DESIGN × AI - Forging the Future of Interfaces

Prompting the future

This is where I build things. I design AI products, play with prompts, and vibe-code stuff until it works. Some of it ships. Some of it breaks. All of it teaches me something. Not a portfolio. A laboratory.

about me
terminal://gianluca

booting gianluca.os...

[✓] curiosity module loaded

[✓] ai toolkit mounted

[✓] design sense: online

[✓] caffeine: critical

ready.

Projects

Case studies

ai-content-evaluator-annotator.mdfeaturedin-progress·2025

AI Content Evaluator & Annotator

Three months rating AI responses, one rubric at a time. Some days it's catching a hallucination in two seconds flat, other days it's untangling something messy across text, images, even code, and still hitting the deadline. Hundreds of responses in, still adjusting to whatever comes next.

Data AnnotationRLHFPrompt EvaluationQAMultimodal Evaluation
ai-voice-speech-evaluator.mdin-progress·2025

AI Voice & Speech Evaluator

Two AI voices, same prompt, and I'm the one deciding which one actually nailed it. Pronunciation, how close it stuck to the original ask, whether the audio has weird glitches, how natural it sounds instead of robotic. Side by side, over and over, until the better one is obvious.

Voice AITTS EvaluationAudio QAA/B ComparisonNaturalness Review
a-rubric-for-rating-ai-honesty.mdconcept·2025

A Rubric for Rating AI Honesty

Most rubrics score correctness. This one tries to score honesty. Does the model hedge when it should, or sound confident about something it's guessing? Concept work, grown out of months of rating real responses.

AI EvaluationRubric DesignCalibrationRLHF
ai-trust-signals.mdconcept·2025

AI Trust Signals

A pattern library for how interfaces could actually show their confidence, not just a chat bubble that sounds sure of everything. Citations, uncertainty markers, and 'I might be wrong' states, explored as UI.

UX PatternsAI Product DesignTrust & SafetyResearch
vibeui.mdconcept·2025

VibeUI

A small design system built for AI products specifically: streaming text, thinking states, model pickers, the stuff every AI app ends up rebuilding from scratch. Concept components, ready to steal from.

Design SystemFigmaAI InterfacesComponents
model-comparison-console.mdconcept·2025

Model Comparison Console

A concept tool for the way I actually compare AI outputs: two responses side by side, scoring criteria built in, notes attached to the ones that need a second look. Grew out of doing this same thing in a spreadsheet for months.

AI EvaluationTool ConceptRLHFA/B Comparison
prompt-studio.mdconcept·2025

Prompt Studio

A workbench for saving, tagging, and re-testing the prompts that actually work, instead of losing them in fifty scattered chat tabs. Still just a concept, but it's the tool I keep wishing existed.

Prompt EngineeringTool ConceptProduct Design
onboarding-rebuilt.mdconcept·2025

Onboarding, Rebuilt

Most AI products dump you into a blank chat box and hope for the best. A redesign concept for the first five minutes: showing what the tool can actually do before asking you to guess.

UX TeardownOnboardingAI Product Design

Personal Project

Building FORGE

My own take on Jarvis. Still in progress, but it's the project I keep coming back to.

terminal://forge

Building FORGE

> what it is

An AI assistant built to actually know your context instead of starting from zero every time you open it. Claude Code runs the thinking, Obsidian holds the memory: notes, decisions, everything it needs to remember so you don't have to repeat yourself.

> status

in progress, long-term build. no demo yet, no public repo.

> built with

Claude CodeObsidian

~/forge