GO TO A SECTION

↑ ↓ to navigate · Enter to openExplore all sections →
FDEInterviews logo
← AI Security, Privacy & Governance / 31
hardSalesforceOpenAIStripe

Design defense-in-depth for a support agent that can issue refunds and update customer records.

The agent has real money authority and a write path into the system of record, which is the exact shape attackers want. The strong answer is layered enforcement outside the model, with the spend cap and the chain rule in code, not in the prompt.

Updated Sep 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.

The agent has real money authority and a write path into the system of record, which is the exact shape attackers want. The strong answer is layered enforcement outside the model, with the spend cap and the chain rule in code, not in the prompt.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 548 remaining answers · ₹2,000 / $25

Every answer, concept and course, every paper breakdown, all published video lessons, hands-on FDE Lab missions, Premium PDF guides and companion files, the full practice-test bank and work-sample downloads. Referral Premium excludes guide PDFs and their companion files.

6 months · One payment · No auto-renewal

Study alongside free video lessons.

Related course lessons

Keep practising

Next in this trackDesign per-tenant data isolation and audit for a multi-tenant AI product. Where does cross-tenant leakage actually happen?PremiumNext in this trackYour customer's developers install MCP servers freely. Build the program that secures that tool-integration supply chain.PremiumNext in this trackWrite the incident runbook for a data-leak-via-model event: the assistant showed one customer's data to another.Premium
FEDITOR'S NOTE

This is the question where 'instruct the agent to be careful' dies fastest, because the action is irreversible and costs money; the only passing answer puts the spend ceiling and the approval gate in the tool layer with the user's scoped credentials. Watch for the candidate who secures the user input and forgets that an inbound ticket body is untrusted content that reaches the same agent. The senior move is tiering by materiality and reversibility so automation survives, then proving the worst case is bounded to 'what this support rep could already do', which is the sentence a CISO signs off on.

DISCUSSION · 0

No comments yet — be the first to share your approach.