Home
Programs For Experts (B2C) For Companies (B2B) Curriculum Curriculum Licensing
About About Us Credentials Contact
Apply — Founding Cohort
Curriculum

Artifact-first. Graded like the industry grades. Domain-anchored.

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.

FOUNDATIONS COHORT AUDITOR
Original Frameworks

The spine of every program.

The GRADE Loop

Golden answer first · Reverse-engineer criteria · Atomize (one idea per criterion) · Difficulty-check against a live model · Evaluate blind.

The Four Failure Families

Fabrication · Omission · Misapplication · Presentation. Every QC review maps errors to a family before a word of feedback is written.

The Self-Containment Test

"Could a stranger judge this criterion true/false without seeing the prompt, the sources, or any other criterion?" Drilled until reflexive.

Level 1 · Self-Paced

Foundations — Modules F1–F6

F1

The Expert Data Economy

How models are trained (pretraining → SFT → RLHF → evals) in plain language; who buys expert data and why; where the money concentrates; honest market risks.

F2

Anatomy of a Task

Prompts, input files, golden answers, rubrics, spec sheets; attempter/reviewer/auditor roles; how a package flows through QA.

F3

Prompt Craft I

Realistic persona and context, timelessness, jurisdiction clarity, explicit deliverables, objective gradability. Exercise: repair three broken prompts.

F4

Rubric Craft I

The rubric as the training signal; self-contained criteria; one idea per criterion; verb-first, objective wording. Exercise: five criteria, auto-checked.

F5

Working the Platforms

Application mechanics, the expert profile, time and rate economics, contractor basics, burnout prevention.

F6

The Integrity Code

What we never do — and why integrity is the graduate’s competitive asset. Signed as a condition of certification.

Level 2 · Flagship · 4 Weeks

The Cohort — Modules C1–C8

Legal and Finance tracks share the spine; each applies it through domain labs.

C1

Prompt Craft II (Lab 1)

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.

C2

Building Input Worlds (Lab 2)

Realistic synthetic source material; document-authenticity standards; file hygiene. Graded: a 3-document input set.

C3

Rubric Craft II (Lab 3)

The GRADE Loop end-to-end: composition, logical-progression ordering, bounded ranges, the name-swap test, offline evaluability.

C4

Negative Criteria & Weighting (Lab 4)

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.

C5

The Golden Answer (Lab 5)

Perfect-answer-first; citation integrity verified against primary sources. Graded: a golden answer + rubric pair, peer-graded blind.

C6

Annotation & Preference Work (Lab 6)

SFT vs. RLHF evaluation; strict annotation formats; preference justifications; timed calibration practice.

C7

Surviving QC (Lab 7)

Reading feedback without ego; the Four Failure Families on your own work; self-review checklists; professional escalation.

C8

Career Architecture (Lab 8)

Portfolio assembly; platform strategy; rate negotiation with real market data; the attempter → reviewer → auditor ladder. Capstone review.

Level 3 · Advanced · 2 Weeks

Reviewer & Auditor Intensive — Modules R1–R4

R1

The Reviewer’s Method

Verify first, annotate second; independent verification of every claim against primary sources; ambiguity analysis; documenting "considered but not flagged."

R2

Audit Practice

Full-package audits: prompt ↔ inputs ↔ golden ↔ rubric consistency; criterion-by-criterion rubric audit; findings vs. preferences; severity discipline.

R3

Feedback That Teaches

Consolidated, specific, warm, actionable author-facing feedback; the economics of review throughput.

R4

Calibration Capstone

Three packages audited independently, calibrated against reference audits — inter-rater agreement becomes your credential evidence.