The AI Operating Sprint is five working days, fixed scope. An executive and their team build a working prototype of a real application with AI and keep the practice.
Working days, soak days, and a handoff that survives the room.
- Day 1The operationReview map
- Day 2The data and the rulesDecision and rules map
- Soak 1Reflect and experimentRead-only bridge
- Day 3Build togetherBounded working step
- Soak 2Harden the shared surfacemaintenance rhythm
- Day 4Shared and governedOwner and controls map
- Day 5Read-through and handoffRunbook · sign-off · next decision
Workshops
the sprint
The AI Operating Sprint: five days, fixed scope. Your team builds a working prototype of a real application with AI, and learns the practice along the way. Co-delivered with Justin Goethe.
how it runs
Scoping first, then five working days: half-day clinic, half-day office hours.
A pre-workshop scoping session (virtual, 1.5–3 hours, in the price) agrees the application, its functions, the data sets, and the technical prerequisites. Then five working days, half-day clinic + half-day office hours. The first two days on-site; the build days can go remote.
Two projects run all week: the shared company application your team builds together, and a personal passion project each person picks.
the outline
The five days, step by step.
Day 1 — What AI is, how it works, where it works
Step 1
Break the chatbot frame. The short history, and why the models are probabilistic. The persona demo. The four hosting tiers and the data risk in each. Your actual stack: seven layers, and where the DIY path ends.
Day 2 — Decompose the app as a group
Step 2
Think first, by hand. Decompose the application into an emerging spec, together, on screen. The AI-vs-deterministic fork. Most of the day is the thinking that has to happen before the model can do anything useful.
Day 3 — The build, first pass
Step 3
The spec meets the model. One-shot vs. the interviewing persona, two people, two very different results. The group stands up the stack in the working environment we host: a database, a server, a deploy. Then your team points their Claude at a live MCP server over a data lake we host, runs real queries against your operations data, and watches every call land on an audit log the IT lead reads in real time. The model never touches your ERP directly; it touches a gated, read-only, logged copy. That’s the safe data bridge.
Day 4 — The build, the IT team, the hardening
Step 4
The build continues. The IT team owns the controls and the policy calls. The four controls applied to the real surface. The cliffs, named (debugging, integration, hardening, multi-user, compliance, maintenance) with guidance at each.
Day 5 — The handoff
Step 5
The prototype as built. The read on what production takes. The five things your people can do, starting Monday. The governance for the artifact you now own.
what you leave with
The prototype, the practice, the named cliffs, and the bridge. Yours to keep.
- A working prototype or MVP of the application you scoped together, built by your people in the working environment we host. You own the code, the spec, and the repo.
- A team that understands what the model can do, where it works, and where the cliffs are.
- Hands-on time on the safe data bridge. Your people have pointed their Claude at a hosted, gated, read-only MCP server over a data lake, run real queries, and read the audit log. That is the control the IT team keeps asking for. (We host it for the sprint. Anything inside your own environment is a separate conversation after the week.)
- The named cliffs: where your people can operate on their own, and where the edges are.
- A shared, governed setup with boundaries and owners documented, and the working rhythm to run it.
We guarantee the experience of building it, not production-ready software.
price and next
$9,000–$12,000, set at scoping.
$9,000–$12,000, with the exact number set during scoping.
What happens next is your call: build it yourselves, hire someone, or hand it off. The retainer is the next conversation →
Reply to Braydon to talk through fit and scope.
Delivery referenceSee the draft facilitator and artifact kit →
Already know you need ongoing help?See retained work →