Question 1

Context windows in 2025-26: how do you use 128k-1M tokens without drowning?

Accepted Answer

**Target Audience:** Engineers who have a 1M-token model available and need to decide when to use the window and when to keep retrieving.
**Difficulty:** Easy
**Verified with:** Node 22.22.0 and Python 3.12.3 (cost arithmetic, chunk reordering and a needle-test harness with canned answers; no real model is called). Model window sizes, prices and published guidance are cited inline with the date checked (October 2026); these change often, so check the provider docs for the model you use.

> **How

Question 2

What is a context window and what happens when you exceed it?

Accepted Answer

**Target Audience:** Beginners building chat features, RAG or agents who have hit (or will hit) "context too long" errors.
**Difficulty:** Easy
**Verified with:** Node 22.22.0 and Python 3.12.3 (a simulated provider with a 200-token window; no real model is called). Provider behaviour is cited inline from documentation and forum reports, 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 3

How do you get reliable structured JSON output from an LLM?

Accepted Answer

**Target Audience:** Engineers whose LLM feature has to hand JSON to ordinary code (a parser, a database, an API) and who want it to stop breaking.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the constrained-decoding simulation below). Provider API shapes were checked against the vendor docs and announcements cited inline, in October 2026.

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

Question 4

What are reasoning models and when should you use them?

Accepted Answer

**Target Audience:** Engineers who know how a regular LLM API call works and need to decide where a "thinking" model belongs in a product.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the example is deterministic arithmetic and stub answers; no real model is called). Product facts are cited inline with the source and the date checked (October 2026).

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

Question 5

How do temperature, top-p and other sampling parameters affect output?

Accepted Answer

**Target Audience:** Developers who call LLM APIs and want to set sampling parameters on purpose rather than by copying defaults.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the sampling pipeline in the example runs on a fixed logits vector; no real model is called). API parameter rules are cited inline with the source and the date checked (October 2026).

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

Question 6

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

Accepted Answer

**Target Audience:** Engineers who have heard "add let us think step by step" as a magic fix and want to know when it is worth its tokens.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (a stub model with a fixed compute budget per token, plus a real answer extractor; 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 al

Question 7

What is LLM-as-judge and what are its known biases?

Accepted Answer

**Target Audience:** Engineers about to let a model grade their model, and candidates who need to name the biases and the fixes precisely.
**Difficulty:** Medium
**Verified with:** Node 22 and Python 3.12 (a pairwise judge with a simulated position bias, and a scoring judge with a simulated verbosity bias). The judges are deterministic stubs with a bias built in on purpose, so the mechanism and the fix are visible; the size of the bias is an assumption, not a measurement of any model. Published

Question 8

What are RLHF and DPO, and how do they turn a base model into an assistant?

Accepted Answer

**Target Audience:** Engineers who use chat models every day and want to know what happened between "a model that continues text" and "an assistant that answers questions", without a reinforcement-learning background.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (a four-response toy, solved exactly; no real model is trained or called). Paper facts are cited inline with the date they were checked (October 2026).

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

Question 9

What is the ReAct pattern and why did it become the default for agents?

Accepted Answer

**Target Audience:** Engineers who know what an agent loop is and want to understand the pattern most agent frameworks are built on, including its history and what is still true today.
**Difficulty:** Medium
**Verified with:** Node 22.22.0 and Python 3.12.3 (the example below, identical output). Paper details were checked in October 2026 against the arXiv listing (2210.03629), the ICLR 2023 proceedings listing and the Google Research blog post on ReAct (November 2022).

> **How to read this doc:

Question 10

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

Accepted Answer

**Target Audience:** Engineers and tech leads who must choose how to adapt an LLM for a real product, and want a decision process they can defend with numbers rather than opinions.
**Difficulty:** Hard
**Verified with:** Node 22.22.0 and Python 3.12.3 (a freshness simulation, a cost model with **assumed** prices, and a rule-based decision table; no model is called). Provider and paper facts are cited inline with the date they were checked (October 2026).

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

AI ENGINEERINGDECODED.

Easy