# Flutter Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/flutter
> Markdown URL: https://aitinkerers.org/technologies/flutter.md
> Technology record last updated: 2026-09-18T15:13:49Z
> Generated: 2026-09-21T10:43:49Z

Flutter is Google's UI toolkit: build, test, and deploy natively compiled applications for mobile, web, and desktop from one codebase.

Flutter is Google’s open-source UI software development kit (SDK), designed for crafting beautiful, high-performance applications across six platforms (iOS, Android, web, Windows, macOS, and Linux) from a single codebase. It uses the Dart programming language and leverages a reactive, widget-based architecture for its UI. The key productivity feature is Hot Reload, which allows developers to see code changes reflected in the running app in milliseconds, without losing application state. This efficiency, combined with its native compilation to ARM or Intel machine code, ensures fast performance and a consistent, pixel-perfect user experience on every screen.

- Official technology site: https://flutter.dev
- Public AI Tinkerers demos and talks: 24
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Teaching an LLM to be an interior designer](https://nyc.aitinkerers.org/talks/rsvp_G0dtIg_V-Dw)

A pipeline that turns a LiDAR room scan into art-placement decisions — which wall, what size, what art — by converting usdz geometry into per-wall design constraints that drive image generation, with a vision-LLM design critic whose judgments are verified, calibrated, and used to teach the deterministic scoring engine. Live, I'll walk the raw scan data (the LiDAR mesh and its JSON), the geometry visualizers that turn planes into design constraints, and the tooling we use to calibrate the critic and verify its judgments against the engine.

- Event context: August Demo Day ft Runpod, Veris, Openrouter, — 2026-08-19 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_G0dtIg_V-Dw

### [MenuMind: On-Device AI for Menu Translation and Allergen Awareness](https://dubai.aitinkerers.org/talks/rsvp_PkjdlO5VgRk)

MenuMind is a Flutter mobile app that helps travelers understand restaurant menus and identify possible allergen risks using on-device multimodal AI. In the demo, I will show how a user can scan a menu image, extract dishes and ingredients, translate unfamiliar items, flag common allergens such as nuts, dairy, gluten, seafood, and eggs, and explain the risk in simple language before ordering. The app is designed as an awareness assistant, not a medical guarantee: it highlights possible allergen risks and encourages users with severe allergies to confirm with restaurant staff.

- Event context: AI Tinkerers Dubai - May Demo Day — 2026-05-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_PkjdlO5VgRk

### [UI on the Fly](https://nyc.aitinkerers.org/talks/rsvp_95YAuinv7Hk)

A system that lets AI agents change app UI on the fly. The demo will show components being swapped live across existing app frameworks.

- Event context: Demo Day: Adaptive Software with Sky Valley and Veris — 2026-05-13 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_95YAuinv7Hk

### [Building for the Future Internet: Agent Services](https://upstate-ny.aitinkerers.org/talks/rsvp_GetoIsT3wio)

meetSpace - exploring an agent-first service for creating and finding local IRL events.

- Event context: AI Tinkerers Upstate NY: March Meetup — 2026-03-10 — Upstate NY
- Public talk page: https://upstate-ny.aitinkerers.org/talks/rsvp_GetoIsT3wio

### [Using AI to Build Production Grade Mobile Apps](https://san-diego.aitinkerers.org/talks/rsvp_K3TaJybd13w)

I will demo how I built Bizzie, a production-grade stock market app, by leveraging an AI-augmented pipeline from design to deploy. This isn't a "Hello World" demo; it’s a look at how to use AI to enforce Clean Architecture and enterprise standards (on par with a Fortune 100 company). The Stack & Flow: Design-to-UI: Using Figma Make + Figma MCP to bridge the gap between design tokens and production Flutter code. Agentic Engineering: Managing a fleet of specialized AI Agents (Antigravity) to scaffold CI/CD, write unit tests, and enforce strict architectural patterns. Accessibility: Leveraging Stark’s AI for adherence to WCAG 2.2 AA. What I’ll Show: I’ll run the app live and dive into my IDE (Antigravity) to show the "messy" reality of agentic development. You’ll see exactly where AI excels (boilerplate/scaffolding) and the specific hacks required to make it output Fortune 100-level code quality.

- Event context: AI Tinkerers San Diego: February Meetup at Google — 2026-02-27 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_K3TaJybd13w

### [QuAI: The Vibe-Coded AI Writing Assistant I Use Every Day](https://montreal.aitinkerers.org/talks/rsvp_c6ieg8zqrj4)

I'll be presenting how I used vibe-coding to solve a personal challenge and showcasing my solution: QuAI, a desktop app I use daily for writing on my Mac. I will also discuss the tech stack and tools I utilized. Since it was vibe-coded, I don't even know all the details; however, because people are now asking for access, I'm considering moving toward agentic engineering, where I will actually deep-dive into the code and structure.

- Event context: AI Tinkerers Montreal - February 2026 Meetup — 2026-02-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_c6ieg8zqrj4

### [Teaching an AI to Text: Turning Natural Language Into Chat Actions](https://chicago.aitinkerers.org/talks/rsvp_XrA7jcPfzYI)

This demo explores how AI can improve the texting experience by letting users send messages using natural language instead of UI steps. I’ll present SmartChat, a real-time chat experiment where users can type commands like “Send Aron I’ll be late” and have the system infer the recipient, message, and intent. The focus is on how the AI layer was designed: parsing ambiguous text, matching recipients from partial names, confirming intent, handling mistakes, and keeping the interaction fast enough for real-time chat. I’ll walk through how LLMs were integrated into a mobile messaging flow, how failures are handled, and what design patterns worked (and didn’t) when AI becomes part of the text input itself.

- Event context: AI Tinkerers Chicago: February Meetup ft. DubClub — 2026-02-17 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_XrA7jcPfzYI

### [Solibox](https://conakry.aitinkerers.org/talks/rsvp_qAI5FNo6z5g)

Transformez votre surplus solaire en revenus Avec SoliBox, l'électricité que vous n'utilisez pas alimente vos voisins et vous génère un revenu passif.

- Event context: AI Tinkerers – Conakry: Inaugural AI Conference @ Afrinov Tech Expo — 2026-02-11 — Conakry
- Public talk page: https://conakry.aitinkerers.org/talks/rsvp_qAI5FNo6z5g

### [SmarTrack](https://conakry.aitinkerers.org/talks/rsvp_pu0UjJawKQc)

SmarTrack Élevage - SmarTrack est une solution technologique innovante conçue pour répondre aux défis majeurs de l’élevage en Afrique, en particulier en Guinée. Le projet consiste en un collier intelligent connecté destiné aux animaux d’élevage (bovins, ovins, caprins, etc.), combinant géolocalisation GPS, suivi de la santé animale et géofencing.

- Event context: AI Tinkerers – Conakry: Inaugural AI Conference @ Afrinov Tech Expo — 2026-02-11 — Conakry
- Public talk page: https://conakry.aitinkerers.org/talks/rsvp_pu0UjJawKQc

### [Working Off the Same Page](https://upstate-ny.aitinkerers.org/talks/rsvp_t-0Ys0BmdmU)

Demonstrating contextWiki - an application that uses human-readable Wiki pages as the knowledge store for an agentic system. Natural language is used to track projects and capture ideas - automated by the Gemini 3.0 Flash powered agent to edit linked Wiki pages for reference by both the agent and the user.

- Event context: AI Tinkerers – Upstate NY Inaugural Meetup — 2026-02-10 — Upstate NY
- Public talk page: https://upstate-ny.aitinkerers.org/talks/rsvp_t-0Ys0BmdmU

### [Nihongo Convo: AI Powered Japanese Conversation Practice App](https://nashville.aitinkerers.org/talks/rsvp_D3dj1VvE31A)

In this demo, I’ll walk through the core user flow—from selecting a grammar goal or JLPT (Japanese Language Proficiency Test) level, to speaking naturally into the app, to receiving a real-time, spoken response in Japanese. The system adapts its vocabulary, grammar, and tone to match what the learner is actively studying, such as specific Genki chapters or grammar patterns. I’ll also show how Nihongo Convo provides post-conversation feedback, highlighting grammar usage, corrections, and alternative ways to express the same idea—helping learners bridge the gap between understanding grammar and actually using it in speech. Overall, this demo shows how Nihongo Convo functions as a focused conversation partner, designed to fit alongside textbooks and lessons, and help learners build real speaking confidence through deliberate, level-appropriate practice.

- Event context: AI Tinkerers Nashville – January 29th, 2026: Live Demos, Code, and Architecture — 2026-01-29 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_D3dj1VvE31A

### [Engineering a Consistent Image Gen Pipeline for Augmentative and Alternative Communication](https://valencia.aitinkerers.org/talks/rsvp_Y29X1ZoMALk)

I’ll demo how I built an AI-powered pictogram workflow that combines three components: 1. An offline prompt-to-image matching architecture that maps user intent to the most relevant pictograms (generated or existing), including how I represent prompts, store image/text embeddings locally, and select candidates with lightweight retrieval—so the experience stays fast and consistent. 2. Pictogram generation using an image generation model (prompt → pictogram), including the constraints and post-processing steps I use to maintain a consistent pictogram style and usable output format. 3. A lightweight “AI builder” workflow that assembles pictograms into simple compositions, focusing on the interaction model and the data structures that make the builder feel like a practical tool rather than a one-off generator. The demo will walk through each workflow step-by-step, paired with technical implementation notes and lessons learned around consistency, latency, and reliability.

- Event context: AI Tinkerers Valencia January Meetup — 2026-01-29 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_Y29X1ZoMALk

### [The Secret to Stunning UI: How AI Helped Me Design and Ship InkyCards in 7 Days](https://cologne.aitinkerers.org/talks/rsvp_EmnVHJCgoK0)

In just one week, I took InkyCard, a conversational language learning app from an idea in my head to a production-ready product. This session isn’t just about generating code; it’s about using AI to solve the "Developer Design Gap" and build a brand with a soul. I will demo the InkyCards workflow, focusing on: The Design Extraction Hack: How to feed UI inspiration (from sites like Dribbble) into LLMs to generate custom design systems, ensuring your app doesn’t look "AI-generated." Building the "Soul": Using Gemini Nano and Higgsfield to create a unique app mascot and custom iconography, overcoming creative blocks and building an emotional connection with users. Production Speed-running: A look at the "Plan-First" prompting strategy and context management that allowed me to build complex features—like real-time AI conversations (Firebase Vertex AI) and "Tap-to-Learn" flashcard generation—without losing code quality. Technical Deep-Dive: State Management & AI: How to use Claude and AntiGravity to scaffold architecture that stays clean as the project grows. The Fresh Convo Rule: My framework for managing LLM context to prevent "code rot" and quality degradation.

- Event context: AI Tinkerers Cologne #2: Let's Build. — 2026-01-21 — Cologne
- Public talk page: https://cologne.aitinkerers.org/talks/rsvp_EmnVHJCgoK0

### [Your Gaming PC, Humanity’s Cloud: A New Vision for AI Infrastructure](https://nyc.aitinkerers.org/talks/rsvp_vFB96_Hru3U)

I’ll be presenting a desktop platform that turns any gaming PC into an OpenAI-compatible GPU server. The goal is to make compute accessible, collaborative, and decentralized — allowing anyone to share their unused GPU power with friends, communities, or the public. The demo will walk through how the platform transforms a local GPU into an API-compatible endpoint, showing how it integrates with the OpenAI API format for seamless use with existing AI clients. I’ll cover the technical architecture, including GPU resource management, real-time job routing, and the underlying stack used for model execution. I’ll also demonstrate running an AI model locally, sharing it within a small peer group, and scaling it into a shared public pool — all with minimal setup. The presentation will emphasize how this approach can democratize AI compute and enable a community-powered alternative to centralized cloud infrastructure.

- Event context: The Future of AI Infrastructure (Ft. Oracle & NVIDIA) — 2025-12-09 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_vFB96_Hru3U

### [The 4-Month Sprint That Turned Me Into an AI Developer](https://nairobi.aitinkerers.org/talks/rsvp_WD4ja5qTLgo)

The last few months I have scaled down my team and turned instead to upskilling myself, I learnt from complete scratch how build fully functioning apps and how I have upskilled myself to where I am now not just a marketer but also a developer that can build end to end apps. I will talk about the 3x apps that I have built that are contiuations of what I previously spent $60k+ on with developers, I failed 2 projects. 1) PadelBuddy and 2) Dabu - I failed those super badly and lost a lot of money but now have kickstarted those projects all again by just simply coding them myself and having much larger success with that, I will also talk about the third app I built out of pure passion.

- Event context: AI Tinkerers Nairobi – Sep 25, 2025 Meetup — 2025-09-25 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_WD4ja5qTLgo

### [Adding In house AI into your company workflows using open source llms](https://nairobi.aitinkerers.org/talks/rsvp_mWMUcp9UD4s)

Train AI to ingest in house data for the company and use it to make every day operations easier, giving insight and tracking bottle necks. I will demonstrate by the use of law data, how lawyers will be more efficient when using AI driven workflows to reach decisions quickly based on cases and summarisations needed on the go

- Event context: AI Tinkerers Nairobi – Sep 25, 2025 Meetup — 2025-09-25 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_mWMUcp9UD4s

### [Aplicación móvil con AI](https://san-salvador.aitinkerers.org/talks/rsvp_RkxoZ5zhP08)

Aplicación móvil en fluter que consue api de OpenAI, entrenada para hablar como salvadoreño de calle.

- Event context: AI Tinkerers San Vicente Sur - Agosto 2025 — 2025-08-30 — San Salvador
- Public talk page: https://san-salvador.aitinkerers.org/talks/rsvp_RkxoZ5zhP08

### [GPU Sharing for AI Computations](https://nyc.aitinkerers.org/talks/rsvp_lTMJXnmec7s)

I’ll be demoing an app that lets you use the GPU of another computer to run AI computations. It works with Cursor so you can easily connect from your own machine and offload heavy AI work to a more powerful GPU elsewhere.

- Event context: AI Tinkerers August Demo Day ft. Auth0 and Comet. Demo what you've built! — 2025-08-26 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_lTMJXnmec7s

### [How to vibe code a native and scalable cross platform app (as a software dev)](https://nurnberg.aitinkerers.org/talks/rsvp_stuPZEMjkbY)

I would present my journey how I (successfully?) vibe coded a native app with flutter and supabase - although I've not touched on both technologies ever before in my 12 years of web software development. I can show (messy) AI generated code, share which tools and models I used for vibe coding and tell what went well and wrong.

- Event context: AI Tinkerers Nürnberg First Meetup - July 3rd — 2025-07-03 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_stuPZEMjkbY

### [Struggles in Unity to Vibing in Flutter: lessons learned in building a mobile game startup with GenAI.](https://nyc.aitinkerers.org/talks/rsvp_ItyHLRG_lVo)

I'm still thinking about this, (flying in from Vancouver, BC and just discovered this through NYC Tech Week) but I think the most interesting thing I could talk about would be how I ended up transforming our 5-month prototype built with a 3-person team in Unity into a solo-founder vibe coding app to ship the MVP on my own. What I would present: - Quick side by side comparison of our mobile game that let's gamers take pictures of food and play with them in-game. - quick timeline of how our "OpenAI CV" has progressed from google sheets -> Unity -> Flutter) - Lightning round of "fast wins" from a game development perspective (eg. auth -> 3 months to 3h, OpenAI API changes and progress) - Prompting and managing features via .md specs, to do lists, and recent learnings through Sonnet 3.7, Gemini, and ChatGPT 4.1 and o4-mini - Where things have went bad: auto-complete rampages and context windows. - Creativity and Narrative. Writing character sheets with a virtual writing room, scripts and changes in quality over time.

- Event context: Demos and Dim Sum with Deel and Apollo — 2025-06-03 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_ItyHLRG_lVo

### [Vinchy: AI-Powered Fit Matching and Virtual Try-On for the Real-World Body (Prefer to do Science Fair)](https://seattle.aitinkerers.org/talks/rsvp_6N2EwXqJpNw)

Vinchy is a personalized fashion platform that uses AI to help users find clothes that actually fit their unique bodies. At our booth, we’ll demonstrate our proprietary fit engine, which compares a user’s body measurements to a large database of hand-measured garments and returns only those that fit well—down to the centimeter. Visitors can try our real-time virtual try-on feature, which superimposes well-fitted clothing onto their own photo. We'll also showcase how users can discover others with similar bodies, fostering a new kind of social commerce built around real fit, not aspirational sizing. Our setup will include live demos of the tailored search engine, AI stylist feedback, and outfit-of-the-day feed filtered by measurement similarity.

- Event context: AI Tinkerers Seattle - April Meetup — 2025-04-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_6N2EwXqJpNw

### [AI MAXIMALIST](https://nairobi.aitinkerers.org/talks/rsvp_6xOTEkqX7oU)

Elyxa is an AI assistant that enables you to focus on the more important details of you day and leave the obnoxious details to systems optimized to streamline just that. A dedicated personal assistant for yourself.

- Event context: AI Tinkerers - Nairobi Inaugural Meetup (April) — 2025-04-09 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_6xOTEkqX7oU

### [Dynamic Structured Record Augmentation of LLMs](https://nyc.aitinkerers.org/talks/rsvp_o5c_H5O-V5U)

An approach that enables LLMs to dynamically create, manipulate, and retrieve structured records in a NoSQL database. This approach serves as an alternative to vector-based RAG, creating a data store that's both human and model-readable. Demoed in a mobile app for tracking daily records (e.g., cat medication, exercise, expenses) to illustrate practical applications. The core mechanism I’m focusing on is prompting for structured Tool/Function completions to do CRUD operations on structured records - to capture, remember, retrieve, and query against information the user wants to reference later. The schema / structure of the records themselves is also frictionlessly created / edited by the model. Both the table structures and the records themselves are stored in a NoSQL database. The “magic” is in actively managing the system prompt on the chat chain to provide full context and dynamically generate the functions available as tools for each completion. This “dynamic but structured” approach uses JSON Schema to define, communicate, and validate functions. A technical challenge was dynamically generating and validating table / context-specific functions. I did this by embracing JSON Schema in the table definition as well as the functions presented to the LLM. I’ll focus my demo on the prompt, the Firestore database, and the function building. This is a Flutter app that runs on iOS and Android. I’m very excited to share this approach with the other Tinkerers - shown as a fully working implementation that can be tried out, as well as access to all the code.

- Event context: AI Tinkerers July Meetup — 2024-07-24 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_o5c_H5O-V5U

### [Fluffy - An answer-engine for public repos & open-source libraries.](https://nyc.aitinkerers.org/talks/rsvp_eQaYs2ojaAE)

Most code in production right now is business logic weaved into functionalities of open source libraries, from flutter plugins for app development to Drizzle for ORM and LangChain for GenAI pipelines. However, I encountered they encounter three main challenges: A. Sometimes repo are poorly documented or maintained... or really new (I had to watch a tutorial in Spanish on Vercel's AI/SDK, lol) B. Or at times, they'd stumble upon bugs so specific to their use case that they ended up spending a lot of time trying to figure out a fix C. Or at times, they want to quickly check out a new research driven repo that's come out Fluffy helps them navigate those challenges easily.

- Event context: AI Tinkerers June Meetup at Betaworks! — 2024-06-27 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_eQaYs2ojaAE

## Related Technologies

- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Dart](https://aitinkerers.org/technologies/dart) ([Markdown](https://aitinkerers.org/technologies/dart.md)) — 3 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Firebase](https://aitinkerers.org/technologies/firebase) ([Markdown](https://aitinkerers.org/technologies/firebase.md)) — 23 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [Gemini API](https://aitinkerers.org/technologies/gemini-api) ([Markdown](https://aitinkerers.org/technologies/gemini-api.md)) — 20 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 105 public demos
- [Android](https://aitinkerers.org/technologies/android) ([Markdown](https://aitinkerers.org/technologies/android.md)) — 11 public demos
- [Anthropic](https://aitinkerers.org/technologies/anthropic) ([Markdown](https://aitinkerers.org/technologies/anthropic.md)) — 36 public demos
- [Antigravity](https://aitinkerers.org/technologies/antigravity) ([Markdown](https://aitinkerers.org/technologies/antigravity.md)) — 6 public demos
- [ARKit](https://aitinkerers.org/technologies/arkit) ([Markdown](https://aitinkerers.org/technologies/arkit.md)) — 3 public demos