# Wealth Experiment — AI workflow practice pack

Published 2026-10-16. Original educational prompts and exercises. Use approved, minimized source material. Outputs need human review.

## Measure whether an AI assistant actually saves you time

Use a simple task comparison to measure the time AI returns after setup, review, corrections, and tool costs.

### Include the hidden minutes

Help me design a fair comparison for this recurring task: [task and acceptance criteria]. Propose a simple log with task complexity, method, setup time, active work, review, corrections, elapsed time, and quality outcome. Identify likely sources of unfairness. Do not predict a time saving. Separate one-time setup from recurring effort and define what counts as an acceptable completed result.

### Calculate the result you can defend

Analyze this task log: [log]. Check whether the tasks and quality standards are comparable. Calculate observed active time for each method, including failed attempts and corrections. Show setup separately, describe uncertainty, and flag missing data. Distinguish time returned, tool spending, and actual cash effects. Recommend continue, revise, or stop based only on this evidence.

### Your exercise

1. Choose one recurring task and write three acceptance criteria.
2. Log a small set of comparable tasks using both methods, including every correction.
3. Calculate the observed saving and choose where the recovered time will go.

### Review checklist

- [ ] Both methods face the same quality standard.
- [ ] Setup, failed attempts, review, and corrections are counted.
- [ ] Active effort and elapsed time are separate.
- [ ] Time returned is not presented as guaranteed income.

Your evidence:

Your next decision:

Owner and review date:

## Build a personal AI chief of staff for one small business experiment

Give your assistant a focused brief, decision log, and weekly review so it helps move one business experiment forward.

### Use a daily brief to expose the next decision

Act as a planning assistant for this single business experiment: [current brief, dated evidence, task status]. I have [time] available today. Recommend at most three actions, with the decision or uncertainty each action addresses. Identify blockers, outdated information, and one task to defer. Separate facts from suggestions. Do not contact anyone, spend money, publish, or change connected systems.

### Run a weekly review that ends with a choice

Review this experiment using the dated brief, task history, and evidence: [materials]. Summarize what changed, what we actually learned, and what remains assumed. Identify the strongest evidence against our current direction. Recommend continue, change, pause, or stop, with reasons and confidence limits. Propose the smallest next action that could change the decision. Do not infer demand or revenue from activity alone.

### Your exercise

1. Create a one-page brief for one active experiment with explicit time and spending limits.
2. Run the daily brief manually and complete one recommended action.
3. Record a decision and use the weekly-review prompt before adding any scheduler.

### Review checklist

- [ ] The assistant serves one defined experiment.
- [ ] Facts, interpretations, and suggestions are distinguishable.
- [ ] Publishing, spending, and customer contact require your explicit decision.
- [ ] A recurring prompt is not described as active until scheduling is configured and verified.

Your evidence:

Your next decision:

Owner and review date:

## Keep learning

Free beginner course: https://aiteachers.cc/courses/first-useful-ai-workflow/

Free experienced-user course: https://aiteachers.cc/courses/repeatable-ai-workflows/