Skip to courses

Curio Chat Academy

You’re using AI tools. The system underneath is missing.

Engineering discipline for software engineers. Sovereignty systems for solopreneurs and practitioners. Both build the same thing — infrastructure that turns AI from a workaround into a repeatable system you’d stake your reputation on.

Choose Your Path

Or start free: the Sampler Pack lands Monday, August 17 — join the list →

Before you scroll

Two kinds of people land on this page.

“You want AI to just handle it.”

Sound familiar?

  • You’re hoping there’s a setup you do once — then the emails write themselves and the business runs while you sleep.
  • You’ve bought a prompt pack or two. They worked for a week.
  • Honestly, you’d rather not think about how it works.

That product is sold on ten thousand other pages — and we think it’s a toy. We don’t sell it, and we’d rather tell you now than after you’ve paid. If that’s where you are today, the honest next step is free: read along for a few weeks and see if the deeper argument grows on you.

Read the blog instead →

— or start with the guided version →

“You suspect the system underneath is the real work.”

Sound familiar?

  • You’ve used the tools — and watched the output quietly drift by week three.
  • You’ve noticed every fix you make gets forgotten, and you’re paying for the same lesson twice.
  • You’ve started to suspect that making AI dependable is a building job, not a shopping job.

You don’t want magic — you want an eye-level peer who adds the engineering to what you already know. That’s exactly what this academy is. Come in.

Choose your course →

Neither card quite you — but the problem sounds familiar? The free Sampler Pack lands Monday, August 17: join the list and see what changes when your business starts remembering →

building bank systems that weren’t allowed to be wrong
36  yrs
one discipline, three operating systems
3  courses
across the catalog
54  modules
one connected method
65  named frameworks

Three Courses. One Discipline.

Pick the course that matches who you are and what you’re trying to build.

Software Engineers

Agentic Coding Mastery

Your AI writes code fast — and quietly makes design decisions you never signed off on. Learn to run AI coding the way senior engineers run a team: context that persists between sessions, explicit checkpoints before anything merges, and decisions you can see and audit.

29 modules · 21 frameworks · Foundation & Mastery tiers

See the Pitch →

Step 1 — install the system

Solopreneurs

AI-Powered Solopreneur

Every morning your business starts from zero — yesterday’s corrections gone, last week’s refinements forgotten. Install AI inside your real workflows — email, content, client operations — so the business keeps what it learns. Built so the voice and judgment your clients pay for stay yours.

8 modules · ~15 hours · founding pricing $497

See the Pitch →

Step 2 — stay sharp while you run it

Practitioners

Stay Sharp

Your output is speeding up — and you can’t tell whether your judgment is keeping pace or quietly going soft. That’s what AI does to you, not for you. For professionals using AI every day: a way to check, not just a hope.

17 modules + capstone · 11 frameworks · ~6.5–8.5 hours

See the Pitch →

The big picture

One method. Three operating systems.

If you like to understand the map before you move, start here. Everything we teach comes from one connected method — this is the big picture of how the pieces fit together. The full depth is one click away, and it’s there when you want it.

“Businesses don’t become intelligent by using AI. They become intelligent by remembering.”

Read the CurioChat Manifesto →

Pierre Boutquin

Pierre Boutquin — 36 years building bank systems that weren’t allowed to be wrong. CurioChat is that standard, made teachable. Pierre also advises organizations on AI delivery governance.

Read my story →

From the Blog

Notes on engineering-grade AI — the discipline underneath the tools.

Aug 3, 2026

What Is the Agent Audit? Measuring If Your AI Compounds

You’re good at this. You’ve put in the reps, you know how to steer the model, your output is genuinely better than it was a year ago. And you still can’t answe…

Read post →

Aug 2, 2026

This Week in AI: The Doing Got Cheaper. The Deciding Didn't.

Two numbers landed this week that point in opposite directions. Ten million people are now using OpenAI’s agentic coding products, and the newest frontier mode…

Read post →

Aug 1, 2026

This Week in AI: Verifying Got Cheap, Finding Still Isn't

Every result worth reading this week came from the verification side of the loop, not the discovery side. A research agent that improves by checking its own in…

Read post →

The Saturday Reset

Stay in the Loop

Weekly notes on building the infrastructure underneath your AI work. No fluff, no hype.

No spam. Unsubscribe anytime.