DO IT YOURSELF · SELF-PACED PROGRAMS

Ship production AI with Claude Code. At your own pace.

For engineers and founder-engineers who ship. Video, working repos, and the 85-skill library. Lifetime access.

Two ways to learn

Pick your program

Build with Claude Code

2-day intensive · ~12 hrs recorded + repo + skills library

Ship a working Claude-Code agent end-to-end
File-edit, MCP tools, hooks, slash commands
Lifetime access + the skills library

$297 $997 founder price

Become an AI Engineer

6-week self-paced · ~30 hrs across 6 modules + repos

RAG, agents, evals, observability, prod-deploy, multi-agent
Ship a full RAG + agent + eval-CI stack
Lifetime access + updates + skills library

$497 $2997 founder price

What's included

Every program comes with

Lifetime access to videos + repos + updates
The 85-skill library
Invite-based Discord community

Laws we live by · LLMs in production

10 laws for shipping AI to production without burning cash

Both programs teach these as the spine. By week 6 you've shipped a stack that obeys all ten.

01
Spec hard, code soft.
A page of working spec is worth a week of throwaway code. LLMs accelerate the wrong thing if the spec is wrong.
02
Evals before the model call.
Write the failing eval first. Without a passing bar you don't have a product, you have a forever-prototype.
03
Tools beat prompts.
A 20-line tool with a strict schema beats a 2,000-token system prompt. The model recovers from a wrong tool call; it doesn't recover from a vague instruction.
04
Cache aggressively, route ruthlessly.
Prompt cache, embedding cache, response cache. Cheap model routes; expensive model produces. 80% of the bill is the wrong model on the wrong call.
05
Monolith for LLMs, microservices for humans.
LLMs read a monolith faster than a 12-service mesh. Split early and you lose the one thing they're best at: holding the whole system at once.
06
Curate the context, don't polish the prompt.
The model is only as good as what's in the window. Cut every token that isn't a fact, an example, or a constraint.
07
Receipts, not claims.
Every “it works” is a test run, an eval row, or a git log line. Vibes don't ship.
08
Subagent review = 2 stages.
Finder + adversarial verifier. One agent gets confidently wrong; two disagreeing agents force the truth.
09
Manager mode: 5 → 1.
One operator orchestrating 5 parallel agents ships what used to need a team. Lanes, async, documented handoffs.
10
Player-coach.
Ship code and review agents in the same day. The skill is reading whether today needs hands-on-keyboard or orchestration.

FAQ

Questions

Is this cohort-based?

No. It's self-paced with lifetime access. Start and finish whenever.

What if I don't finish?

Lifetime access. Come back any time.

What's the refund policy?

14-day money-back from purchase, regardless of course progress.

Do I need to know Claude Code already?

No. The 2-day intensive teaches it from zero.

Is the 6-week program strictly sequential?

No. Jump between the six modules in any order.

Does it cover Bedrock + OpenSearch?

Yes. Both are covered in the prod-deploy module.