Question 1

What are embeddings and what are they used for?

Accepted Answer

**Target Audience:** Engineers who keep hearing "it runs on embeddings" (search, RAG, recommendations) and want to know what an embedding actually is before building with one.
**Difficulty:** Easy
**Verified with:** Node 22.22.0 and Python 3.12.3 (the toy embedding program below; its 6-number word vectors are hand-written stand-ins for a learned model). Product facts are cited inline with the date they were checked (October 2026).

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

Question 2

What is a vector database and when do you actually need one?

Accepted Answer

**Target Audience:** Engineers starting a RAG or semantic search project who keep being told to "add a vector database" and want to know what that is and whether they need one yet.
**Difficulty:** Easy
**Verified with:** Node 22.22.0 and Python 3.12.3 (the sizing, filtered search and sync simulation below). The per-core speed in the sizing table is a stated assumption, not a measurement. Product facts are cited inline with the date checked (October 2026).

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

Question 3

What is RAG and why use it instead of fine-tuning for knowledge?

Accepted Answer

**Target Audience:** Beginners meeting retrieval-augmented generation for the first time, and engineers who need to defend "RAG, not fine-tuning" for a knowledge feature in an interview.
**Difficulty:** Easy
**Verified with:** Node 22.22.0 and Python 3.12.3 (a keyword retriever plus deterministic stub models; no real model or vector database is called). Papers cited inline were checked in October 2026.

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

Question 4

What are evals and why does every LLM feature need them?

Accepted Answer

**Target Audience:** Anyone building on top of an LLM API who has never written an eval, and candidates who need to explain why "it looked good in the playground" is not a test.
**Difficulty:** Easy
**Verified with:** Node 22 and Python 3.12 (an eval harness over two stubbed prompt versions, and a sampling simulation with Wilson intervals). No model is called; the stub replies stand in for a real model. Vendor guidance is quoted with its source, checked October 2026.

> **How to read this doc:**

Question 5

What is the difference between zero-shot, one-shot and few-shot prompting?

Accepted Answer

**Target Audience:** Beginners writing their first production prompts, and anyone who needs to explain in-context learning precisely in an interview.
**Difficulty:** Easy
**Verified with:** Node 22.22.0 and Python 3.12.3 (a ticket-classifier harness with a deterministic stub model; no real model is called). Paper results are cited inline, 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 the

Question 6

How do you build a golden dataset for evaluating an LLM feature?

Accepted Answer

**Target Audience:** Engineers who know why evals matter and now have to assemble the dataset behind them, and candidates asked to design one in an interview.
**Difficulty:** Medium
**Verified with:** Node 22 and Python 3.12 (a dataset builder over 200 simulated traces, and an inter-annotator agreement calculation). The traces and labels are synthetic and stated as such; no model is called.

> **How to read this doc:** Every idea is explained in plain language first, then tagged with `📌 Intervi

Question 7

Embeddings in 2025-26: how do you choose model, dimensions, and distance?

Accepted Answer

**Target Audience:** Engineers setting up retrieval who must commit to an embedding model, a vector size and a metric, and want a defensible way to choose rather than copying a blog post.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the truncation and quantization program below, on seeded synthetic vectors). Model facts, prices and limits are cited inline with the source and the date checked (October 2026); they change often, so treat them as examples of the mechanis

Question 8

Beyond Ragas: how do you eval LLMs with LLM-as-judge, DeepEval, and human eval?

Accepted Answer

**Target Audience:** Engineers who have one eval framework running (often Ragas on a RAG endpoint) and now need to evaluate the rest of an LLM product: summaries, support replies, agents, anything without a neat retrieval score.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the judge-calibration and review-routing example below). DeepEval and G-Eval details were checked against the DeepEval docs, PyPI and the G-Eval paper via web search in October 2026; where only sec

Question 9

Cost optimization for LLM apps: how do you keep the bill predictable?

Accepted Answer

**Target Audience:** Engineers and tech leads who already know roughly what their LLM features cost, but whose monthly bill keeps surprising finance, and who need it to land within a known range.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (a 30-day spend simulation with and without controls, and a worst-case and reserved-capacity calculator). All prices and traffic in the examples are **hypothetical**; provider budget and capacity features are quoted from the Anthro

Question 10

Reranking in RAG: when and how to add a cross-encoder?

Accepted Answer

**Target Audience:** Engineers who already understand what a reranker is and now have to decide whether to put one into a real RAG system, which one, how deep, and inside what latency budget.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the depth sweep and timeout simulation below). The relevance scores are simulated with a seeded generator and the reranker latency comes from a stated cost model, so the numbers show the *method*, not a benchmark of any product. Vendo

AI ENGINEERINGDECODED.

Easy

What are embeddings and what are they used for?

What is a vector database and when do you actually need one?

What is RAG and why use it instead of fine-tuning for knowledge?

What are evals and why does every LLM feature need them?

What is the difference between zero-shot, one-shot and few-shot prompting?

Medium

How do you build a golden dataset for evaluating an LLM feature?

Embeddings in 2025-26: how do you choose model, dimensions, and distance?

Beyond Ragas: how do you eval LLMs with LLM-as-judge, DeepEval, and human eval?

Cost optimization for LLM apps: how do you keep the bill predictable?

Reranking in RAG: when and how to add a cross-encoder?

What chunking strategies exist and how does chunk size affect RAG quality?

What is context engineering and how does it differ from prompt engineering?

What is chain-of-thought prompting and when does it actually help?

Hard

How do you evaluate a RAG pipeline end to end?

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

What are common RAG failure modes and how do you debug them?

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

Fine-tune vs RAG vs prompt engineering: how do you choose in 2025-26?

How do you monitor LLM quality drift in production?

How do agents maintain memory across steps and sessions?