When should you use it?
- A company runs on many disconnected tools
- Leaders want AI but processes are messy
- You can interview the people doing the work
Not for: Single small automations; Firms happy with their current system
What do you need, and what do you get?
You need
- Staff interviews
- Current tools list
- Documents the work produces
You get
- Workflow maps
- List of steps to cut
- Wireframe and build plan
How does it work, step by step?
- Interview the doersMeet the people who do the work, not only leaders.
- Map workflowsWrite each workflow step by step with inputs and outputs.
- Cut stepsRemove steps that add no value before automating anything.
- WireframePlan screens and data flow before building.
- Add AI lastAutomate document reading and reminders once the base is clean.
The prompt
Our own prompt, inspired by Luke Pierce (@lukepierceops) and written to work in Custom agent. Values in lime are placeholders.
Fill in the blanks (optional; the copied prompt uses your values)
Help me map this workflow: {workflow}. Here are interview notes from the people who do it: {notes}. List each step with input, output, owner and time taken. Mark steps that add no value and could be cut. Then suggest which remaining steps could be automated, and what data each automation would need.
Inspired by Luke Pierce (@lukepierceops): This headline is a preview of the next 5 years of AI consulting.. The prompt above is written by playbooks.bot in our own words; nothing from the original is quoted.
What can go wrong?
- Replacing a working system can cost more than keeping it.
- Cutting processes is not cutting people; say so early.
- Scope creep is the common failure; freeze the wireframe.
Our take
The order of Luke Pierce's steps is the argument: AI arrives fifth. Teams that start by adding a model to a messy process usually get the same mess faster, with less visibility into why. Mapping the work with the people who actually do it is the step most often skipped, and it is where the list of things to delete comes from; every removed step is one you never have to automate, monitor or debug. Wireframing before building forces agreement on screens and data before money is spent. The client figures come from a consultant describing his own engagement, so read them as his claims rather than audited results. The method, though, is sound and cheap to trial. Pick one department, interview two or three people about a single recurring process, write it out step by step, and mark each step as keep, merge or cut. Only then ask where software, and finally AI, would remove real effort. Measure time per job before and after so the result is a number, not a feeling.
Where the time goes back: AI lands on a clean process instead of automating a messy one.
FAQ
Do I always replace existing software?
How long does it take?
Source and credit
Inspired by Luke Pierce (@lukepierceops). We describe the idea in our own words, link to the original, and wrote the prompt ourselves; nothing is quoted.
- Inspired by
- This headline is a preview of the next 5 years of AI consulting.
- Creator
- Luke Pierce (@lukepierceops)
- Published on
- X
- Original date
- Jul 11, 2026
- License
- Not openly licensed (the poster keeps all rights), so we quote nothing and link to the original
- Originally for
- Custom agent
- AI dry run
- Oct 23, 2026: passed. Dry-run tested by our AI test agent on sample input. PASS: Gates held on desk check; no live sends, bookings or purchases.
AI dry run on sample data; not run with live connected accounts. The playbooks.bot test agent filled the prompt with synthetic inputs, produced the output and checked it against the page's stated outputs and guardrails. - Verified
- Oct 23, 2026: source link resolves to the original, the credited creator published it, our excerpt or prompt matches it, and the license allows our use.
Are you the creator? Claim or correct this page.