The Harness Academy

Three paths · one shared foundation

Understand the machinery behind AI.

From absolute zero to Builder, Solution Architect, or Leader — three destination paths over one shared library, every core idea taught with a demo you can poke.

no signup · no API keys · demos run in your browser

Signature instrument · F1 / lesson 02

Watch a rule emerge.

deterministic system · a real perceptron

○IdleThe starting boundary is deliberately wrong.

0EPOCH — passes over examples

9/20MISTAKES — it gets wrong

▶ Auto-trainStep ×1Reset

Nobody tells it where the line goes — the rule emerges from examples. The three numbers it's adjusting? Lesson 2 →

01 · Sequence

Start at zero. Leave with judgment.

No prior AI knowledge is assumed, and a built-in bridge course means no prior coding is required either. Everyone walks F1–F3 first; then the paths diverge over one shared content library.

See it, don’t just read it. Every core idea comes with a deterministic browser demo you can step through.

Work at your pace. Checkpoints give instant feedback; capstones use published self-scoring rubrics.

Know when to say no. Judgment is a first-class course, not a footnote.

Foundation · everyone walks F1–F3

F1What Is AI, Actually?F2Working With AIF3Where AI Belongs

Builder →

• E0Just Enough Code (optional)
• E1Talking to Models in Code
• E2Grounding — RAG
• E3The Harness
• E4Evals & Reliability
• E5Shipping & Operating
• CapstoneBuild something real
• R1Local AI Workbench wing →
• D1Data Foundation wing →
• A1–A10Advanced Engineer wing (A-tier) →

Solution Architect →

• L1AI Judgment
• E0Just Enough Code (optional)
• E1Talking to Models in Code
• E2Grounding — RAG
• E3The Harness
• L2AI in the Organization
• L3Risk, Safety & Governance
• S1Discovery & Opportunity Qualification
• S2Solution Architecture for AI Systems
• S3Scoping, Estimation & the ROI Case
• S4Delivery, Adoption & Living with the Client
• S5The Vertical Playbook: Contact Center & CX
• CapstoneThe Engagement Brief
• R1Local AI Workbench wing →
• D1Data Foundation wing →

Leader →

• L1AI Judgment
• L2AI in the Organization
• L3Risk, Safety & Governance
• L4Leading AI Initiatives
• CapstoneThe initiative brief

M1–M5 + CapstoneModel Internals wing — a Go Deeper wing off any path →

02 · Choose

Choose your direction.

All three paths share the same Foundation. You pick a direction at the gate after F3, but every course remains open and you can switch at any time.

1. 01
   Builder

   Build, evaluate, and operate real AI systems — from “what is AI?” to a capstone you design and defend. The original path, unchanged.

   F1–F3 · E0–E5 · Capstonecode · taught from zero

   Choose BuilderFit guide →
2. 02
   Solution Architect

   Scope, architect, and deliver AI solutions for real organizations. You’ll build first (E0–E3) — you can’t scope what you can’t build.

   F1–F3 · L1 · E0–E3 · L2–L3 · S1–S5 · Capstonecode · taught from zero

   Choose Solution ArchitectFit guide →
3. 03
   Leader

   Decide, govern, and lead AI initiatives — no code required. Deciding and governing well is the scarcer skill.

   F1–F3 · L1–L4 · Capstoneno code

   Choose LeaderFit guide →

a path is a direction, not a lock · every course stays open · switch anytime

The Engineer capstone rubric

1. 1

   Worth building — the F3 write-up holds up to a skeptic

   Evidence one page: task-fit, dials, the assist/automate call

2. 2

   Sound construction — structured outputs, retry armor, right-sized models

   Evidence code review + the model map

3. 3

   Grounded honestly (if factual) — citations, threshold, refusal

   Evidence the Slack test, passed

4. 4

   Evaluated — 15+ golden cases incl. edges & attacks; green baseline

   Evidence npm run eval output

5. 5

   A caught regression — the suite has stopped at least one bad change

   Evidence the red run, kept as a trophy

6. 6

   Operable — traces answer “what happened, what did it cost?” in minutes

   Evidence the 2:14am drill, performed

7. 7

   Survivable — degraded mode + kill switch, demonstrated

   Evidence break it on camera

8. 8

   Honest write-up — what works, what doesn’t, what you’d do next

   Evidence one page, no marketing voice

Evidence, not attendance — every path ends in work you can inspect and defend.

03 · Prove

Every lesson is something you do.

1. 01Interact. Real models and deterministic systems run in the page, not in videos.
2. 02Check. Instant feedback shows whether the idea held before you move on.
3. 03Build. A portfolio-grade capstone is scored against a rubric you can see from day one.

Open the lesson behind the instrument →

04 · Before you start

Questions, answered plainly.

Do I need prior AI experience?−

No. Every path starts from absolute zero — the shared Foundation answers "what even is a model?" before anything else.

Which path should I pick?+

Builder if you want to make AI systems work; Solution Architect if you deliver AI for organizations (you build first — you can’t scope what you can’t build); Leader if you decide and govern, no code. A path is a direction, not a lock — every course stays open to everyone, and you can switch anytime.

Do I need to know how to code?+

Not to start. The Foundation (F1–F3) and the whole Leader path are code-free. The Builder and Solution Architect paths teach the code they need from zero — E0 is a built-in bridge course with a 60-second self-check you can use to skip it.

Do I need API keys, accounts, or a GPU?+

The demos run entirely in your browser — no setup, no keys, no GPU. From the Builder stage up, the hands-on labs are bring-your-own-key (about $5 of usage covers everything), and a free account syncs your progress across devices.

How long does it take?+

It’s self-paced — no cohorts, no deadlines. The full guided path is roughly a six-month part-time arc, but every course is independently completable, so you can go as fast or as slow as you like.

What do I build at the end?+

Each path ends in a capstone you design and defend against a published rubric you score yourself — a real, portfolio-grade artifact: a working AI system (Builder), a complete engagement brief (Solution Architect), or an initiative brief (Leader).

What are the "Go Deeper" wings?+

Optional branches off the main path. Model Internals opens up how models actually learn; the Advanced Engineer wing extends the Builder path into security, MCP, retrieval, orchestration and more; and the Data Foundation wing covers the data work an AI system assumes — how to scope it, sequence it, and hand it over. The course map above lists each one with its courses.

05 · Begin

Understanding beats mystique.

Every impressive AI behavior has ordinary machinery underneath. Learn the machinery and you can build with it, improve it, or lead teams that do — without being fooled by anyone’s demo.

Start the path — lesson one →