Question 1

What belongs in the system prompt versus the user message?

Accepted Answer

**Target Audience:** Engineers wiring their first chat-API feature who are unsure which text belongs in which role.
**Difficulty:** Easy
**Verified with:** Node 22.22.0 and Python 3.12.3 (a request builder with a simulated byte-exact prefix cache; no real model is called). Provider API facts are cited inline from their docs or forum posts, checked October 2026.

> **How to read this doc:** Every idea is explained in plain language first, then tagged with `📌 Interview term:` so you also learn th

Question 2

What is the Model Context Protocol (MCP) and what problem does it solve?

Accepted Answer

**Target Audience:** Engineers who have used tool calling and keep hearing "just ship an MCP server", and anyone preparing for an AI engineering interview.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (both examples, identical output). Protocol details were checked in October 2026 against the published SDK packages themselves: `@modelcontextprotocol/sdk` 1.32.1 (the v1 line, spec up to 2025-11-25), `@modelcontextprotocol/server` and `@modelcontextprotocol/core` 2.3.1

Question 3

How do you scope retrieval with metadata filtering and multi-tenancy?

Accepted Answer

**Target Audience:** Engineers putting RAG into a multi-customer (B2B) product, or into a company where not every employee may read every document.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the filtered-search and authorization simulation below). Vector database behaviour is cited from vendor documentation with the date checked (October 2026); the SQL snippets are labelled "not run here".

> **How to read this doc:** Every idea is explained in plain language first

Question 4

How do you handle PII and sensitive data when calling LLM APIs?

Accepted Answer

**Target Audience:** Engineers putting a hosted LLM behind a product that touches customer data (support, CRM, HR, health, finance) and who need a design legal and security can sign off.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the redaction pipeline below). Provider retention terms were checked against the Anthropic docs and OpenAI's data-controls guide as summarised in search results, in October 2026. This is engineering guidance, not legal advice.

> **How to

Question 5

How do you sandbox an agent and enforce least-privilege tool access?

Accepted Answer

**Target Audience:** Engineers giving agents real tools (shell, files, network, API tokens) and candidates facing the "how do you keep an agent safe" question.
**Difficulty:** Hard
**Verified with:** Node 22.22.0 and Python 3.12.3 (both examples, identical output). Vendor references (Claude Code sandboxing docs, MCP SDK source comments, Simon Willison on the lethal trifecta) were checked by web search or by reading the published packages in October 2026.

> **How to read this doc:** Every idea i

Question 6

How would you design a production RAG pipeline end-to-end in 2025-26?

Accepted Answer

**Target Audience:** Engineers preparing for an AI or backend system design round who can explain RAG in one sentence and now need to design the whole thing: ingestion, retrieval, generation, numbers, operations and evaluation.
**Difficulty:** Hard
**Verified with:** Node 22.22.0 and Python 3.12.3 (the miniature pipeline and the sizing arithmetic below). Every input to the sizing is a stated assumption, and the prices in it are illustrative placeholders, not a vendor price list. Product facts ar

Question 7

What is prompt injection and how do you defend against it?

Accepted Answer

**Target Audience:** Engineers building LLM features that read outside content (web pages, emails, documents, tool results) or take actions, and anyone asked to explain why "just tell the model to ignore it" is not a defence.
**Difficulty:** Hard
**Verified with:** Node 22.22.0 and Python 3.12.3 (both examples below, identical output). Research and standards cited were checked by web search in October 2026: OWASP Top 10 for LLM Applications 2025 (via reference summaries), the OpenAI instruction

Question 8

How do you validate and repair structured LLM output at runtime?

Accepted Answer

**Target Audience:** Engineers putting LLM output into systems of record (databases, billing, tickets) who need a runtime layer that catches bad output and fixes what can be fixed.
**Difficulty:** Hard
**Verified with:** Node 22.22.0 and Python 3.12.3 (two programs: the validate-repair-fallback pipeline and the truncation demo). Library and provider behaviour is cited inline with the source, checked October 2026.

> **How to read this doc:** Every idea is explained in plain language first, then

Question 9

pgvector vs Pinecone vs Qdrant: how do you choose a vector DB in 2025?

Accepted Answer

**Target Audience:** Engineers and tech leads who have decided they need vector search and must pick between an extension in Postgres, a managed service and an open-source engine, then defend the choice.
**Difficulty:** Hard
**Verified with:** Node 22.22.0 and Python 3.12.3 (the filtered-search simulation below). Product behaviour, limits and pricing models are cited inline with the source and the date checked (October 2026). The title says 2025; the facts here are as found in October 2026, and

Question 10

What is red-teaming an LLM application and how is it done?

Accepted Answer

**Target Audience:** Engineers and tech leads asked to "red-team the assistant before launch" who want a method rather than a list of famous jailbreak prompts.
**Difficulty:** Hard
**Verified with:** Node 22.22.0 and Python 3.12.3 (the example below, identical output). Research, tools and standards mentioned were checked by web search in October 2026: Anthropic's Constitutional Classifiers announcement (February 2025), the Crescendo paper (Russinovich, Salem and Eldan; USENIX Security 2025), sec

AI ENGINEERINGDECODED.

Easy