Coding AI Interview Questions

Hallucination in RAG systems is the #1 production failure mode cited in AI engineering interviews. Your interviewer wants a systematic debugging framework — not a list of buzzwords. Learn how to measure faithfulness, fix retrieval precision, and layer mitigations the way senior engineers at Databricks and Meta actually ship RAG.

Claude Code is Anthropic's CLI coding agent designed for repository-level work: reading the codebase, editing multiple files, running tests/builds, and iterating until a task succeeds. Unlike autocomplete-first copilots that live inside the editor, Claude Code operates as an agent loop — observe → plan → act (edit/run tools) → verify.

A production Claude Code rollout is an agent platform problem, not a 'give everyone a CLI' problem.

Interviewers want a practical comparison, not marketing.

Codex CLI represents OpenAI's push into agentic coding outside the editor — similar category to Claude Code and other CLI agents. The core loop is: understand task → explore repo → edit → run commands → iterate.

A production AI coding agent typically includes:

This is an enterprise platform design question spanning agents, MCP, governance, and observability.

MCP (Model Context Protocol) defines a clean separation:

MCP multiplies agent power and attack surface.

Prompt injection is the #1 security interview topic for agents that read untrusted text.

Prompt engineering focuses on instruction wording. **Context engineering** focuses on the full state fed to the model each step: policies, repository maps, retrieved files, prior tool outputs, memories, and task specs.

Company-wide context is a platform product.

AGENTS.md is becoming the de facto 'README for agents.'

Governance is becoming the bottleneck — not model IQ.

Product teams shouldn't each reinvent agent security.

AI observability extends classic APM.

Treat agent models/prompts/tools like dependencies.

Part 2 of the LLM hallucination handbook — factual, citation, reasoning, math, code, temporal, context, and tool-use hallucinations; decoding risks; RAG failure modes; production case study.

Medium GPT API question on structured outputs reliability vs JSON mode.

**3.1** 128k context, stronger instruction following — update inference stack for long context KV cache.

**Fit** Non-interactive bulk — not user chat latency sensitive.

**Eval dimensions** SWE-bench-style tasks on private repo sample; CI fix rate; hallucinated APIs.

**Supervisor pattern** Central node decides next worker or FINISH based on plan and worker outputs — alternative to flat handoff messages.

**Pattern** Planner node outputs list of work items → map workers process each (possibly subgraph) → reducer synthesizes executive summary or ranked list.