AI Playbook Undeniable Speaking Trainings About Blog Subscribe Work With Me

The 92/8 Principle

Put AIon a clock.

A routine is an AI agent that does one job, on a schedule, then stops. AI does 92 percent of the work. You keep the 8 percent that actually needs you. Here is how to run it.

  • 92 / 8AI / You
  • 1Job Per Routine
  • 5Moments That Stay Yours

01What a routine is

One job, on a clock, then stops.

It wakes up at a set time, does the single thing it was hired to do, writes down what it found, and goes back to sleep until tomorrow. A clock and a job. That simple shape is the whole point. A routine that does one job on a clock is something you can trust, check, and reason about. An agent that does five jobs and never sleeps is something you spend your life debugging.

The 92% the AI does

Figures out how to do the job, builds itself, runs every day, checks its own work, and tells you how it went.

The 8% you do

The handful of decisions a machine should never make for you. What is worth automating. What good looks like. When it has earned the right to run on its own. Whether today's output is right. Small in time, large in leverage. You stop doing the work and start deciding about the work.

02The two homes

Where your routine lives.

A routine runs in one of two places. Picking the wrong one is the most common early mistake.

Local Scheduled Task

Where it runs
On your computer, while your AI app is open
Fires when the app is closed?
No. A missed slot runs the next time you open the app
Best for
Personal, context-rich routines where a late run is fine, like a morning brief or a weekly debrief

Cloud Agent

Where it runs
In the cloud, always on
Fires when the app is closed?
Yes. Runs on time no matter where you are
Best for
Anything that has to fire reliably, like revenue checks, client-facing work, and time-sensitive sends
The rule

"Does it matter if this silently doesn't run today?"

  • Noa local scheduled task is fine.
  • Yesput it in the cloud.

03The five moments

Your 8%, gate by gate.

A routine moves through six gates from idea to trusted. The AI carries almost all of it. You step in at five points, and only five.

GateWhat the AI does (the 92%)What you do (the 8%)
Pre-flightAnswers the scoping questions and names the blind spots before anything gets builtConfirm or correct the scope
DesignProposes a one-page build spec against the scoping rulesName the gap. Approve the one duty.
BuildWrites the entire routineNothing
DeploySchedules it on the clockGreen-light it to go live
On-ramp (7 days)Runs every day, logs its own performance, writes a graduation reportOne word on Day 7: Graduate, Run another week, or Fix it
GraduationFlips to active and takes ownership of the dutySpot-check the output, not the work

You touch the routine five times. Every touch is a decision only a human can make.

04The five non-negotiables

What makes a routine you can trust.

These separate a routine you can trust from one that bites you later. Hold every routine to all five.

1

One duty

Version one does exactly one job. New ideas park in a "v2 and beyond" list. An agent doing three jobs is three agents wearing one coat, and it fails three ways at once.

2

Bounded sources

Name every database, tool, and document it is allowed to read. A finite list. Unbounded reading is unbounded risk.

3

Memory loop

Every run reads the corrections and lessons from past runs, and writes back one observation. A routine that does not remember repeats the same mistake forever.

4

Fail loud, never silent

A blocked run writes a visible report that says what failed, where, and when, somewhere you will see it the next morning. The nightmare case is an agent that died on an expired login and nobody noticed for weeks.

5

You own the send button until graduation

Anything that reaches the outside world, like an email that sends or a post that publishes, stays in your hands in version one. The routine drafts it. You ship it.

05Where to start

Begin with a routine that only reports.

Start with a routine that surfaces things and never acts. A morning brief that reads your numbers and hands you a 90-second summary. A watchdog that checks whether yesterday's routines actually ran and flags the ones that went quiet. Neither one touches a send button. Neither one can do harm.

Read-only routines that report loudly build trust faster than anything else, because you feel the 92/8 split with zero risk on the line. You watch the AI do the daily work and you do nothing but read the result. Once that feels normal, graduating to a routine that drafts and then sends becomes an easy next step. From there these routines become the moving parts of a larger AI operating system for your business, and if you have not stood up your first agent yet, here is how to get your first agent set up. The same philosophy applied to your content and brand assets is The Library Method, where AI publishes the entries and you keep the taste.

  1. 1Read-only that reports
  2. 2Drafts that you send
  3. 3Sends on its own (after graduation)

Undeniable Studio

Build your first routine with a room full of people doing the same.

Undeniable Studio is where entrepreneurs go from AI curious to AI dangerous. Weekly live coaching, the playbooks, and the room that keeps you building. Bring the routine you want off your plate and walk out with it on a clock.

Weekly Live Coaching · Human-First AI