# User Interface Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/user-interface
> Markdown URL: https://aitinkerers.org/technologies/user-interface.md
> Technology record last updated: 2026-03-02T07:34:04Z
> Generated: 2026-09-23T03:47:26Z

The Human-Machine Interface (HMI): the critical space where a user exchanges information with a system, enabling control via input and output elements.

User Interface (UI) technology dictates how a human operates a machine: it is the full interaction layer. This layer includes both physical hardware (touchscreens, keyboards) and software components (Graphical User Interfaces or GUIs). Effective UI design is paramount: it directly impacts system usability and user efficiency. Consider the difference between a simple Command-Line Interface (CLI), like a Unix shell, and a complex, icon-driven mobile OS (iOS, Android). The goal remains consistent: translate complex machine functions into intuitive, accessible controls for the end-user, minimizing friction and maximizing throughput.

- Official technology site: https://en.wikipedia.org/wiki/User_interface
- Public AI Tinkerers demos and talks: 5
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Infinite canvas for your thoughts](https://nyc.aitinkerers.org/talks/rsvp_nmx_SC-lsOo)

Our company is building an AI-native canvas workspace that helps visual thinkers, especially product managers, plan, brainstorm, and produce structured outputs without switching tools. Problem: Product managers and similar roles often use multiple tools—on average five—to go from brainstorming to final deliverables. Canvas-based tools are good for ideation but don’t translate into real outputs, forcing constant context switching and duplicate work. Solution: We provide a familiar, infinite canvas where users can plan visually, interact through natural multi-turn conversations, and instantly turn their work into actionable outputs like PRDs, diagrams, or presentations. Users can also pull relevant data directly into the canvas, so they have more data points to plan efficiently and make informed decisions. Core Technology: Our system combines an infinite canvas interface with context-aware conversational AI, supported by the ability to bring in structured datasets on demand. Every component on the canvas shares context, allowing seamless collaboration and efficient planning. Customer Audience: We are initially focused on product managers and planning-heavy professionals such as city planners, architects, and consultants—users already familiar with canvas tools who want to reduce context switching and streamline their workflow.

- 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_nmx_SC-lsOo

### [Alignment Platform for LLM-as-a-Judge](https://london.aitinkerers.org/talks/rsvp_BKcNgmzepMA)

A simple UI that's currently in beta that helps developers align an LLM-as-a-Judge to their use case.

- Event context: AI Tinkerers London - January Meetup — 2025-01-22 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_BKcNgmzepMA

### [DeepX Hub](https://palo-alto.aitinkerers.org/talks/rsvp_Ek9BbtrQstI)

Applied AI and Computer Vision platform

- Event context: AI Tinkerers - Palo Alto - November 2024 Meetup — 2024-11-21 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_Ek9BbtrQstI

### [Living Museum](https://toronto.aitinkerers.org/talks/rsvp_EFLikAFW2Z4)

The Living Museum is a museum exhibit from the future, powered by AI. Visitors can search over a museum's collection semantically using natural language, with queries like "pottery from ancient rome", "aboriginal australian tools", "modern art in the style of andy warhol", etc. They can also have conversations with individual artifacts, which have complete knowledge about themselves and their origins. Visitors can ask them about the time period when they're from, what life was like back then, how they came to be, and how they ended up in the museum. I originally wanted to build an AI-powered search engine over the British Museum's collection, so I scraped 2.5 million artifacts from them. But then I experimented with the personification angle, and found it very compelling as a completely novel modality for educating the public about history and culture. Editor's note: It's about 95% done, just working out some glitches in the UI, esp. on mobile. If you're testing this, and run into issues with searching, just try rerunning or waiting -- there's a cold start bug with the db, it can take time to warm up right now, but I'm working on it!

- Event context: AI Tinkerers - Toronto - September 2024 Meetup — 2024-09-20 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_EFLikAFW2Z4

### [Generative UI: Using LLMs to Build Dynamic UI at Runtime](https://seattle.aitinkerers.org/talks/rsvp_KQgxuBn8zPQ)

Demonstrate how the UI can be built dynamically at runtime by the LLM based on the user's query/needs.

- Event context: AI Tinkerers Seattle - August Meetup — 2023-08-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_KQgxuBn8zPQ

## Related Technologies

- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Keras](https://aitinkerers.org/technologies/keras) ([Markdown](https://aitinkerers.org/technologies/keras.md)) — 74 public demos
- [ONNX](https://aitinkerers.org/technologies/onnx) ([Markdown](https://aitinkerers.org/technologies/onnx.md)) — 83 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [scikit-learn](https://aitinkerers.org/technologies/scikit-learn) ([Markdown](https://aitinkerers.org/technologies/scikit-learn.md)) — 84 public demos
- [TensorFlow](https://aitinkerers.org/technologies/tensorflow) ([Markdown](https://aitinkerers.org/technologies/tensorflow.md)) — 90 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [Chat Interfaces](https://aitinkerers.org/technologies/chat-interfaces) ([Markdown](https://aitinkerers.org/technologies/chat-interfaces.md)) — 1 public demo
- [Computer Vision](https://aitinkerers.org/technologies/computer-vision) ([Markdown](https://aitinkerers.org/technologies/computer-vision.md)) — 22 public demos
- [Database](https://aitinkerers.org/technologies/database) ([Markdown](https://aitinkerers.org/technologies/database.md)) — 8 public demos
- [DeepX Hub](https://aitinkerers.org/technologies/deepx-hub) ([Markdown](https://aitinkerers.org/technologies/deepx-hub.md)) — 1 public demo
- [Dynamic UI](https://aitinkerers.org/technologies/dynamic-ui) ([Markdown](https://aitinkerers.org/technologies/dynamic-ui.md)) — 1 public demo
- [Feedback Loop](https://aitinkerers.org/technologies/feedback-loop) ([Markdown](https://aitinkerers.org/technologies/feedback-loop.md)) — 1 public demo
- [Few-Shot Learning](https://aitinkerers.org/technologies/few-shot-learning) ([Markdown](https://aitinkerers.org/technologies/few-shot-learning.md)) — 1 public demo
- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 68 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos