# Gemini 3 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/gemini-3
> Markdown URL: https://aitinkerers.org/technologies/gemini-3.md
> Technology record last updated: 2026-02-22T15:42:09Z
> Generated: 2026-09-20T23:38:27Z

Gemini 3 Pro: Google's most intelligent, state-of-the-art multimodal AI model, engineered for advanced reasoning and complex agentic coding workflows.

This is the third-generation model, the new intelligence foundation for Google's ecosystem. Gemini 3 Pro delivers state-of-the-art reasoning and world-leading multimodal understanding: it seamlessly processes text, images, video, audio, and code. It is our most powerful agentic and vibe-coding model yet, designed to handle long-horizon, multi-step tasks; it features an industry-leading 1 million token context window. The model's performance is validated by its breakthrough score of 1501 Elo on the LMArena Leaderboard, confirming its superior capability for developers building on platforms like Vertex AI and the new Google Antigravity.

- Official technology site: https://ai.google.dev/gemini/models/gemini-3
- Public AI Tinkerers demos and talks: 8
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building NousyBooks - Orchestrating Low-Latency Multimodal Voice Agents with Gemini Live](https://atlanta.aitinkerers.org/talks/rsvp_La-nqq5lOEo)

I built NousyBooks, an AI-powered storytelling platform where children become the heroes of their own books. I built this project as part of Gemini Live Agent Hackathon Challenge. The core of the experience is "Nousy," a floating multimodal voice assistant that uses the Gemini Live API to brainstorm story themes, collect character details, and select art styles through natural, bidirectional conversation.

- Event context: AI Tinkerers Atlanta: Community Demos & Technical Deep Dives — 2026-04-21 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_La-nqq5lOEo

### [Lazy Marketing v3: From Meeting to Content Pipeline in Zero Click](https://seattle.aitinkerers.org/talks/rsvp_TtXOReDjy68)

Most of us have 10+ meetings a week full of insights worth sharing — but turning those into content never happens. Marketing Machine fixes that by wiring together Claude, Gemini, Slack, Google Sheets, and the LinkedIn API into a fully automated content pipeline. A Read.ai transcript hits a webhook. Claude extracts the best marketing hooks and expands them into on-brand LinkedIn posts using a 100+ line brand-voice prompt. You pick and refine posts entirely inside Slack with buttons and modals — no separate app needed. Gemini generates an accompanying image. Approved posts queue up in Google Sheets and auto-publish to LinkedIn on a schedule. In this demo, I'll walk through the full loop live — from raw meeting transcript to a published LinkedIn post — and dig into the prompt engineering, multi-model orchestration, and Slack-as-a-UI patterns that make it work. Built with Node.js, Express, and APIs anyone can sign up for. No GPUs, no fine-tuning, no ML infra required.

- Event context: AI Tinkerers Seattle: GTM Track — March — 2026-03-26 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_TtXOReDjy68

### [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

### [How We Build Pipelines to Detect Product Issues and Fix Them with Coding Agents](https://prague.aitinkerers.org/talks/rsvp_C35CGsy9rLA)

I'll walk through how we built a pipeline that detects product issues from multiple data sources (session recordings, error logs, support tickets, LLM traces) and routes them to coding agents that generate PRs. * Step 1: Signal. Render videos from session recordings, transcribe them, and analyze, searching for issues. * Step 2: Cluster. Group signals from different sources and decide what’s worth fixing. * Step 3: Code. Preview of Twig ADE (AI Development Environment), where confirmed tasks get handed off to coding agents.

- Event context: Product Engineering: Apify x PostHog — 2026-02-26 — Prague
- Public talk page: https://prague.aitinkerers.org/talks/rsvp_C35CGsy9rLA

### [Making PDFs editable, using typst, LLMs and crazy fast inference](https://seattle.aitinkerers.org/talks/rsvp_3c8BxGevKFo)

I'll be presenting a demo of a tool that takes in a PDF and outputs a typst conversion of that PDF, with similar style setting as the original PDF. Typst is a markdown based typesetting system that is similar to LateX but uses significantly less compute resources and enables local WASM based compilation. As the documents compile isntantly, it enables quicker feedback to LLMs to reproduce visual elements in the documents as is. After I have the typst code ready, I will use a custom cursor like interface to demo context aware precise edits on the document without changing any of the document structure.

- Event context: AI Tinkerers Seattle: January Meetup — 2026-01-31 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_3c8BxGevKFo

### [JobsYo: Building an AI-based but Human-driven Job Search, Research and Apply Ecosystem](https://toronto.aitinkerers.org/talks/rsvp_kotKIOHzcrE)

Live demo of JobsYo, an AI-powered job search platform I built to automate & organize job hunt - built based on my own experience. I'll show the technical internals: 1. Multi-Model AI Chatbot dedicated for Customized Application and Connection: How I built a unified abstraction layer that routes between GPT-5, Gemini 3, and Claude based on user preferences, with encrypted API key storage and streaming response handling across all providers. 2. Context Engineering: The unified prompt system that dynamically injects user profiles, parsed job requirements, base resumes, and linked networking connections into a single context window - enabling AI to generate highly tailored responses. 3. Agentic Job Discovery: Orchestration function that coordinates 4 different job APIs (Adzuna, JSearch, RemoteOK, custom scrapers), handles deduplication, and generates AI recommendations for failed sources. 4. Profile-to-Job Matching: AI-powered analysis that compares parsed user profiles against job requirements and provides actionable improvement suggestions. All running on React + Supabase Edge Functions with real-time streaming.

- Event context: AI Tinkerers Toronto - January 2026 Meetup at Google! — 2026-01-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_kotKIOHzcrE

### [vibe MLing - e2e finetunes on arbitrary domains with claude code via carefully synthesized data](https://cologne.aitinkerers.org/talks/rsvp_q79JPVgHEdM)

Inspired by huggingface's recent blog post on using Claude code to fine tune a model with an existing dataset (via their new CC skill), I wanted to see how much more of the e2e finetune process could be captured in SKILLs. Had a few days over Xmas break and 150 commits later I have 3 new SKILLs to share with the community to help (1) extract domain knowledge (2) iteratively generate and filter synthetic data and (3) run the finetune and eval it Have lots of challenges and learnings to share how I did it. I chose therapeutic coaching as my domain (but the SKILLs apply generally) and the resulting 14b finetuned model competes with human text based therapy

- Event context: AI Tinkerers Cologne #2: Let's Build. — 2026-01-21 — Cologne
- Public talk page: https://cologne.aitinkerers.org/talks/rsvp_q79JPVgHEdM

### [AI agents for Video Editing](https://london.aitinkerers.org/talks/rsvp_oFoTwKtiMq0)

Show a Lovable like flow where you create a video about "AI tinkerers in London gathering to hang out and share thoughts"

- Event context: AI Tinkerers London Meetup - 25th November 2025 — 2025-11-25 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_oFoTwKtiMq0

## Related Technologies

- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [GPT-5](https://aitinkerers.org/technologies/gpt-5) ([Markdown](https://aitinkerers.org/technologies/gpt-5.md)) — 30 public demos
- [Agentic](https://aitinkerers.org/technologies/agentic) ([Markdown](https://aitinkerers.org/technologies/agentic.md)) — 3 public demos
- [Antigravity](https://aitinkerers.org/technologies/antigravity) ([Markdown](https://aitinkerers.org/technologies/antigravity.md)) — 6 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Claude Opus](https://aitinkerers.org/technologies/claude-opus) ([Markdown](https://aitinkerers.org/technologies/claude-opus.md)) — 18 public demos
- [Claude Sonnet 4](https://aitinkerers.org/technologies/claude-sonnet-4) ([Markdown](https://aitinkerers.org/technologies/claude-sonnet-4.md)) — 18 public demos
- [clustering](https://aitinkerers.org/technologies/clustering) ([Markdown](https://aitinkerers.org/technologies/clustering.md)) — 3 public demos
- [ElevenLabs](https://aitinkerers.org/technologies/elevenlabs) ([Markdown](https://aitinkerers.org/technologies/elevenlabs.md)) — 42 public demos
- [Embeddings](https://aitinkerers.org/technologies/embeddings) ([Markdown](https://aitinkerers.org/technologies/embeddings.md)) — 22 public demos
- [Express](https://aitinkerers.org/technologies/express) ([Markdown](https://aitinkerers.org/technologies/express.md)) — 18 public demos
- [Figma](https://aitinkerers.org/technologies/figma) ([Markdown](https://aitinkerers.org/technologies/figma.md)) — 6 public demos
- [Flash](https://aitinkerers.org/technologies/flash) ([Markdown](https://aitinkerers.org/technologies/flash.md)) — 14 public demos
- [Flutter](https://aitinkerers.org/technologies/flutter) ([Markdown](https://aitinkerers.org/technologies/flutter.md)) — 24 public demos
- [Gemini-2](https://aitinkerers.org/technologies/gemini-2) ([Markdown](https://aitinkerers.org/technologies/gemini-2.md)) — 15 public demos
- [Gemini Live API](https://aitinkerers.org/technologies/gemini-live-api) ([Markdown](https://aitinkerers.org/technologies/gemini-live-api.md)) — 2 public demos
- [Google Sheets API](https://aitinkerers.org/technologies/google-sheets-api) ([Markdown](https://aitinkerers.org/technologies/google-sheets-api.md)) — 4 public demos
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos