Steve Jobs Vision Prover MCP Connector for Claude
A+A product had settings menus with 47 options and 15 integrations. This tool forces it to kill features, absorb complexity, and own the whole experience.
The Problem
Ask an LLM to design a product. It will add a dashboard. A settings panel. Notification preferences. Third-party integrations. It starts with "Powered by AI" and works forward. That is not a product — that is a feature factory.
Every LLM commits five design failures:
- Feature Bloat — it adds without subtracting. Focus is what you KILL.
- Tech-First Framing — it pitches "our ML pipeline" instead of what the human FEELS.
- Configuration Cowardice — it pushes hard decisions to the user via settings menus.
- Fragmentation — it relies on Zapier, plugins, and third-party APIs for core value.
- Taste Absence — it hedges, compromises, and produces safe committee design.
How It Works
The Steve Jobs Vision Prover forces the LLM to fill in 6 reflection fields and commit to 5 Decision Pivots before concluding any product idea is viable.
The 5 Decision Pivots
| Pivot | Question |
|---|---|
| Radical Simplification | Did you KILL more than you kept? |
| Experience Backwards | Does the pitch start with the HUMAN, not the tech? |
| Complexity Absorbed | Does the SYSTEM decide, not the user? |
| Whole Widget Owned | Do you OWN the entire experience end-to-end? |
| Taste Exercised | Did you make a BOLD choice a committee would reject? |
The Verdict Matrix
Pivot 1 fails → FEATURE_BLOAT
Pivot 2 fails → TECH_FIRST
Pivot 3 fails → COWARDICE_DESIGN
Pivot 4 fails → FRAGMENTATION
Pivot 5 fails → TASTE_ABSENT
All pass → VISION_PROVEN
The LLM commits to a verdict. The server validates it against the pivots. If the reasoning is contradictory, the tool rejects and coaches the fix.
Why It Works
Tool calls are obligations — instructions are suggestions. The LLM cannot skip a field. It must name what it killed, describe the human moment without tech words, explain how the system decides for the user, map the ownership boundary, and commit to a bold choice. Every rejection message names the exact contradiction and tells the LLM what to fix.
The tool computes nothing. It generates nothing. It validates that the LLM is thinking like someone who shipped products to millions — not someone who accumulated features in a spreadsheet.
Related Connectors
Techstars Mentor Prover MCP
A founder pitched for 45 minutes without mentioning a single customer conversation, a single mentor challenge, or a single dollar of revenue. Zero feedback sought. Zero market validation. Zero network. That is not acceleration — that is solo building in a vacuum. This tool forces five Techstars-level axes: mentor leverage, feedback discipline, customer discovery, revenue readiness, and network strategy.
Leonardo da Vinci Prover MCP
An AI designed an enrollment process without watching a single participant session. Zero observations — 47 assumptions. It solved the problem inside one domain, never asking what psychology, architecture, or game design could teach about friction. It presented one final concept. No sketches. No variations. No constraints exploited. Da Vinci filled 7,000 notebook pages with cross-domain observations before building anything. This tool forces that method: observe, connect disciplines, prototype, exploit constraints, iterate.
First Principles Prover MCP
LLMs reason by analogy, copying industry norms. This engine is a 6-pivot cognitive trap that forces the agent to discard jargon and derive original solutions exclusively from physical, mathematical, or logical axioms.
Pricing Strategy Prover MCP
An AI recommended '$29/month per seat' because that is what three competitors charge. No value metric analysis — seat count has nothing to do with value delivered. No WTP research — the price was copied, not discovered. No segmentation — enterprise pays the same as a 3-person startup. No unit economics — CAC was $380 and LTV at $29/month with 14-month retention was $406. LTV/CAC of 1.07x. The company grew revenue 12% while burning 40% of cash on acquisition. This tool forces value metric definition, WTP research, segment pricing, unit economics, and packaging design.