E&C Forge

Designing a static GenUI MVP from zero: Intent → Result → Action · 2026

2026

Zero-to-MVP, tested with real users before scaling

5 roles

AI Product Designer · IxD · UI · Design System · QA-UX

MUI → Design System

Proprietary system, Light + Dark, fully responsive

Designer-led, AI-built

Design System + Figma MCP + Claude Code

My Rol

AI Product Designer
IxD · Interaction Design
Design System
QA-UX
Design System
QA-UX

E&C Forge is our own startup, so there was no client brief to translate. I owned the product vision, the UX, the design system and the quality bar. Implementation was done with Claude Code, and I supervised it directly as QA-UX instead of handing specs to a team and hoping for fidelity.

What Makes This Project Different

This wasn't a redesign. It was a new product in a new paradigm, built from zero, where nobody had a validated mental model to copy. The product is also part of the argument: E&C Forge offers GenUI and accessibility-oriented design to mid-market US companies, so the site itself had to be the demo.

The Problem

Most company websites make visitors do the work: guess which menu item holds the answer, click through sections, assemble the picture themselves. For a studio selling a new way of building interfaces, that is the wrong first impression.

The bet behind E&C Forge is to prioritize user intent. Instead of navigating a fixed tree, the visitor says what they want, and the interface responds with a simple, relevant result and a clear next action. This first MVP is a static GenUI: a conversational prompt, guided chips and generated response cards inside a controlled layout, rather than a fully open generative canvas.

The risk was just as clear. A new paradigm has no conventions, and I had seen how products in this space, such as Google's Disco from Google's AI lab, can ship powerful ideas with little UX scaffolding. I wanted the opposite: an experimental concept on a disciplined UX foundation.

Process — From Structure to Interaction

01.

Benchmarking: Learning From Products Without a UX Foundation

I started by analyzing GenUI and AI-native products, including Google Disco. The pattern worth avoiding: a strong concept with weak discoverability and unclear boundaries between generated and static content. That became my list of risks to design against from day one.

01.

Benchmarking: Learning From Products Without a UX Foundation

I started by analyzing GenUI and AI-native products, including Google Disco. The pattern worth avoiding: a strong concept with weak discoverability and unclear boundaries between generated and static content. That became my list of risks to design against from day one.

02.

Information Architecture: Structure Before Aesthetics

Even though the product is conversational, I began with a professional information architecture: content hierarchy, what lives in the static layer, what the agent generates, and how the two relate. A generative interface still needs a skeleton. Without it, the agent has nothing reliable to draw from.

02.

Information Architecture: Structure Before Aesthetics

Even though the product is conversational, I began with a professional information architecture: content hierarchy, what lives in the static layer, what the agent generates, and how the two relate. A generative interface still needs a skeleton. Without it, the agent has nothing reliable to draw from.

03.

Mid-Fidelity Wireframes: Validating the Intent → Result → Action Model

I wireframed at mid-fidelity so that layout, hierarchy and the chat/content relationship could be evaluated without the noise of final visuals.

03.

Mid-Fidelity Wireframes: Validating the Intent → Result → Action Model

I wireframed at mid-fidelity so that layout, hierarchy and the chat/content relationship could be evaluated without the noise of final visuals.

04.

Documentation Before Pixels: Giving the AI a Design Brain

Before starting UI, I wrote the knowledge base that would guide both me and the AI agent: Design System rules, Tone & Voice, interaction design principles, navigation, forms, errors, input controls, tooltips, dialogs and overlays, privacy and ethics, Gestalt, and a Nielsen heuristic checklist with a severity scale. These .md files and skills became the project's single source of truth, so every generated component answered to documented rules instead of the model's defaults.

04.

Documentation Before Pixels: Giving the AI a Design Brain

Before starting UI, I wrote the knowledge base that would guide both me and the AI agent: Design System rules, Tone & Voice, interaction design principles, navigation, forms, errors, input controls, tooltips, dialogs and overlays, privacy and ethics, Gestalt, and a Nielsen heuristic checklist with a severity scale. These .md files and skills became the project's single source of truth, so every generated component answered to documented rules instead of the model's defaults.

UI: Light and Dark Modes, Responsive by MUI Guidelines

05.

UI: modos Light y Dark, responsive según las directrices de MUI

I started from the MUI UI kit and adapted it into the E&C Forge Design System. Light and Dark were designed together, not as an afterthought, and responsive behavior follows MUI's breakpoint guidelines.

05.

UI: modos Light y Dark, responsive según las directrices de MUI

I started from the MUI UI kit and adapted it into the E&C Forge Design System. Light and Dark were designed together, not as an afterthought, and responsive behavior follows MUI's breakpoint guidelines.

06.

Core Screens

Services, About, Works and Case Study

06.

Core Screens

Services, About, Works and Case Study

07.

Full Prototype, Tested on a Real Phone

I built the complete prototype in Figma and worked on it in real time on my phone through the Figma mobile app, checking touch targets, reading comfort and layout behavior on the actual device before implementation.

07.

Full Prototype, Tested on a Real Phone

I built the complete prototype in Figma and worked on it in real time on my phone through the Figma mobile app, checking touch targets, reading comfort and layout behavior on the actual device before implementation.

Design-to-Code: Figma MCP + Claude Code

Design, documentation and code were connected end to end: Figma → Figma MCP → Claude Code. That changed my role. Instead of writing a spec and waiting, I worked as QA-UX directly on the implementation, correcting spacing, states, behavior and copy with the agent in the same loop.

Some interaction details I had specified for years but rarely seen implemented, because they are slow and expensive with human teams. Tognazzini-style latency handling, with distinct feedback depending on how long the wait is, is the clearest example. With the agent, it could be implemented and verified in the same session.

Accessibility Built In

Screen reader support, full keyboard navigation, and contrast tuned for different visual conditions, including color blindness and low vision. These were implemented and checked by me; validation with assistive-technology users is part of the next round.

Validation — Where the Product Got Real

I believed the product was solid. The tests proved otherwise, and that is exactly why they were worth running.

Methods

  • Guerrilla tests

  • Tests with friends and professionals

  • Professional usability test: 5 participants, moderated, think-aloud, 4 fixed phases, 10 tasks

  • Synthesis: 47 atomic notes → affinity diagram (NN/g method) → 9 categories, each rated for frequency, severity (0–4) and Nielsen heuristic

  • Cross-check: formal heuristic scoring on top of the qualitative synthesis. Two independent methods converged on the same findings.

What worked

All 5 participants described the experience positively ("different", "competitive", "I'd never seen anything like it") and valued the conversational freedom. Nobody rejected the paradigm. That is the thing to preserve, not fix.

Usability findings, 5 participants. Severity scale 0–4.
#FindingFrequencySeverity
1Minimal first impression read as “unfinished page”4/5Major
2Blank prompt: not knowing what or how to ask (incl. language expectation)3/5Major
3Unclear boundary between generated and static content3/5Major
4History and edit functions not recognized3/5Major
5Pricing: all 5 had to ask the prompt, no visible shortcut5/5Major
6No state signal right after sending a message2/5Major
7Contact CTA recognized inconsistentlyMixedMinor
8Agent translated “CEO” as “CTO” when describing the team1/5Catastrophic

The last one is the finding I'm proudest of catching. It occurred once, but it isn't a perception problem; it's a content-reliability problem in the generation pipeline. I rated it by impact on brand credibility, not by frequency, and separated it from the visual-signal issues so it wouldn't be diluted into a "learning curve" story.

The research question, answered honestly

Is GenUI the problem, or is it missing interaction signals around a concept that works?

Six of the nine categories were missing signals (visibility of system status, recognition over recall, help, consistency), exactly what the hypothesis predicted. Finding #8 was a different kind of risk and needs engineering, not copy.

Iterations Driven by Research

• P0 — Facts about the company come from a structured source of truth, not free generation (CEO/CTO error)

• P0 — "Pricing" chip returning one prioritized answer with an indicative range, not a list of options

• P1 — Example chips + a framing line before the first interaction, so the page reads as intentionally generative

• P1 — Persistent history and edit icons with text labels and aria-label, never icon-only

• P1 — Visible waiting state between send and response (skeleton or indicator)

• P1 — One visual treatment for cards in chat and in static sections, with one source of truth per content type

• P2 — Real example placeholder in the prompt and a visible note that Spanish works

• P2 — Single recognizable contact CTA across chip, card and header

• Preserve — the open prompt. Fixes are scaffolding around it, never a forced wizard.

Design System — From MUI to a Proprietary System

Started from MUI's UI kit and extended it into a documented system with tokens, components, states, tone & voice and interaction patterns for both modes.

  • Pattern 01 — Latency & waiting states

  • Pattern 02 — Empty states (what it is + why + how to start)

  • Pattern 03 — Error handling with recovery paths

  • Pattern 04 — Generated vs static content signaling

Why These Patterns Matter Beyond Design

They are the shared language between me and the AI agent. Documented rules replaced repeated corrections.

Current Status and Next Steps

MVP live at ecforge.com. Business outcomes aren't measurable yet

Feb 2024

Inicio del proyecto · en curso hacia lanzamiento.

4 roles

UX · UI · IxD supervisor · QA-UX

Prime Vue → DS

UIKit extendido hasta Design System propio

Libertad total

Decisiones de diseño y producto 100% propias

I treat every project I take on as if it were my own. This means tough decisions, rigorous design criteria, and improvements you'll see in your product, your conversions, and your team's workflow. If this sounds like what you're looking for, let's talk.

© All rights reserved 2026 – Erick Rodriguez

I treat every project I take on as if it were my own. This means tough decisions, rigorous design criteria, and improvements you'll see in your product, your conversions, and your team's workflow. If this sounds like what you're looking for, let's talk.

© All rights reserved 2026 – Erick Rodriguez

I treat every project I take on as if it were my own. This means tough decisions, rigorous design criteria, and improvements you'll see in your product, your conversions, and your team's workflow. If this sounds like what you're looking for, let's talk.

© All rights reserved 2026 – Erick Rodriguez