NeU/X

An AI co-pilot that turns creator goals into actionable plans.

Self-directed capstone project. AI research, Figma prototype, React final build in Visual Studio with Claude Code.

Solo capstone, chief build officer

August 2026

  • Figma
  • AI-assisted code
  • CoLoop + Listen Labs
  • React
  • Visual Studio
NeU/X goal-setting screen asking the creator what their goal is
3
Completed research interviews
5.0
Avg. response quality score
8
Steps mapped, goal to advocacy

NeU/X started years ago as a side idea to automate repetitive UX work — it sat dormant until a UX-of-AI-products class rekindled it.

The core insight: a non-agentic way to derive milestones by working backward from a goal state, a straightforward calculation inside a small product space, not a judgment call.

The premise, half-joking but genuinely the point: build something that makes myself obsolete — specify a goal, and NeU/X calculates and manages the milestones to get there.

Research ran through Listen Labs, CoLoop, and Hey Marvin — 3 real classmates plus 17 invented profiles rounded out the data pool, not for sample size, but to learn the tools end to end.

That pointed toward a journey map for Priya and email campaign management as her sharpest need — a judgment call off synthesized research, not a directly cited finding.

That research became two artifacts: a full journey map for Priya, and a record-launch process map.

Early screens were roughed out in Uizard, then moved into Figma — about 10 screens, clickable, scoped narrowly to Priya's book launch and email campaign.

The AI co-pilot panel went through several passes, from a blank prompt to contextual insight tied to what the creator had just done.

That's where it stayed — a class capstone, parked for about a month once the class ended.

Picked back up a month later and rebuilt in React, expanding to about 10 milestones — email campaign management now one among several, not the whole product.

The journey map validated the mechanic against a book launch; the React rebuild demonstrates it against a record deal.

The milestones change; the underlying goal-to-plan logic doesn't — closer to the actual point than either example alone.

A React-based milestone dashboard walks creators from goal to release, surfacing an AI co-pilot that reads the actual state of their plan, not a generic assistant.

On the email side, a campaign flight check reviews subject lines, metadata, and send timing before anything goes out.

The email campaign shipped as one flat step, not the fuller teaser/launch-day/thank-you sequence originally mapped out — tabled for cost, not because it didn't matter.
There's no real LLM behind the co-pilot yet, either. This is a proof of concept built to show the shape of the product cheaply, not production wiring.
The real friction was mine: not understanding React deeply enough to have an informed opinion when the build needed one from me, not just a green light.

The real outcome was what this taught me about finding product-market fit — including learning to be honest with myself about where the evidence was thin.

NeU/X today is a working React prototype, demonstrating a goal-state-to-milestone mechanism that generalizes across creator goals, not one hardcoded to a single scenario.

That's the actual business value underneath a capstone project — a repeatable way to turn any stated goal into a concrete plan.

  • Capstone
  • AI Product
  • Figma โ†’ Code