Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

What should an agent be allowed to remember, for how long, and how do you delete memories, including the embeddings derived from them?

Define memory classes and their purpose, then inventory active records, derivatives, in-flight tasks and restored copies. Report retrieval denial and physical removal as separate milestones with evidence for each.

mediumNewUpdated Nov 2026

Define memory classes and their purpose, then inventory active records, derivatives, in-flight tasks and restored copies. Report retrieval denial and physical removal as separate milestones with evidence for each.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

The answer works through 4 follow-ups like an interviewer would

Alder removes a customer’s stored note. A summary and embedding depend on it, a draft job already loaded the summary, and an older backup is available for recovery.

  1. What if the primary note disappears but the summary remains?
  2. What if a queued worker publishes a new summary during cleanup?
  3. What if disaster recovery restores an older backup?
  4. What would you put in the completion report?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackDesign trust between AI agents owned by different organisations, such as your procurement agent and a supplier's sales agent.Next in this trackHow would you measure an agent's excessive-agency risk quantitatively, so you can compare designs and track it over time?Next in this trackWhat is scope drift in an autonomous agent, and how would you detect it from the agent's traces?
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.