loud in the mock interview

Today's AI turns are used

Lessons, roadmaps, videos, practice cards and the code playground stay free with your account, with no limit.