# Google Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/google
> Markdown URL: https://aitinkerers.org/technologies/google.md
> Technology record last updated: 2026-02-22T16:33:30Z
> Generated: 2026-09-20T13:47:32Z

The global technology leader: Google organizes the world's information and delivers essential services (Search, Android, YouTube) to billions of users daily.

Google (a subsidiary of Alphabet Inc.) dominates the digital landscape, starting with its core search engine, which processes trillions of queries annually. The company’s vast ecosystem extends far beyond search: Android powers over 70% of the world's smartphones; YouTube serves billions of hours of video content; and Google Cloud Platform (GCP) competes aggressively in the enterprise space. They drive innovation using AI and machine learning, focusing on making information universally accessible and useful through products like Gemini and the Pixel hardware line. This strategic portfolio maintains Google’s position at the center of consumer and enterprise technology.

- Official technology site: https://about.google/
- Public AI Tinkerers demos and talks: 9
- Result page: 1 of 1

## Recent Public Talks and Demos

### [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

### [Multi-Agent Fraud Detection: When LLMs Argue About Bitcoin Laundering](https://toronto.aitinkerers.org/talks/rsvp_l2U61QefZDs)

I built a real-time Bitcoin fraud detection system where three LLM agents debate whether a transaction is fraudulent: - Agent 1 (Prosecutor): Uses Graph RAG (Neo4j) to find suspicious network patterns and builds a case for fraud - Agent 2 (Defense): Searches for legitimate explanations and challenges the prosecutor's claims - Agent 3 (Judge): Reviews both arguments and makes the final verdict The Live Demo: 1. A suspicious transaction streams in via Kafka 2. Prosecutor Agent queries the Neo4j graph and constructs a fraud case using Gemini 3. Defense Agent counter-argues with alternative explanations 4. Judge Agent renders a verdict with confidence scoring 5. I pop the hood and show: the exact prompts, the Cypher graph queries, and the decision logic Technical Deep Dive: - How I structure multi-hop graph context for LLM reasoning - Prompt engineering to prevent agent "hallucination" on graph data - Latency battles: why I moved from Gemini Pro to Flash and added prompt caching - The surprising failure modes: when agents agree too quickly vs. when they hallucinate connections

- Event context: AI Tinkerers Toronto - January 2026 Meetup at Google! — 2026-01-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_l2U61QefZDs

### [Dr Auntie](https://dubai.aitinkerers.org/talks/rsvp_sWWnSfyOWQQ)

Meet Dr. Aunty — an AI-powered Telegram health companion that transforms confusing lab reports into understandable, memorable advice delivered in the voice and attitude of a real aunty. This live demo will showcase how Dr. Aunty analyzes a lab report photo in under 2 seconds using Gemini Vision and Groq Llama 3.3, remembers your health trends via Mem0, and delivers dual-mode updates: comforting messages for patients and clinical summaries for caregivers. You’ll also see her custom-cloned voice (via ElevenLabs) and avatar videos (via fal.ai) that make health communication engaging, empathetic, and culturally authentic.

- Event context: AI Tinkerers Dubai Demo Day - November 15, 2025 — 2025-11-15 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_sWWnSfyOWQQ

### [DSPy 101](https://boston.aitinkerers.org/talks/rsvp_SyIBBZH64qI)

Learn by example to use DSPy and write AI programs, not prompts I will pick a classification task and walk through a DSPy program that loads evaluation data, evaluates a base classifier, optimizes the classifier and then evaluates the optimized classifier. I will highlight how the DSPy approach differs from having a big long string as the prompt.

- Event context: AI Tinkerers Boston: Langchain & Beyond Meetup — 2025-08-25 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_SyIBBZH64qI

### [Build Conversational AI Agents that speak ALL of Singapore's languages!](https://singapore.aitinkerers.org/talks/rsvp__o3bhqKErzI)

Singapore is a vibrant tapestry of languages and cultures—and now your AI agents can be too. In this session, discover how to build multilingual conversational agents using ElevenLabs' powerful conversational AI platform. Learn how to seamlessly integrate automatic language detection and real-time switching capabilities to create agents that effortlessly understand and respond in English, Mandarin, Malay, Tamil, and more.

- Event context: AI Tinkerers Singapore: 6th Meetup - April 25th, 2025 — 2025-04-25 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp__o3bhqKErzI

### [Talk about AI personal assistant](https://seattle.aitinkerers.org/talks/rsvp_t3TDH2Ez8Vk)

LLMs are kind of dumb. They excel at predicting the next token, but if you ask them about anything outside of their training set, you're SOL. Recently, this problem has been tackled via function calling, but setting these tools up has proved to be quite the ordeal. Thus, Patrick started with a simple goal: build an agentic, modular, and context-aware office assistant with access to all of your tools and files!

- Event context: AI Tinkerers Seattle - April Meetup — 2025-04-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_t3TDH2Ez8Vk

### [AI for Analyzing Trends](https://prague.aitinkerers.org/talks/rsvp_ushlLXZWFM4)

This talk is about building an AI-powered blog that uses trend data from Google and Amazon to write human sounding articles about what is trending. We will discuss the following topics: 1. Motivation for a trend app 2. Designing an AI-blog stack architecture 3. Implementation Details and Code Examples 4. How to take it further

- Event context: AI Tinkerers Prague Launch Event - September 2024 — 2024-09-04 — Prague
- Public talk page: https://prague.aitinkerers.org/talks/rsvp_ushlLXZWFM4

### [Combining Multiple Public Pre-Trained Models for Better Audio Segmentation](https://toronto.aitinkerers.org/talks/rsvp_t6jOg5jQ84M)

The work-in-progress includes an audio processing pipeline. The audio is segmented and transcribed. Linguistic text features are extracted from the transcribed text. The use of publicly pre-trained AI models has provided high quality results. The next development stage will be focused on finer segmentation of the audio using the outputs of these public models.

- Event context: AI Tinkerers Toronto - Inaugural Meetup — 2024-04-11 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_t6jOg5jQ84M

### [How to train ML models with feature constraints to guarantee expected model behaviors](https://la.aitinkerers.org/talks/rsvp_rJN7Qf7MaUY)

When training ML models, it is never the case that your data is perfect or infinite. The noise in your data will result in an ML model that has pockets of unexplainable behavior that go directly against your expectations. For example, consider training a model to predict the price of a house. You generate a prediction only to realize you input the wrong square footage, but after increasing the square footage the predicted price goes down. Now you struggle to trust the results of your model and are back to the drawing board. SOTAI enables you to train models that guarantee certain real-world expectations such as this one. Simply set a constraint such that increasing square footage should only ever increase the predicted price, all else being equal, and your model will guarantee this behavior even on unseen examples. Of course, it is only the expected increase that is guaranteed -- the amount of increase is learned from your data.

- Event context: Innaugural AI Tinkerers LA - Aug 17 — 2023-08-18 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_rJN7Qf7MaUY

## Related Technologies

- [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
- [Flash](https://aitinkerers.org/technologies/flash) ([Markdown](https://aitinkerers.org/technologies/flash.md)) — 14 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [Apache Kafka](https://aitinkerers.org/technologies/apache-kafka) ([Markdown](https://aitinkerers.org/technologies/apache-kafka.md)) — 8 public demos
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [Backend](https://aitinkerers.org/technologies/backend) ([Markdown](https://aitinkerers.org/technologies/backend.md)) — 7 public demos
- [Bubble](https://aitinkerers.org/technologies/bubble) ([Markdown](https://aitinkerers.org/technologies/bubble.md)) — 1 public demo
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [DSPY](https://aitinkerers.org/technologies/dspy) ([Markdown](https://aitinkerers.org/technologies/dspy.md)) — 12 public demos
- [Electron](https://aitinkerers.org/technologies/electron) ([Markdown](https://aitinkerers.org/technologies/electron.md)) — 12 public demos
- [ElevenLabs](https://aitinkerers.org/technologies/elevenlabs) ([Markdown](https://aitinkerers.org/technologies/elevenlabs.md)) — 42 public demos
- [ElevenLabs Conversational AI](https://aitinkerers.org/technologies/elevenlabs-conversational-ai) ([Markdown](https://aitinkerers.org/technologies/elevenlabs-conversational-ai.md)) — 3 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Gemini API](https://aitinkerers.org/technologies/gemini-api) ([Markdown](https://aitinkerers.org/technologies/gemini-api.md)) — 20 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Groq Llama 3](https://aitinkerers.org/technologies/groq-llama-3) ([Markdown](https://aitinkerers.org/technologies/groq-llama-3.md)) — 1 public demo
- [ICLR](https://aitinkerers.org/technologies/iclr) ([Markdown](https://aitinkerers.org/technologies/iclr.md)) — 1 public demo