Junior interview question
What are input and output guardrails?
Model answer
Input guardrails stop private data leaking to external APIs and bad prompts compromising the system. Output guardrails catch failures (format, facts, toxicity, private data, brand risk) and apply a policy: retry, repair, block or hand to a person.
Scroll sideways to see the whole diagram
AI Engineering: input guardrails protect against two risks: leaking private information to external APIs, and executing prompts that compromise your system.
Text version
- AI Engineering: input guardrails protect against two risks: leaking private information to external APIs, and executing prompts that compromise your system.
- The model runs on whatever passes.
- Output guardrails have two jobs: catch output failures, and specify the policy for handling each kind.
Practise the rest
6 Guardrails questions, 492 in all, each with a model answer. Free.