Loading...
Loading...
Browse 5 real-world technical and behavioral interview questions about Agents. Review scenarios, edge cases, and architectural best practices.
Give each tool one narrow purpose with a self-describing schema, return failures as structured results the model can act on rather than raising, take an idempotency key on anything that mutates, and put validation and authorisation in the executor because arguments produced by a model are untrusted input.
Indirect prompt injection is when instructions hidden in content the model reads are followed as if they came from you. Instructions and data share one token sequence, so there is no complete fix and the defence is architectural: least-privilege tools, filtered output, and human approval for side effects. It also connects llm security to the point an interviewer is testing.
Enforce step, token, wall-clock and monetary budgets in the orchestrator rather than in the prompt, detect repetition and lack of progress as separate conditions, and require an approval bound to specific arguments before any irreversible action. Exhausting a budget should hand back partial work, not vanish.
Assume the agent's context can be manipulated and control the exits instead. Scope each tool to the least data it needs, resolve the caller's identity in the executor rather than from a model-supplied argument, treat generated arguments as hostile input, and allow-list egress destinations.
Whenever you can draw the flowchart. A fixed pipeline with a model at the two steps needing judgement is cheaper, testable and debuggable, and per-step error compounds across a planning loop. Reach for an agent when the tool sequence is open-ended and the environment verifies the work.