What usually breaks
- Specs come after code.
- AI changes are hard to trace.
- Technical debt arrives early.
- Handoffs become painful.
- Control shifts away from the team.
Human in the Middle
Human in the Middle MVP Lab
Build fast. Decide slowly.
A Human-in-the-Middle MVP Lab for designers, founders, and serious builders who want AI-assisted speed without losing architectural control. It is built around the HITM executional framework inside JBA, so responsibility stays human from start to finish.
The problem
Most AI-assisted builds fail because the process is weak
Teams generate quickly, then discover that no one can explain why the repo looks the way it does, what the AI changed, or how to hand the work to another developer. Founders lose visibility. Developers inherit cleanup. Trust drops fast.
Proof of framework
This already works on real projects
CO2Calc, an emissions workflow MVP for a real client, was built into a working first version in two days using this executional framework. The frozen snapshot shows the teachable architecture state. The live version shows the workflow continuing beyond that snapshot.
Frozen teaching version
Clean architecture state for teaching, review, and case-study reference.
Open frozen snapshotLive evolving version
Current working version as development continues and workflows evolve.
Open live versionYou are not being asked to believe in a theory before seeing an outcome.
How the framework works
HITM is an executional framework, not a prompt trick
You decide what is being built, what AI is allowed to touch, and what must be reviewed by a human. AI helps with execution. The structure stays human. This is different from Human-in-the-Loop, where the person mainly steps in after output appears.
In practice
- Define constraints.
- Write structured specifications.
- Generate in bounded steps.
- Review and approve before shipping.
Why this is not Human-in-the-Loop
- HITL checks output after generation.
- HITM defines boundaries before generation.
- HITM keeps approvals inside the build process.
- Responsibility stays human from start to finish.
What you build
A real MVP and a process you can reuse
Everyone works on the same example product. That keeps the complexity high enough to be useful, but controlled enough that the executional framework stays visible.
What you leave with
- A working MVP.
- A structured specification process.
- A cleaner, more reviewable repo.
- A handoff-ready README and limitations file.
- A workflow you can reuse on future projects.
Why the project is shared
- Shared vocabulary across the cohort.
- Shared debugging instead of private chaos.
- Controlled complexity.
- A realistic build instead of a toy exercise.
The example product is a Spec-to-MVP tool with authentication, API separation, export functionality, and proper documentation.
5-day intensive
Five consecutive days. Serious work. Small group.
Each day ends with a concrete artifact, not just a lecture or prompt session.
Day 1
Architecture and spec: constraints, markdown specification, folder structure, boundaries, and AI permissions.
Day 2
Controlled AI execution: stepwise generation, approval gates, commit discipline, and architecture checks.
Day 3
UI and asset layer: component structure, design-to-code alignment, and naming governance.
Day 4
Refinement and documentation: error handling, refactoring, README writing, and limitations documentation.
Day 5
Demo and packaging: architecture summary, roadmap, risk documentation, and funding-ready demo.
Who this is for
Serious builders who want speed without surrender
- Product designers transitioning into build roles.
- UX architects.
- Indie SaaS founders.
- Technical designers.
- Developers curious about disciplined AI workflows.
This is not for
Shortcut culture and automation-by-default
- Complete beginners.
- Prompt hobbyists.
- People looking for shortcuts.
- “Just generate everything” workflows.
If you want to automate responsibility away, this is not your lab.
Apply
Build fast. Decide slowly.
If you want controlled acceleration instead of chaos, this is the flagship applied format for teaching the HITM executional framework inside the JBA philosophy. Use it to understand the framework, build a real MVP, and keep the repo human-owned.