# Generative AI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/generative-ai
> Markdown URL: https://aitinkerers.org/technologies/generative-ai.md
> Technology record last updated: 2026-02-24T08:27:55Z
> Generated: 2026-09-23T08:57:33Z

Generative AI employs foundation models (e.g., Large Language Models) to create novel, complex content—text, images, code, and audio—from simple user prompts.

Generative AI is a deep learning paradigm focused on *creating* new output, not just classifying data. Key models like OpenAI's GPT-4 and Stability AI's Stable Diffusion leverage massive datasets (trillions of parameters) to identify complex patterns. This enables them to generate high-quality, original content: from drafting software code and summarizing 50-page reports to producing photorealistic images in seconds. It fundamentally shifts the human-computer interaction model from command-based to prompt-based creation, driving immediate, high-impact productivity gains across all industries.

- Official technology site: https://www.ibm.com/topics/generative-ai
- Public AI Tinkerers demos and talks: 45
- Result page: 1 of 2

## Recent Public Talks and Demos

### [From Chat to Action: Omnichannel AI in the Real World](https://saopaulo.aitinkerers.org/talks/rsvp_sXjsXqQu7Ro)

I built an omnichannel AI agent that allows a conversation to move seamlessly across different communication channels while preserving context, memory, and session continuity. In this demo, a user starts by registering basic information, selects a scenario, and then interacts with the agent through WhatsApp. The agent can continue the same conversation across channels such as messaging, phone, email, and future digital touchpoints, without losing history or forcing the user to restart context. The goal is to demonstrate how conversational AI can become channel-independent, enabling a persistent and natural user journey across enterprise communication environments.

- Event context: AI Tinkerers SP e Banco BMG — 2026-03-26 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_sXjsXqQu7Ro

### [AI Predictions for 2026 from AI Tinkerers](https://montreal.aitinkerers.org/talks/rsvp_iBOlQ50Yzlk)

AI Predictions for 2026 from AI Tinkerers Community

- Event context: AI Tinkerers Montreal - January 2026 Meetup at Ateko — 2026-01-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_iBOlQ50Yzlk

### [Infinite Wiki - Using GenAI for cooperative World Building](https://cologne.aitinkerers.org/talks/rsvp__PwrDSyvMvE)

I'll be showing off a hobby project that's using generative AI to auto-create an ever expanding wiki on any world you can think of. The project goes for a human-AI collaborative approach giving humans lots of control during generation and editing capabilities.

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

### [Personalized Product Discovery with Agentic AI: Beyond Traditional Recommendation Engines](https://singapore.aitinkerers.org/talks/rsvp_TYi5dO1vY58)

E-commerce platforms have long used recommendation engines to boost sales. Yet, these systems often fall short when it comes to true personalization. This talk introduces how Agentic AI can revolutionize recommendations for mobiles, gadgets, accessories, and insurance plans—shifting from static algorithms to adaptive, goal-oriented agents. We’ll discuss how these agents combine customer intent, multi-modal data, and conversational interactions to deliver next-generation recommendations that drive engagement, increase trust, and create measurable business impact.

- Event context: AIT Singapore - AI Agents Showcase - 7th Oct 2025 — 2025-10-07 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_TYi5dO1vY58

### [FINDER AFRIC](https://nairobi.aitinkerers.org/talks/rsvp_EJjkc96NLNs)

Finder is an AI-powered shopping tool that lets buyers find exactly what they’re looking for just by using images. We’re building a platform where vendors don’t need to be known or followed to make a sale—if they have the product, we’ll match them with the buyer using visual search. I’ll be showcasing how Finder helps small vendors increase visibility and reach, and how we use cutting-edge image recognition to simplify product discovery.

- Event context: AI Tinkerers - Nairobi Inaugural Meetup (April) — 2025-04-09 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_EJjkc96NLNs

### [VOZY: PoC Sales FAQ Agent (VoiceGenAI)](https://medellin.aitinkerers.org/talks/rsvp_Qsjz5DCQzYQ)

This agent is a virtual assistant to attend phone calls from prospect or potential customers, answer some FAQs about the owner company and catch the interest details and contact details.

- Event context: AI Tinkerers Medellín #11 - Science Fair - Agentes en acción — 2025-04-01 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_Qsjz5DCQzYQ

### [Objetos de aprendizaje conducidos por IA](https://medellin.aitinkerers.org/talks/rsvp_8wTJzmdM4rs)

Como desarrollar objetos virtuales de aprendizaje, interactivos, y lo mejor, creador por IA.

- Event context: AI Tinkerers Medellín #10 - 26 de Febrero 2025 — 2025-02-26 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_8wTJzmdM4rs

### [x2 faster diffusion model in 3 lines of code](https://paris.aitinkerers.org/talks/rsvp_gDKrDrEbvwU)

In a few lines of code, pruna enables you to compress any text to image GenAI model. We will show how we can easily generate an image, and how we can speedup this generation without any quality loss.

- Event context: AI Tinkerers - Paris Meetup on January 30th — 2025-01-30 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_gDKrDrEbvwU

### [Limits of Data Extraction with LLMs](https://boston.aitinkerers.org/talks/rsvp_V6-lXyyojRQ)

ETL and data processing/extraction is one of the most useful generalized tasks LLMs can pull off. This coding demo would walk through the basics and advanced capabilities of generative AI for explicit data extraction.

- Event context: AI Tinkerers Boston Meetup January 2025 — 2025-01-27 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_V6-lXyyojRQ

### [Finding Patent Prior Art with AI](https://chicago.aitinkerers.org/talks/rsvp_vHz4JF0Wu5U)

Patents form the cornerstone of innovation protection, with the USPTO processing over 600,000 applications annually representing billions in economic value. To get a patent, an invention must be genuinely novel—but proving novelty is a complex, time-consuming process that costs companies tens of thousands of dollars per application. Patent examiners and professionals spend countless hours searching for "prior art" that might show an invention already exists. In this talk, I will demonstrate an AI-powered system that not only identifies relevant prior art but provides detailed mapping between patent claims and existing disclosures, enabling patent examiners to quickly evaluate patentability and transform the examination process.

- Event context: AI Tinkerers Chicago January Meetup — 2025-01-14 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_vHz4JF0Wu5U

### [Space LLM](https://paris.aitinkerers.org/talks/rsvp_Wu5F_vrQMUw)

Generative Floor Plans Designs using fine-tuned LLMs

- Event context: AI Tinkerers - Paris Meetup on December 10th — 2024-12-10 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_Wu5F_vrQMUw

### [CTO @ Neuphonic](https://london.aitinkerers.org/talks/rsvp_9KkLFlU8bJc)

We build low latency text to speech systems for conversational AI!

- Event context: AI Tinkerers London - December Meetup 🎄 — 2024-12-04 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_9KkLFlU8bJc

### [LABonWEB: An AI-powered platform for virtual science labs](https://toronto.aitinkerers.org/talks/rsvp_IdOwiCXacjs)

LABonWEB is a virtual learning platform empowering educational institutions to create immersive, impactful learning modules using Generative AI and advanced simulations. Designed for students and researchers alike, LABonWEB transforms complex subjects into interactive experiences, fostering deep understanding and innovation in fields like chemistry, materials science, and beyond.

- Event context: AI Tinkerers Toronto - November 2024 Meetup at Accenture — 2024-11-28 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_IdOwiCXacjs

### [One Digital Timeline - Automatic Context Switching](https://nyc.aitinkerers.org/talks/rsvp_hzhSwxy-9IE)

You wouldn’t have different human personal assistants for each project in your life - so why do we change our behavior to accommodate the limitations of LLM powered personal assistants? The latest contextFound feature demonstrates a single event / conversation timeline - while automatically switching to the appropriate context for each chat completion. It is the first glimpse of a future where you have a single digital timeline for your life, while still working naturally within constrained contexts. I will demo a conversation in the app that spans multiple projects, showing how the system detects and switches context behind the scenes automatically to draw on a dedicated scratchpad of status / historic information.

- Event context: Vector Databases Are the Wrong Abstraction! Friendsgiving with Timescale — 2024-11-21 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_hzhSwxy-9IE

### [RAGBuilder by Krux AI](https://bengaluru.aitinkerers.org/talks/rsvp_xyUihhdpH9g)

RAGBuilder is an open-source toolkit that helps you create optimal Production-ready RAG (Retrieval-Augmented-Generation) setup for your data automatically. By performing hyperparameter optimization on various RAG parameters (Eg: chunking strategy, chunk size, embedding models etc.), RAGBuilder evaluates these configurations against a test dataset to identify the best-performing setup for your data.

- Event context: AI Tinkerers Bangalore - November - RSVP REQUIRED — 2024-11-12 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_xyUihhdpH9g

### [PREMIER SPORTS](https://dubai.aitinkerers.org/talks/rsvp_9275Yfq6xKc)

Title: Predicting Football Match Outcomes with AI: My Approach to Premier Sports Description: I'm excited to share my project, PREMIER SPORTS, an AI-powered application designed to predict football match outcomes. By leveraging advanced machine learning algorithms and data analytics, I aim to provide accurate predictions that enhance game analysis for fans, coaches, and analysts alike. My approach combines historical team performance data with real-time player and team statistics to deliver more insightful and actionable information. I'm particularly interested in exploring how my model can be fine-tuned using transfer learning techniques, enabling me to adapt to changing team lineups and player performances. I'll also be showcasing some key features of my tool, including: Real-time data ingestion from various sources (e.g., sports databases, social media) Advanced feature engineering techniques for handling high-dimensional data Model selection and hyperparameter tuning Technical Depth and Focus: To provide a more comprehensive understanding of my approach, I'll be focusing on the following technical aspects: Data Handling: I employ a combination of libraries such as pandas, to carry out feature engineering, for labelling and extracting as much relevant data as possible. Transfer Learning Techniques: I leverage pre-trained language models such as Llama to capture contextual relationships within predicted match data and give insights to the application user. Live Demonstration and Code Walk-through: To enhance the audience's understanding of my approach, I'll be providing a live demonstration that includes: Interactive Data Visualization: I'll use a library like Plotly to create an interactive visualization of my data, allowing the audience to explore different scenarios and see how my model generates predictions. Code Walk-through: My demo will include a code walk-through where I explain the reasoning behind specific design choices, highlighting how AI techniques can be applied to improve the accuracy and interpretability of my model. Generative AI Integration: To further enhance the interpretability of my model, I'll be incorporating generative AI techniques: Text Generation: I'll use Llama to generate text-based outputs (e.g., player profiles, and team statistics) that can provide additional context for predictions. Clarity and Engagement To ensure clarity and engagement during the presentation: Concrete Examples: I'll use concrete examples from real-world football matches together with a web UI dashboard, to illustrate how my model can be applied in practice.

- Event context: AI Tinkerers - Dubai Meetup #3 (November) — 2024-11-10 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_9275Yfq6xKc

### [Empowering service reliability: A predictive and generative AI tool for early fault detection and field technician support](https://medellin.aitinkerers.org/talks/rsvp_fCAGcOFYUNY)

Immersion in how we developed an innovative tool that combines predictive and generative AI for early fault detection, data enrichment, and support for field technicians in diagnosing and resolving Internet service degradations. Discover how this cutting-edge solution enhances service reliability and empowers teams to maintain peak performance

- Event context: AI Tinkerers Medellín #7 - SoftServe - 5 de Noviembre — 2024-11-05 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_fCAGcOFYUNY

### [Toybox](https://toronto.aitinkerers.org/talks/rsvp_A41w5FMUrnQ)

An Jackbox TV-style party game that uses AI image generation as the primary mechanic. The game starts with players writing prompts to generate images using a given set of starting words. In subsequent rounds, each player receives an image from another player and has to try to create as similar an image as possible. The catch? They can't use the same words. Every round, more words are taken away until you're left trying to generate an image of a cat without using the words cat, kitten, feline, kitty, or any other cat-adjacent word.

- Event context: AI Tinkerers Toronto - Spooky Botober Meetup at Mozilla HQ — 2024-10-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_A41w5FMUrnQ

### [RFP Summary](https://montreal.aitinkerers.org/talks/rsvp_tlZIcFu8LAY)

Hi - I am JP - I developed an RFP Summary with Gen AI. I have linked a video URL which will give you a good idea of the demo.

- Event context: AI Tinkerers - Montreal Inaugural Meetup (October) — 2024-10-29 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_tlZIcFu8LAY

### [Classifying Data with LLMs](https://amsterdam.aitinkerers.org/talks/rsvp_tkzXfpiXRgg)

GenAI can create categories and match items into these categories. This can be a powerful alternative to traditional classifiers which require large labelled training sets.

- Event context: AI Tinkerers Amsterdam - September — 2024-09-25 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_tkzXfpiXRgg

### [Post-Postman: Creative End-to-End API Testing with Generative AI](https://amsterdam.aitinkerers.org/talks/rsvp_lBLnWhgMApA)

How can we use GenAI to help developers build and debug API's faster. In this lightning talk we will show what we've been prototyping at Fiberplane; an HTTP debugging tool using GenAI for payload suggestions and code prompts, friendly and hostile personas, and third party webhooks in order to squash bugs way earlier in the development cycle. Your code reviewer will wonder what shadow team you’ve secretly hired.

- Event context: AI Tinkerers Amsterdam - September — 2024-09-25 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_lBLnWhgMApA

### [Computer Vision and Nanotechnology to Power Immersive Content](https://nyc.aitinkerers.org/talks/rsvp_hAb7erkjEQU)

Leia Inc. utilizes computer vision algorithms and nanotechnology to create immersive content on any device. In this short presentation you will learn how Leia is working with creators and OEMs to bring this exciting future to reality.

- Event context: AI Tinkerers September Meetup at Betaworks — 2024-09-18 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_hAb7erkjEQU

### [Transforming Alerts into Actions](https://austin.aitinkerers.org/talks/rsvp_LXb_T8feHJw)

Leveraging genAI to automate response to AWS CloudWatch alerts. I will cover ideas, pitfalls and considerations for practical use.

- Event context: Community AI Demos - September Edition — 2024-09-12 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_LXb_T8feHJw

### [RAG for Voice Assistants](https://hamburg.aitinkerers.org/talks/rsvp_bFvn83wouWk)

I'd like to talk about building a simple RAG pipeline for voice assistants to expand access to knowledge during real-time conversations and avoid the current character limits of voice builder platforms.

- Event context: AI Tinkerers Hamburg - September 12 — 2024-09-12 — Hamburg
- Public talk page: https://hamburg.aitinkerers.org/talks/rsvp_bFvn83wouWk

## 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
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos
- [Computer Vision](https://aitinkerers.org/technologies/computer-vision) ([Markdown](https://aitinkerers.org/technologies/computer-vision.md)) — 22 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
- [Stable Diffusion](https://aitinkerers.org/technologies/stable-diffusion) ([Markdown](https://aitinkerers.org/technologies/stable-diffusion.md)) — 32 public demos
- [TensorFlow](https://aitinkerers.org/technologies/tensorflow) ([Markdown](https://aitinkerers.org/technologies/tensorflow.md)) — 90 public demos
- [Text-to-Speech](https://aitinkerers.org/technologies/text-to-speech) ([Markdown](https://aitinkerers.org/technologies/text-to-speech.md)) — 16 public demos
- [DALL-E 2](https://aitinkerers.org/technologies/dall-e-2) ([Markdown](https://aitinkerers.org/technologies/dall-e-2.md)) — 7 public demos
- [DALL-E 3](https://aitinkerers.org/technologies/dall-e-3) ([Markdown](https://aitinkerers.org/technologies/dall-e-3.md)) — 12 public demos

## More Results

- Next: https://aitinkerers.org/technologies/generative-ai.md?page=2