# Gemini API Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/gemini-api
> Markdown URL: https://aitinkerers.org/technologies/gemini-api.md
> Technology record last updated: 2026-09-18T15:14:01Z
> Generated: 2026-09-23T04:51:15Z

Integrate Google's multimodal Gemini models (Pro, Flash) into your application via REST or SDKs: generate content, process up to 1000-page PDFs, and execute code with a 2-million token context.

The Gemini API delivers Google's most advanced models (Gemini 3 Pro, 2.5 Flash) directly into your applications. Leverage its multimodal power: process text, images, video, and audio inputs for tasks like content generation, summarization, and visual understanding. Utilize key features including the 2-million token context window, structured JSON output, and function calling to build complex, reliable agents. Choose your integration: use the standard REST API, streaming endpoints (SSE), or the Live API (WebSockets) for real-time conversational experiences. Get started with the free tier and robust SDKs for Python, Java, Go, and more.

- Official technology site: https://ai.google.dev/
- Public AI Tinkerers demos and talks: 20
- Result page: 1 of 1

## Recent Public Talks and Demos

### [EduSense: A Multi-Agent AI Platform for Emotion-Aware Education](https://dubai.aitinkerers.org/talks/rsvp_KyNKCO_MVFc)

EduSense is a multi-agent AI education platform built for the Kaggle AI Agents Capstone. It uses DeepFace for real-time facial emotion analysis via webcam, and 7 specialized agents — orchestrated by a central workflow — to generate lessons, quizzes, flashcards, and PDF reports for instructors. The backend runs on FastAPI with PostgreSQL. I'll demo the live agent pipeline: emotion capture, the sequential agent workflow, and the instructor dashboard.

- Event context: AI Tinkerers Dubai — August Demo Day — 2026-08-08 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_KyNKCO_MVFc

### [What happens when you give a guy with little coding experience an AI Server? Just Another AI DAW (JAAD)](https://columbus.aitinkerers.org/talks/rsvp_4YU8BPj7FwE)

Just Another AI DAW (JAAD) is an open-source, browser-based, multitrack Digital Audio Workstation that integrates Google Gemini to deliver real-time AI mixing advice, generative MIDI/stem creation, and mastering tools directly in a local-first interface. In the live demo, I will showcase a working multitrack workspace with responsive AudioWorklet playback, demonstrate Gemini-powered tempo detection and natural-language MIDI sequence generation, and show how we handle local storage caching using the Origin Private File System (OPFS) alongside a WebGL-based visual analyzer.

- Event context: AI Tinkerers - Columbus July Meetup — 2026-07-06 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_4YU8BPj7FwE

### [Contextual Synthesis: Engineering a Multi-Agent Context Extraction Pipeline for Stakeholder Audio](https://doha.aitinkerers.org/talks/rsvp_X1LkLLGS_0I)

I built a multi-agent workflow engine that ingests long-form, unstructured stakeholder meeting transcripts and dynamically transforms them into targeted, context-aware corporate assets—including domain-specific LinkedIn posts, official press releases, and structured follow-up emails with clear action items.

- Event context: AI Tinkerers Doha: Round 2 — 2026-06-15 — Doha
- Public talk page: https://doha.aitinkerers.org/talks/rsvp_X1LkLLGS_0I

### [Turning a Hackathon Prototype into a Scalable Solution](https://saopaulo.aitinkerers.org/talks/rsvp_A_SzBK-d0uU)

JustaLuz is a mobile app that uses on-device capture plus Gemini vision to parse Brazilian utility bills, flag inconsistencies with deterministic rules and search-grounded tariff checks, and walk users through formal billing disputes. This addresses a recurring issue in Brazil: errors and confusing charges on electricity bills. The demo showed the end-to-end workflow in the app and illustrated how the team worked on evolving a hackathon prototype into a clear and scalable architecture.

- Event context: AI Tinkerers SP - Meetup de Maio - Kiro & AWS — 2026-05-28 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_A_SzBK-d0uU

### [Lixpi is a visual, node-based workflow engine for building AI image and video generation pipelines](https://toronto.aitinkerers.org/talks/rsvp_SxMp4PNqTxU)

Lixpi is a visual, node-based workflow engine for AI image and video pipelines an infinite canvas where spatial arrangement is the workflow. Instead of writing a workflow DSL or fighting a linear chat prompt, you drop documents, images, and AI chat threads onto the canvas and draw edges between them. The edge graph directly drives context extraction, dependency chains, and execution order for the underlying models. In the demo I'll show live character-consistent image generation via "artifact piping" (one generated image fanned out as edge-context into multiple downstream threads), mid-conversation model switching between OpenAI / Anthropic / Google, and progressive image streaming rendered into the node in real time.

- Event context: AI Tinkerers Toronto - April 2026 - hosted by Shopify — 2026-04-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_SxMp4PNqTxU

### [UofT - Embedding the Canadian Job Market: Building a Job Discovery Engine](https://toronto.aitinkerers.org/talks/rsvp_GtxmkHX09Ow)

This demo presents how we built a multi-interface job discovery platform organized around a shared AI and analytics pipeline. The system supports three roles: a student interface for discovering opportunities, an employer interface for creating structured job postings, and an admin interface for monitoring platform analytics and data quality. The technical focus is a content-based recommendation system built using sentence-transformer embeddings and tag-based metadata. Jobs are embedded during AI assisted ingestion, and user preference vectors are constructed dynamically from saved and recently viewed jobs. Recommendations are generated by computing cosine similarity between the user embedding and active job embeddings. We will walk through the architecture of the pipeline and discuss how structured job templates, behavioral signals, and analytics instrumentation helped improve the quality of recommendations and observability of the system.

- Event context: AI Tinkerers Toronto - March - hosted by Mozilla! — 2026-03-25 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_GtxmkHX09Ow

### [Ai in Human Resource](https://bremen.aitinkerers.org/talks/rsvp_M5plVNmMjOw)

An HRMS software where I am using an LLM for context-based answers.

- Event context: AI Tinkerers Bremen — 2026-03-25 — Bremen
- Public talk page: https://bremen.aitinkerers.org/talks/rsvp_M5plVNmMjOw

### [Building a Production-Ready ESG KPI Extraction Pipeline with Gemini API](https://vienna.aitinkerers.org/talks/rsvp_LPKQctsj3Mw)

A practical deep-dive into building an AI-powered system that extracts 170+ structured KPIs from ESG/financial PDF documents. I'll walk through the real engineering decisions behind our two-stage extraction pipeline: how we use Gemini's Files API with explicit caching to control costs, parallel structured outputs processing to speed up extraction, LLM-based conflict resolution for multi-document scenarios and how we evaluate the pipeline. Expect code snippets, architecture diagrams, and honest lessons learned from development.

- Event context: AI Tinkerers Vienna: 2026 — 2026-02-19 — Vienna
- Public talk page: https://vienna.aitinkerers.org/talks/rsvp_LPKQctsj3Mw

### [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

### [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

### [Building FacultyFinder.io: An AI-Powered Academic Discovery Platform with Smart CV Matching](https://toronto.aitinkerers.org/talks/rsvp_AA3BkfpGWxY)

FacultyFinder.io is a comprehensive platform that helps researchers discover and connect with faculty members across Canadian universities using AI-powered matching and intelligent web scraping. I'll demo the complete technical pipeline: 1. Comprehensive Data Source: Combining different sources of data (names from the university website, publications from PubMed, and OpenAlex) 2. AI-Powered Profile Analysis: Multi-LLM CV analyzer (Claude, GPT, Gemini, Grok) that extracts research interests, keywords, and skills from uploaded CVs/resumes 3. Smart Matching Engine: Database-driven faculty recommendation system using PostgreSQL with semantic matching 4. Publication Integration: OpenAlex API integration with ORCID-based disambiguation, processing 42,595+ publications with 88.6% file size optimization 5. Real-time RESTful API: FastAPI backend serving 10+ endpoints with advanced filtering and search The demo will show: uploading a CV, the AI extracting research keywords, querying our database of 500+ faculty members, and generating personalized recommendations with match scoring. I'll walk through the code for the web scraper, the CV analysis prompt engineering, and the database schema optimization.

- Event context: AI Tinkerers Toronto - December Meetup sponsored by Auth0 and TribalScale! — 2025-12-03 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_AA3BkfpGWxY

### [Super Coool Super Awesome Tennis Serve Analyzer](https://montreal.aitinkerers.org/talks/rsvp_4lDuqbxrR9s)

I love playing tennis, my serve is wildly inconsitent and cost me a lot of games. Instructors are pricey and I'm cheap and don't want to shell out 100$ an hour for someone to feeed me a handle full of tips that I could have googled myself. logically to improve ones serve on might actually just go and practice but that would be far to simple. instead I thought the best way to improve my tennis serve would be to sit behind a keyboard and build an web-app powered by AI to tell me how I'm messing up my serve. It got cold and snow came so I wasn't able to actually use it :( but In the presentation I will walk through the implementaiton details and give a demo

- Event context: AI Tinkerers Montreal: Demo Night — November 20, 2025 — 2025-11-20 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_4lDuqbxrR9s

### [IA médica multimodal: análisis de imágenes medicas y conversación clínica](https://pereira.aitinkerers.org/talks/rsvp_l47r_0l5jY4)

El Medical Imaging Diagnosis Agent es una aplicación web diseñada para asistir en el análisis preliminar de imágenes médicas utilizando inteligencia artificial a través de la API de Google Gemini. Esta herramienta permite a profesionales de la salud y estudiantes de medicina obtener un análisis inicial de imágenes médicas y mantener conversaciones contextuales sobre los hallazgos. La aplicación combina capacidades de análisis de imágenes con un sistema de chat inteligente que mantiene el contexto de análisis previos, proporcionando una experiencia integrada para la interpretación asistida de imágenes médicas.

- Event context: 🔥 AI TINKERERS - PEREIRA🤖 De tareas a sistemas inteligentes: la revolución de la automatización 🔥🤖 — 2025-10-30 — Pereira
- Public talk page: https://pereira.aitinkerers.org/talks/rsvp_l47r_0l5jY4

### [Integrating AI Agents in React and Node Applications](https://nyc.aitinkerers.org/talks/rsvp_V65dFTL4U5A)

In this talk, we'll dive into Playpals, an app that transforms the way parents connect. We'll start with a traditional parent social network and then demonstrate how we elevated the user experience by building and integrating AI agents. Learn how these agents simplify the process of scheduling playdates, turning a static platform into a truly intelligent, interactive tool for community building.

- Event context: NYC October Demo Day — 2025-10-02 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_V65dFTL4U5A

### [Semi-Technical Vibe Coding!](https://chicago.aitinkerers.org/talks/rsvp_M-Q7huI4FfA)

I built an AI Reciepe Generator (https://whattoeat.sortedbyshah.com/whattoeat/) and am now working on an AI Meal Planning function. I'd love to show it off, get feedback, as well as walk through how someone with just a CS Minor & less technical background is able to build software

- Event context: AI Tinkerers Chicago June 2.0 Meetup ft Comet — 2025-06-24 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_M-Q7huI4FfA

### [Icons - what's going on?](https://nashville.aitinkerers.org/talks/rsvp_k5WUZIneoXs)

While vibe coding an app for my wife, I discovered the painful difficulty of creating simple and meaningful icons using AI. This seems like an obvious use case, yet very elusive. Here I'll demo my attempts to use AI to solve this problem.

- Event context: AI Tinkerers Nashville – June 23rd, 2025 — 2025-06-23 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_k5WUZIneoXs

### [Vibe Editing – Asynchronous Voice-to-Edit Flow with AI Agents in Cursor](https://toronto.aitinkerers.org/talks/rsvp_Qnxcw3UBF7Y)

Capture ideas on the go with a simple button press. Your voice is recorded, then in the background AI agents transcribe and interpret your thoughts into actionable edit suggestions. Later, when you return to your desk, you review and approve the proposed document changes directly in Cursor. This async pipeline keeps you moving: speak now, refine later. Perfect for long-form writing, technical docs, or software design, Vibe Editing turns scattered thoughts into structured git-tracked edits without breaking your flow.

- Event context: AI Tinkerers Toronto - May 2025 Meetup: AGENTS at Ada — 2025-05-22 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_Qnxcw3UBF7Y

### [Personalized AI Tutor](https://toronto.aitinkerers.org/talks/rsvp_s_xEQsS6lP0)

We will be presenting a web application built using a local LLM that provides personalized learning plans by dynamically assessing the user's knowledge level. The application also gracefully handles FAQ-style queries, enhancing the overall user experience.

- Event context: AI Tinkerers Toronto - April 2025 Meetup at Shopify — 2025-04-24 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_s_xEQsS6lP0

### [Inside Cortex: Engineering an LLM-Powered Agentic OS](https://chicago.aitinkerers.org/talks/rsvp_h_HlajILZsE)

I’ll present a technical deep-dive into Cortex – Agentic OS, an LLM-powered operating system designed to manage modular digital knowledge workflows. The demo covers three specialized applications: • Explorer: Technical walkthrough of the file-management system, demonstrating how documents and generated outputs are uploaded, organized, and tracked through AI-enhanced workflows. • Deep Research: Behind-the-scenes look at how this module combines user-uploaded documents with live internet data, showing internal document search implementation, Gemini-powered content summarization, Google search integration, and the logic for automated report grading. • Maestro: Detailed code-level exploration into Maestro’s integration with financial databases, demonstrating automated workflow creation for competitive analyses and annual reports, and showcasing specialized tooling for competitor analysis, business highlight extraction, and detailed company description analysis. Expect detailed code walkthroughs, live examples, and practical insights on agent orchestration using LangGraph and Gemini API, emphasizing the engineering challenges and solutions behind Cortex’s intelligent modular design.

- Event context: AI Tinkerers Chicago April Meetup — 2025-04-15 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_h_HlajILZsE

### [In-Context Learning For Continuous Hyper-Personalization](https://la.aitinkerers.org/talks/rsvp_nmMMXxqgOnQ)

An iterative system for personalizing an LLM's generated outputs to specific users through few-shot examples.

- Event context: Feb 24 - LA AI Tinkerers Meetup & Demo — 2025-02-25 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_nmMMXxqgOnQ

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 664 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 220 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 106 public demos
- [Claude API](https://aitinkerers.org/technologies/claude-api) ([Markdown](https://aitinkerers.org/technologies/claude-api.md)) — 21 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Flutter](https://aitinkerers.org/technologies/flutter) ([Markdown](https://aitinkerers.org/technologies/flutter.md)) — 24 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 68 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 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
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Amazon Bedrock API](https://aitinkerers.org/technologies/amazon-bedrock-api) ([Markdown](https://aitinkerers.org/technologies/amazon-bedrock-api.md)) — 1 public demo
- [Angular](https://aitinkerers.org/technologies/angular) ([Markdown](https://aitinkerers.org/technologies/angular.md)) — 6 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos