Miatz Tuukul · structured thinking for the AI era

When the interface disappears, thinking is all that's left

Every interface shift removed friction — and a reason to think. Tuukul trains the judgment that remains: what you hand to AI, what you accept back, and what you sign your name to.

  1. Punch cards

    thinking was mandatory — every run cost a day

  2. Terminals

    syntax was the gatekeeper

  3. GUIs & IDEs

    the machine started meeting you halfway

  4. Autocomplete

    the machine started finishing your sentences

  5. Chat & agents

    you describe outcomes; software does the work

  6. What's next

    when the interface disappears, thinking is all that's left

The framework

Three gates, every consequential run

Working with AI is a chain of judgment calls. Tuukul installs a deliberate pause at each of the three moments that decide everything.

Delegate

before the AI runs

What exactly am I asking for — and what would tell me the answer is wrong?

Frame the outcome, state a prediction with a confidence, bound the blast radius.

Accept

when output returns

Did I verify this, or did it just sound right?

Check before adopting: run it, trace the claim, reconcile against your prediction.

Deploy

before the deed

If this ships and fails, who is affected — and did I sign it?

Premortem consequential actions, check reversibility, disclose honestly.

The flagship measurement

“You say 90%. You're right 62%.”

Before a consequential AI run, Tuukul asks for a one-line prediction and a confidence. Afterwards it reconciles what actually happened. Over weeks that becomes your personal calibration curve — computed from real work, not a quiz. Nobody else can show you this.

See your curve now — free, 5 minutes

The free Lab uses general knowledge. The real thing measures your calls on your own AI work.

The practice

Five minutes a day, embedded in real work

No abstract brain-training — research is clear that puzzle scores don't transfer. Every rep in Tuukul runs on the work you were already doing today.

Daily check-in

Morning: what's the most consequential thing you'll delegate to AI today — and how confident are you? Evening: what actually happened? Reconcile, reflect, done in three minutes.

The why-engine

A Socratic coach that answers your statement with a question — why this task, why that confidence, what would change your mind. Never more than two probes before it gives you value.

The Gym

Short drills on your real backlog: decomposition katas, premortems on your actual next launch, estimation ladders, inversion, war-room scenarios.

Decision journal

Auto-drafted from your sessions; you confirm in a minute. Over months it becomes the evidence portfolio behind your credential.

Itz'at Score, T-strand

Calibration, gate discipline and verification-before-accepting feed the thinking strand of your one Itz'at Score — every number carries a “how computed” note.

In your flow

The same coach rides along in Claude Code and your IDE — nudging at the gates of real runs, not in another tab you'll never open.

Coach, not cop

Privacy is the architecture, not a policy

Tuukul's ingestion schema has no field for your prompts — a privacy promise you can verify, not just trust. You own your memory: view it, edit it, export it, erase it.

  • · Features only — numbers and flags, never text you didn't write yourself
  • · Learner-owned memory with one-tap export and erase
  • · Organizations see aggregates of 5+ only, with every metric's method shown

Miatz Tuukul wants to coach you

This is the real consent screen — not a marketing mock.

What it reads

  • Signals about how you work: iteration counts, whether you verified before accepting, prediction vs outcome
  • Your predictions and short notes you choose to write (240-character cap, yours to delete)
  • Scores and streaks computed from those signals

What never leaves your machine

  • Your prompts or the AI's responses — the upload API has no field for them
  • Individual data to your employer — organizations see aggregates of 5+ people only
  • Anything after you hit pause — capture stops, queued events are discarded
Allow — coach meNot now
Early access

Tuukul is rolling out cohort-first

Join the waitlist and you'll get the launch note, the open Itz'at rubric, and first access as cohorts open.

What is Miatz Tuukul?

Tuukul (Yucatec Maya: thought) is the structured-thinking strand of Miatz's AI-Fluency program. It trains judgment practices — framing what you delegate, verifying what you accept, signing what you deploy — and measures calibration from your real AI work. It feeds one score (the Itz'at Score) and one credential (Itz'at AI-Fluency).

Does it read my prompts?

No. Raw prompt and response text never leaves your machine — the upload schema has no field for it. Only features (counts, flags, your own short predictions) sync, and you can pause or delete everything at any time.

What does my employer see?

Aggregates only — cohort-level averages over groups of five or more. Individual coaching stays between you and the coach unless you explicitly opt in to identified sharing.

Does the coach do the work for me?

Never. The coach asks at most two questions before giving value, and it never rewrites your prompt or hands you answers. Teach, don't do — that's the design law.

Start with the five-minute version

The Calibration Lab shows you your confidence-vs-accuracy gap right now — free, no account.