Every module produces or corrects a real artifact — a prompt, a rubric, a golden answer, an audit. Every artifact is scored against published rubrics with written feedback. The method is the lesson.
Golden answer first · Reverse-engineer criteria · Atomize (one idea per criterion) · Difficulty-check against a live model · Evaluate blind.
Fabrication · Omission · Misapplication · Presentation. Every QC review maps errors to a family before a word of feedback is written.
"Could a stranger judge this criterion true/false without seeing the prompt, the sources, or any other criterion?" Drilled until reflexive.
Consistency is the point. You always know what a module contains, how long it takes, and how you will know whether it landed — so the only thing that varies between modules is the difficulty of the craft itself.
The method demonstrated rather than described — worked on a real artifact, at the pace you would actually work. Recorded, so you can stop it and rewind the part that mattered.
The same ground in prose, with the rules, the tables and the checklists you will keep open on a second screen while you build. This is the part you return to a year from now.
A brief check at the end of the module. Not a hurdle — a mirror. It tells you whether you actually absorbed the module before you build on top of it.
Every module in this Handbook carries all three. The chips beneath each module below are a reminder, not an exception list.
Everything below — all eighteen modules, F1 through R4, and what each one asks of you — is published in full and free to read. We would rather you knew exactly what you were buying before you bought it.
What one payment unlocks is the Handbook itself: the eighteen video explainers, the eighteen written explainers with their rules, tables and checklists, the module quizzes, the comprehensive exam, and the Handbook as a PDF and Word file you keep.
One payment. No cohort, no start date, no subscription.
How models are trained (pretraining → SFT → RLHF → evals) in plain language; who buys expert data and why; where the money concentrates; honest market risks.
Prompts, input files, golden answers, rubrics, spec sheets; attempter/reviewer/auditor roles; how a package flows through QA.
Realistic persona and context, timelessness, jurisdiction clarity, explicit deliverables, objective gradability. Exercise: repair three broken prompts.
The rubric as the training signal; self-contained criteria; one idea per criterion; verb-first, objective wording. Exercise: five criteria, auto-checked.
Application mechanics, the expert profile, time and rate economics, contractor basics, burnout prevention.
What we never do — and why integrity is the graduate’s competitive asset. Signed as a condition of certification.
Legal and Finance tracks share the spine; each applies it through domain labs.
Tasks that stump strong models legitimately: multi-step dependency chains, document-grounding, plausible red herrings. Legal lab: layperson-voice, jurisdiction-identifiable scenarios. Finance lab: cascading calculations across documents.
Realistic synthetic source material; document-authenticity standards; file hygiene. Artifact you produce: a 3-document input set.
The GRADE Loop end-to-end: composition, logical-progression ordering, bounded ranges, the name-swap test, offline evaluability.
Affirmative failure-mode negatives; criticality discipline; weighting so reasoning carries ~75–80% of points. Legal lab: IRAC-decomposed rubrics. Finance lab: formula-vs-solution separation.
Perfect-answer-first; citation integrity verified against primary sources. Artifact you produce: a golden answer + rubric pair, peer-graded blind.
SFT vs. RLHF evaluation; strict annotation formats; preference justifications; timed calibration practice.
Reading feedback without ego; the Four Failure Families on your own work; self-review checklists; professional escalation.
Portfolio assembly; platform strategy; rate negotiation with real market data; the attempter → reviewer → auditor ladder. Capstone review.
Verify first, annotate second; independent verification of every claim against primary sources; ambiguity analysis; documenting "considered but not flagged."
Full-package audits: prompt ↔ inputs ↔ golden ↔ rubric consistency; criterion-by-criterion rubric audit; findings vs. preferences; severity discipline.
Consolidated, specific, warm, actionable author-facing feedback; the economics of review throughput.
Three packages audited independently, calibrated against reference audits — inter-rater agreement becomes your credential evidence.
Not a trailer — the actual method, in the same voice you get in every module.
Module quizzes tell you whether a module landed. The comprehensive exam asks the harder question: can you hold the whole craft at once, the way a real task package demands — a prompt, its files, its rubric and its audit, all of which have to agree with one another.
Not a recap of the final module. Questions draw across F1 to R4 and deliberately cross module boundaries, because that is where the real failures live — a rubric criterion that contradicts the prompt, a file that leaks the answer the rubric is testing for.
You are shown real task packages and asked what is wrong with them, what would be rejected, and why. Recognising a defective prompt is a different skill from writing a good one, and reviewers are paid for the first.
Passing it is what a proctored credential is eventually built on. Until the certification launches, it is the honest self-test: it tells you whether you are ready to submit work for money.
The comprehensive exam is untimed, and you can sit it as many times as you like. It is included with full access, like everything else here.
The same spine, re-cut for your context: a diagnostic of your instructions and QA outcomes, custom labs built on your task types (NDA-firewalled), pre/post approval-rate measurement, and an optional train-the-trainer license.
Enterprise programs →A proctored, scenario-based exam and blind portfolio review leading to the "SME Standard Certified" credential — with a public registry and a 2-year maintenance cycle. The strategic goal: platforms fast-track credential holders.
Partner on recognition →