Chapters

Every chapter, grouped by Part. Use the card metadata to calibrate how much trust to place in a chapter's specific claims.

Part 1

  1. Chapter 0 verified 2026-06-03

    Why evaluation is the scarce skill

    Model training is commoditizing; knowing whether a system actually works is not. Why evaluation is the highest-leverage AI-engineering skill of 2025–26, what interviews test, and the four-dimension lens this guide grades you against.

  2. Chapter 1 verified 2026-06-08

    The evaluation mindset

    Before any metric: how is the output used, what does each error cost, and what failures do you fear? The evaluation mindset — error taxonomy before metrics — drilled on three systems where the obvious metric hides the real failure.

  3. Chapter 2 verified 2026-06-03

    Offline metrics and the threshold trade-off

    Precision, recall, F1, and the operating point — why a single accuracy number lies on imbalanced data, and how to choose a threshold from the business cost of each error. You build the metrics in mini_eval and feel the trade-off in an interactive demo.

  4. Chapter 3 verified 2026-06-08

    Confidence intervals and statistical rigor

    A metric from a finite eval set is a random quantity. Bootstrap confidence intervals, paired model comparison, and a permutation test — built in mini_eval — to answer the question behind every leaderboard: is B really better than A, or did it just win the sample?

  5. Chapter 4 verified 2026-06-08

    Calibration and reliability

    A model can rank risk perfectly and still lie about probabilities — saying 90% on a batch it gets right 60% of the time. Discrimination vs calibration, reliability diagrams, ECE and Brier built in mini_eval, and why a calibrated probability is the product when a human acts on it.

  6. Chapter 5 verified 2026-06-08

    Data integrity: leakage, contamination, reproducibility

    The fastest way to a great eval number is a broken eval set. Train/eval overlap, parametric-memory leakage in RAG, adaptive overfitting from tuning on a fixed set, benchmark contamination, and the reproducibility hygiene — frozen sets, pinned versions, seeds — that makes a number mean something.

  7. Chapter 6 verified 2026-06-08

    Reference-based vs reference-free evaluation

    Do you have a golden answer to compare against, or not? That single question routes every grading decision — exact match and verifiers when there's one right answer, embedding similarity and multiple references when many phrasings are valid, and reference-free LLM judges when there's no gold at all.

  8. Chapter 7 verified 2026-06-03

    LLM-as-judge and its biases

    Using a strong model to grade another model's outputs is the workhorse of modern evaluation — and it is biased in predictable, demonstrable ways. Position, verbosity, and self-preference bias, why they happen, and the swap-and-aggregate mitigation, built in mini_eval with no live model.

  9. Chapter 8 verified 2026-06-08

    Benchmark literacy

    MMLU, GPQA, HumanEval, SWE-bench, GAIA, Chatbot Arena, HELM, LiveBench — what each actually measures, and the three threats that turn a headline score into a lie: saturation, contamination, and construct validity. How to read a leaderboard like an engineer, not a marketer.

  10. Chapter 9 verified 2026-06-08

    RAG evaluation

    A retrieval-augmented system is two systems in a trenchcoat — a retriever and a generator — and a single end-to-end score hides which one failed. Retrieval metrics (precision@k, recall@k, NDCG) in mini_eval, faithfulness for the answer, and the Type-I vs Type-II hallucination split that tells you which half to fix.

  11. Chapter 10 verified 2026-06-08

    Agentic and task evaluation

    An agent is stochastic and multi-step, so 'did it work?' becomes 'how often, over how many tries, and did it get there the right way?' pass@k vs pass@1 built in mini_eval, why a single successful demo is an anecdote, and grading the trajectory — tool use, efficiency, cost — not just the outcome.

  12. Chapter 11 verified 2026-06-08

    Production evaluation and monitoring

    Offline eval is a snapshot; production is a stream. Why a frozen offline metric stays green while live quality drifts, the online signals and guardrails that catch it, drift detection, cost and latency as first-class metrics, and the alerting that turns evaluation into a continuous process.

  13. Chapter 12 verified 2026-06-08

    Capstone: design an evaluation strategy

    The interview question this whole guide was for: 'design an evaluation strategy for this system.' A framework that is just the guide in order — clarify the use, choose metrics, protect the data, quantify uncertainty, decompose the pipeline, and monitor in production — with the four-dimension rubric as the scorecard you're graded on.

Part 2

  1. Chapter 0 verified 2026-06-09

    Why LLM application engineering is the scarce skill

    Calling a frontier model is one line; turning that call into a system someone can rely on is the job. The LLM-app stack — model, retrieval, orchestration, evaluation — what each layer owns, why integration (not training) is the interview-tested skill, and the three shortcuts that look like the answer and aren't.

  2. Chapter 1 verified 2026-06-09

    Prompt engineering as a discipline

    Prompting isn't magic words — it's writing a spec. What to pin down (role, context, instruction, format), why anything code consumes needs a structured-output contract you validate, and why prompts are code: versioned and tested against a held-out set, not three happy-path examples.

  3. Chapter 2 verified 2026-06-10

    Retrieval 101 — embeddings and vector search

    Why retrieval exists, and how it actually works: vectorize, score by cosine, take the top k. You build the whole mechanism as a readable TF-IDF index, watch exactly where lexical matching misses (paraphrase, morphology), see what dense embeddings change — only the vectorizer — and scale the same idea honestly through ANN and vector stores chosen by constraints.

  4. Chapter 3 verified 2026-06-10

    Chunking and document representation

    Retrieval ranks chunks, not documents — so the chunker decides what a vector can even represent. Build three honest strategies (fixed, sentence, paragraph) plus overlap, see a real fact get cut in half and lost, learn why extraction quality is the ceiling and tables are first-class, and measure chunking like an engineer instead of eyeballing it.

  5. Chapter 4 verified 2026-06-10

    RAG end-to-end: retrieve, assemble, ground, generate

    Assemble the full RAG pipeline and own every stage of it: retrieval feeds a budgeted context assembly, a grounded prompt wraps the survivors, and a generator answers — or abstains. Build it with a per-stage trace, learn the four failure points (retrieval, context window, extraction, generation), and diagnose upstream-first instead of blaming the model.

  6. Chapter 5 verified 2026-06-10

    Evaluating RAG: the builder's loop

    The Evaluation guide teaches the metrics; this chapter wires them into the build. Construct a golden set from your own corpus (including should-abstain rows), evaluate the retrieval half and the generation half of your pipeline separately, and decide between configs with outcome categories instead of vibes — the instrument that turns 'B felt better' into an engineering call.

  7. Chapter 6 verified 2026-06-10

    Advanced RAG: reranking, hybrid retrieval, and query rewriting

    The upgrades that attack ranking quality itself — and the judgment to buy them in the right order. Two-stage retrieval with a reranker (never over the whole corpus), hybrid lexical+dense fusion with RRF, stemming as a vectorizer swap, query expansion through HyDE, and the routing family (Self-RAG, CRAG, Graph-RAG) — each priced in latency and complexity, each verified against Chapter 5's golden set.

  8. Chapter 7 verified 2026-06-10

    RAG in production: latency, cost, and what to watch

    The two budgets every production RAG system answers to — milliseconds and dollars — and the instrumentation that keeps it honest. Latency anatomy (TTFT vs decode, and why output length is the forgotten multiplier), token economics (caching, cascades, the self-host break-even), and observability that watches the knowledge boundary, not just the GPUs.

  9. Chapter 8 verified 2026-06-10

    Agents and tool use: the loop that decides

    An agent is a loop in which the model decides what happens next — which makes control flow, cost, and failure all stochastic. Build the loop with its guards (budgets, loop detection, errors-as-observations), learn tool design as the reliability lever, gate the writes, and earn the judgment call interviews actually probe: when an agent is the wrong answer.

  10. Chapter 9 verified 2026-06-10

    Multi-agent orchestration: when one loop becomes a team

    Multi-agent earns its cost in exactly three currencies — specialization, parallelism, and clean-context decomposition — and charges for it in coordination. Build the supervisor pattern (workers with least-privilege tools and single-ticket contexts), make failure isolation real (one worker's loop costs one handoff, not the run), and learn the coordination failures by name: deadlock, livelock, contention.

  11. Chapter 10 verified 2026-06-10

    Prompt, RAG, or fine-tune: the judgment chapter

    The #1 judgment question in AI-engineering interviews, answered the way seniors answer it: lead with when NOT to fine-tune. The behavior-vs-knowledge split, the data-availability funnel (prompt → RAG → SFT → DPO), the distillation-for-economics case, and the three evaluation gates that a fine-tune must pass before it ships — plus the costs that aren't the training run.

  12. Chapter 11 verified 2026-06-10

    Capstone: design an LLM application, under interview conditions

    Forty-five minutes, one sentence: 'Design a customer-support AI for a mid-size bank.' The capstone assembles the whole guide into the 5-step framework that drives an AI system-design interview — problem framing, architecture, deep dive, trade-offs, eval — with a worked bank-bot mock, a diagnose-the-gap drill, and the four-dimension rubric as your scorecard.

  13. Chapter 12 verified 2026-06-10

    Interview craft and transfer: the skill above the skills

    The meta-chapter: why communication outranks knowledge in documented rejection reviews, the craft loop that makes reasoning visible, the new AI-assisted coding round and the verification-under-automation skill it actually grades, and deliberate practice for transfer — mapping questions you've never seen onto the structures this guide built.

Part 3

  1. Chapter 0 verified 2026-06-10

    Why production is where AI systems live or die

    The demo worked, the offline eval passed, the dashboards are green — and the system is failing anyway. The production loop — deploy, serve, observe, evaluate, respond — what each stage owns, why AI systems fail silently in ways classical services don't, and the three post-launch myths that let them.

  2. Chapter 1 verified 2026-06-13

    Deploying AI safely — shadow, canary, flags, fallback

    The production loop starts at deploy: getting change into production — including the changes you didn't make, like a provider swapping the hosted model under you — without letting it surprise users. The four mechanisms (shadow, canary, feature flag, fallback), why a model-id change is a release and not a config tweak, and why every promotion gates on the golden set rather than on green dashboards.

  3. Chapter 2 verified 2026-06-13

    Latency anatomy — TTFT, decode, and where time goes

    A traffic spike broke p99 while per-request latency never changed — because a slow system under load is a queue, not a slow model. Where a request's time actually goes (prefill vs decode, and why you never quote latency without the output-length assumption), why latency is a distribution measured at the tail, and why capacity = serving slots / service time is the arithmetic that explains the cliff.

  4. Chapter 3 verified 2026-06-13

    Throughput & efficiency levers — quantization, batching, speculation

    Chapter 2's fix for a latency cliff was 'more concurrency' — but every serving slot holds a KV cache in VRAM, so batch size is memory-bound, not free. The KV-cache ceiling on batching, and the three levers that get more requests through a fixed GPU — quantization (free memory), continuous batching (kill idle slots), speculative decoding (more tokens per step) — each matched to the bottleneck it actually attacks, and the cost each one carries.

  5. Chapter 4 verified 2026-06-13

    Cost engineering — routing, cascades, caching economics

    Chapter 0's bot ran 4× over budget. The bill decomposes into per-query token cost times volume, and the two biggest levers aren't efficiency — they're the cascade (route the easy majority to a cheap model, escalate the rest) and the cache (don't run a model on a question you've answered). The catch the island makes visceral: a cascade only saves money if its routing signal is calibrated, and a cost number without a stated accuracy floor is not a saving.

  6. Chapter 5 verified 2026-06-13

    The observability stack — metrics, logs, traces, and evals

    Every serving decision in the last block assumed you could see what the system did — but a metric tells you p99 is high, not where in which request the time went, and none of the classic three pillars watch the one dimension that matters for an AI feature: was the answer right. The four pillars (metrics, logs, traces, evals), how to read a trace to locate where a request spent its time, and which pillar answers which question.

  7. Chapter 6 verified 2026-06-13

    Evaluating in production — sampling, judges, and regression gates

    The eval pillar, operated on live traffic. You can't score every request, so eval-in-prod is sampling — grade a fraction with the same metric you validated offline. And because you sampled, the number has error bars, so a regression gate must fire on a confidence interval (a drop beating sampling noise), not the point estimate. Plus what you sample (stratify the hard segments) and whether your judge is valid matter as much as how much.

  8. Chapter 7 verified 2026-06-13

    Drift & quality decay — detecting the slow failure

    Chapter 0's worst failure had no change to blame: groundedness slid for a month as the help center was reorganized and the query mix drifted, and every point-in-time gate stayed green. Drift is the failure a frozen offline set and a two-point regression gate both miss. The three pieces of a drift monitor — a rolling window to smooth the signal, a non-parametric rank test (Mann-Whitney) to detect a distribution shift, and an SLO guardrail to fire the alert — and how to tell drift from a regression.

  9. Chapter 8 verified 2026-06-13

    Guardrails in production — input gates, output gates, gated actions

    The observe and evaluate stages let you see a bad answer; they don't stop it reaching the user. The respond stage starts with guardrails — the real-time gates that prevent a harmful or manipulated output from going out. Why prompt injection (OWASP LLM01) is a structural failure no system prompt fully fixes, the defense-in-depth stack (input gate, output gate, gated action), and why some failure classes must be blocked at the boundary, not detected after.

  10. Chapter 9 verified 2026-06-13

    Incidents & reliability ops — SLOs, runbooks, degradation modes

    Guardrails stop the failures you anticipated; the bad day is the one you didn't. Reliability as a budget, not an absolute — an SLO with an error budget you spend on velocity, applied to AI quality and not just uptime. Degradation modes that turn an upstream outage into a graceful fallback, and runbooks that turn a 3 a.m. alert into a tested procedure: mitigate first (flip the flag, roll back), then find the cause.

  11. Chapter 10 verified 2026-06-13

    Self-host vs API vs hybrid — the standing judgment call

    Every chapter so far quietly assumed a hosted model API. The standing decision underneath: self-host the model, call an API, or run a hybrid. The break-even is real arithmetic — a fixed monthly GPU cost versus a per-query API bill, with a crossover volume — but cost is necessary, not sufficient. Latency, data residency, control, and the operational burden of owning your own serving stack (every prior chapter becomes yours) routinely decide it before volume does, and a hybrid often captures most of the savings at a fraction of the ops.

  12. Chapter 11 verified 2026-06-13

    System-design capstone — production-grade

    Ten chapters built the production loop one stage at a time; an interview hands you a blank whiteboard and 'design a production AI system' all at once. The method that composes them: lead with requirements and SLOs before architecture, derive the design from the loop's stages, defend each trade-off against a stated target, and anticipate the failure modes — naming the loop mechanism that bounds each. A worked capstone (a bank's internal policy-Q&A bot) walks the whole thing end to end.

  13. Chapter 12 verified 2026-06-13

    Interview craft & transfer — the production story

    The same production experience reads as junior or senior depending on how you tell it. The signals interviewers actually read for seniority — leading with requirements and SLOs, estimating cost and latency unprompted, raising evaluation before being asked — and the documented failure modes they counter ('no production experience', 'ignoring ops/cost/eval'). How to transfer the production loop to any system the interviewer invents, and how to rewrite a weak answer into a strong one. The closing chapter, which returns to the question that opened the guide.

Part 4

  1. Chapter 0 verified 2026-06-14

    Why working with AI is its own engineering skill

    The AI wrote the feature, it compiles, the tests pass — and the interviewer's next question ends the loop: why is it built this way, and what breaks on the input nobody tested? Working with AI is a distinct skill from coding and from prompting: the bottleneck moved from producing code to governing, verifying, and explaining code you didn't type. This chapter frames the loop the rest of the guide builds.

  2. Chapter 1 verified 2026-06-14

    What interviewers actually test

    Two candidates, the same problem, the same AI, the same correct final code — one passes, one fails. The artifact isn't the assessment. AI-assisted rounds score four things the model can't do for you: strategic clarification, comprehension, verification, and communication — which map exactly onto the series' four-dimension rubric, with the stakes raised because the typing no longer proves you understood anything.

  3. Chapter 2 verified 2026-06-14

    Clarify before you code

    The loop's first stage and its highest return. An AI assistant amplifies your aim — including when it's wrong — and never pushes back on a vague request the way a human collaborator would. So the discipline of pinning the real problem before you prompt, once shared with a teammate, is now entirely yours: a twenty-second question against an hour of confidently solving the wrong problem.

  4. Chapter 3 verified 2026-06-14

    Preregistration: commit the target before you prompt

    Borrowed from science, where you register your hypothesis and analysis before seeing the data so the data can't rationalize you. In AI-assisted work the 'data' is the model's output: decide what 'right' means — the interface, the invariants, the tests — before you prompt, so the output is gated against a standard instead of becoming the standard. This is the durable, tool-version-proof skill: governance over automation, not prompt theater.

  5. Chapter 4 verified 2026-06-14

    Strategic prompting: the prompt is a specification

    Prompting is not incantation and not the whole skill — it's the stage where your committed spec becomes a precise request. A vague prompt outsources the specification to the model's statistical defaults; a precise one hands over the invariants and constraints you preregistered. The judgment calls: decompose or one-shot, and what to constrain — including the negatives the model will otherwise fill in for you.

  6. Chapter 5 verified 2026-06-14

    Reading AI-generated code

    Comprehension is the loop stage automation can't do for you, and reading code you didn't write is harder than reading your own — you must reconstruct intent from output instead of building it as you go. Worse, AI code is fluent by construction: clean, idiomatic, well-commented whether or not it's correct, and that polish actively suppresses your skepticism. The discipline is active reading against the spec you committed, hardest exactly where the code looks cleanest.

  7. Chapter 6 verified 2026-06-14

    Verification under automation

    Executing AI code on the example you were handed is the weakest possible evidence — it's the case most likely to pass. Verification is running the output against the standard you preregistered: the boundaries, the invariants, the adversarial cases. This chapter closes the loop's solo stages — prompt, review, run, confirm — and turns a failure into a precise debugging prompt instead of prompt-roulette.

  8. Chapter 7 verified 2026-06-14

    Communication while you delegate

    The loop's sixth stage, and the one most strong candidates underweight — it runs through all the others rather than coming last. When you wrote every line, the code was a trace of your thinking; now the AI writes the lines, so the code traces its thinking and yours is invisible unless you voice it. Silent competence reads as luck. Narration is the interviewer's main window into the comprehension and verification that automation hid — which is why communication is this guide's weighted dimension and the single most common reason strong candidates are rejected.

  9. Chapter 8 verified 2026-06-14

    Anti-patterns: failing while the code looks fine

    The named failure modes of AI-assisted work are dangerous precisely because they mimic the virtues: speed looks like skill, confidence looks like comprehension, a passing demo looks like verification. Copy-paste automation, prompt theater, automation bias, and the velocity trap each feel productive and often pass the immediate check — then fail the follow-up question or the boundary input. Each is a skipped loop stage wearing a costume; telling the anti-pattern from its look-alike virtue is the skill, and the loop is the cure.

  10. Chapter 9 verified 2026-06-14

    Agentic workflows: governing what you can't read

    The loop scales from a single function to multi-file, agent-driven work — and an agent doesn't change the loop, it changes what you can hold in your head. You can no longer read every line, so governance shifts from per-line review to per-checkpoint review: scope the work into units small enough to preregister and verify, gate between them, and govern the seams, the gate, and the riskiest units rather than every line. This is what the un-one-shottable interview problems are built to test.

  11. Chapter 10 verified 2026-06-14

    Evaluating AI-assisted output

    When AI produces output at volume — code across a repo, or generations as a feature — reading samples is the happy-path trap at scale. You need a standard you can run automatically: a golden set, properties, a gate. For deterministic code that's a test suite in CI; for non-deterministic generative output it's measured quality (metrics or an LLM judge) over samples — which is the evaluation discipline of Guide #1, pointed at the AI's output you're now responsible for. Preregistration grown up into a standing eval.

  12. Chapter 11 verified 2026-06-14

    Provenance & accountability

    You can delegate the typing, not the accountability. The moment you ship or approve AI output, you own it as if you'd written it — 'the AI wrote it' is not an explanation, an excuse, or an audit answer. Provenance is how you make that ownership real: what was AI-generated, what it was reviewed and tested against, who approved it. For your own work the loop itself is your provenance — the ability to explain and defend the code; for teams and regulated systems it becomes an explicit record.

  13. Chapter 12 verified 2026-06-14

    Interview craft & transfer: the whole loop in one room

    The capstone: the whole skill run at once, under interview conditions, on a problem you haven't seen. Time pressure and an observer make the two highest-value stages — clarify/preregister and explain — the first to drop, so the craft is rehearsing the loop until it survives. A worked mock round, annotated against the four-dimension rubric, then a self-assessment you can run on your own attempt. The loop and the rubric are problem-independent — that's what transfers.