Reliability

Concept

AI Hallucinations Explained

Why LLMs make things up confidently — what causes hallucinations, why they're hard to fix, and the practical ways to reduce them.

Concept

Idempotency and Retries for LLM Workflows

How to retry failed LLM and tool calls without double-charging customers, sending duplicate emails, or corrupting agent state.

Interview

An LLM hallucinated a fake API in production code. How do you prevent this systematically?

Tests whether you treat LLM reliability as an engineering problem, not a model problem.

Interview

Your LLM keeps returning invalid JSON for structured outputs. How do you fix it systematically?

Tests production reliability — structured outputs power agents, evals, and integrations; failures can't be hand-waved.

Prompt

Incident Postmortem Facilitator

Structure a blameless postmortem and extract durable improvements from an incident.