# Claude-3 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/claude-3
> Markdown URL: https://aitinkerers.org/technologies/claude-3.md
> Technology record last updated: 2026-02-22T17:01:16Z
> Generated: 2026-08-26T10:18:44Z

Claude-3 is Anthropic's state-of-the-art multimodal model family (Opus, Sonnet, Haiku), setting new industry benchmarks for intelligence, speed, and vision capabilities.

Claude-3, developed by Anthropic, is a powerful family of three generative AI models: Opus, Sonnet, and Haiku. Opus, the flagship, excels in complex reasoning, outperforming peers on key benchmarks (MMLU, GPQA) and supporting a 200,000-token context window. Sonnet offers an optimal balance for enterprise workloads, delivering performance that is 2x faster than its predecessor, Claude 2.1. Haiku is the fastest and most cost-effective option, capable of processing a 10,000-token research paper (including charts) in under three seconds. All three models are multimodal, featuring strong vision capabilities for analyzing charts, diagrams, and PDFs alongside text, enabling advanced data extraction and analysis.

- Official technology site: https://claude.ai
- Public AI Tinkerers demos and talks: 110
- Result page: 1 of 5

## Recent Public Talks and Demos

### [AI All the Way Down: Building a Production Fuel Pricing System with 5 AI Agents](https://st-louis.aitinkerers.org/talks/rsvp_uWD0V_b2O1k)

I am a former long time CIO at High Tech manufacturer Laird Technologies (15 years), and then DuPont (https://www.linkedin.com/in/mattmizell/). I have recently joined a small local company named Better Day Energy to build the entire technology stack for last mile petroleum delivery. I am using AI to develop, and also run a lot of the backed. As an example: We use Claude Code to build AI agents in n8n and python that parse emails and monitor AI parsing failures. It's AI turtles all the way down—and it actually works in production.

- Event context: AI Tinkerers – St. Louis Meetup: February 4, 2026 — 2026-02-04 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_uWD0V_b2O1k

### [Violex — I’ll demo my project that enables learning to play the violin in a fun yet professional way, especially for people who have difficulty reading musical notation.](https://eindhoven.aitinkerers.org/talks/rsvp_BcDWQ0V1L38)

Violin is a very hard instrument to play. I’ll present my ongoing project called Violex, it is intended to help reading music sheets and mapping them on the instrument in a fun, intuitive and engaging way. The system also records your play and creates an AI/ML based feedback on how well you are performing! I’ll showcase my progress, the technical hurdles and the feedback mechanisms needed for creating an AI powered hardware like this.

- Event context: AI Tinkerers – Eindhoven Inaugural Meetup · 22 December 2025 — 2025-12-22 — Eindhoven
- Public talk page: https://eindhoven.aitinkerers.org/talks/rsvp_BcDWQ0V1L38

### [Coding Agents Are Good at Algorithms](https://eindhoven.aitinkerers.org/talks/rsvp_OMCQjnHBa1o)

I've been working on a solver for a word game called Strands. Wanting to try out the latest coding agents, I let Claude take a shot at writing an algorithm. I expected a little vibe-coding would get me most of the way there, but the computational complexity proved to be a lot more challenging than I thought. Along the way though, I learned to collaborate with my coding agent in a way that wasn't just a time save, it truly extended my abilities.

- Event context: AI Tinkerers – Eindhoven Inaugural Meetup · 22 December 2025 — 2025-12-22 — Eindhoven
- Public talk page: https://eindhoven.aitinkerers.org/talks/rsvp_OMCQjnHBa1o

### [Gotchas while building ChatGPT Apps](https://seattle.aitinkerers.org/talks/rsvp_ysWTzBfVe4w)

A ChatGPT app that helps you organize your next travel trip.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_ysWTzBfVe4w

### [Stop Generating, Start Understanding: Building a "Diagnosable" ColBERT for Grounded Late-Interaction Reasoning](https://brussels.aitinkerers.org/talks/rsvp_d9B2-FA9J54)

In a landscape obsessed with generative tokens, how can we build millisecond-latency reasoning engines that are interpretable by design and debuggable at the token level? In this demo, I will pop the hood on ClinicalEncoder25 to show how we achieve hallucination-free reasoning through the novel Diagnosable ColBERT architecture. I will walk through a live Jupyter notebook to demystify Late-Interaction Retrieval, visualizing the actual tensor operations that preserve token-level geometry instead of squashing documents into single embeddings. We will inspect the raw vector outputs of clinical text and, using my pre-computed ClinicalMap vector database, demonstrate a live debugging loop where we mathematically map specific token vectors back to SnomedCT concepts. You will see how the model connects the dots betwen a patient working at a "car repair shop" and his "lead contamination" to nudge the vector representation of the latter towards "past history of exposure to lead-based paint," proving that deep semantic understanding is possible without generating a single token.

- Event context: AI Tinkerers Brussels - December 17 — 2025-12-17 — Brussels
- Public talk page: https://brussels.aitinkerers.org/talks/rsvp_d9B2-FA9J54

### [fastworkflow is now SOTA on Tau Bench!](https://houston.aitinkerers.org/talks/rsvp_k2AwqMGR9Wo)

During the last talk a few months ago, we demo'd fastworkflow results on Tau Bench retail and airline benchmarks comparable to GPT4o. With our latest refinements, fastworkflow beats ALL models including Sonnet 4.5! And it does this using models as small as 7B and 14B parameters. I will demonstrate the results and talk about the refinements that made this possible as well as our roadmap for the next 6 months

- Event context: AI Tinkerers Houston Meetup: Code, Demos, and Agentic Architectures (December 9, 2025) — 2025-12-09 — Houston
- Public talk page: https://houston.aitinkerers.org/talks/rsvp_k2AwqMGR9Wo

### [Using the gh cli with local agents for pr responses and guidance](https://seattle.aitinkerers.org/talks/rsvp_jYDzYWaL_As)

I often find the UI for assigning agents (like copilot, etc) to tasks directly in github to be restrictive -- they lack context and can't be guided as easily. But I do like the github PR UI for providing specific feedback. Use both -- have the local agent use the gh cli to open the pr and respond to comments. Extra feedback can be given in the local chat if needed

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — December 8, 2025 — 2025-12-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_jYDzYWaL_As

### [Building AI personas to reduce LLM hallucinations and improve reliability of agentic systems.](https://portland.aitinkerers.org/talks/rsvp_zOOQR9hFzSs)

Andrew Becker — AI Engineer

- Event context: Portland: Agentic Systems Deep Dive — Building the Next Generation of AGI — 2025-12-04 — Portland
- Public talk page: https://portland.aitinkerers.org/talks/rsvp_zOOQR9hFzSs

### [AIR3.ai](https://lausanne.aitinkerers.org/talks/rsvp_xDJAqpdWCpI)

An agentic tool for literature reviews

- Event context: AI Tinkerers Lausanne December 2025 Meetup — 2025-12-03 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_xDJAqpdWCpI

### [Production Incident (PI) to Pull Request (PR) In Minutes](https://bengaluru.aitinkerers.org/talks/rsvp_x17wU05fOj8)

At Oodle AI, we are reimagining Observability with the help of Agentic AI workflows. In this talk, I will go over: 1. Our approach for AI-assisted debugging to provide you relevant insights on an alert. This workflow involves coordinating multiple agents using Google ADK along with tools specifically designed for providing relevant information to Agents. Integration with Cursor/Claude Code to go from a firing alert to a PR becomes possible. 2. Using ideas from WebMCP to enable users to perform day to day tasks like creating grafana dashboards, creating alerts, exploring metrics using prompts. I plan to give a short demo + go over implementation ideas for above.

- Event context: AI Tinkerers - Bengaluru - November meetup — 2025-11-29 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_x17wU05fOj8

### [The Engineer BS Detector: Why Authenticity Wins](https://belgrade.aitinkerers.org/talks/rsvp_1bAv865gK0U)

How to build and communicate engineer-oriented products without fluff. I’ll cover how technical audiences signal feedback, what they value in a product, how to market to them honestly and clearly, and where AI helps (or hurts) when communicating real product value.

- Event context: AI Tinkerers Belgrade Opening Meetup with PostHog — November 27, 2025 — 2025-11-27 — Belgrade
- Public talk page: https://belgrade.aitinkerers.org/talks/rsvp_1bAv865gK0U

### [Claudio: repo as agent](https://sf.aitinkerers.org/talks/rsvp_2C0H-nIGUWo)

Claudio is an experiment in how to create persistent, self improving agents by a simple mechanism of forking and deploying onto VM.

- Event context: AI Tinkerers x Google Cloud SF Meetup — 2025-11-21 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_2C0H-nIGUWo

### [Unstructure your CRM data with an AI node via n8n](https://san-diego.aitinkerers.org/talks/rsvp_6SXBaQqZdVg)

I am open to presenting how to connect CRM to any AI model API via n8n. The use case that I would demo would be showing the webhook setup in a Hubspot private app, a live demo of the n8n flow once triggered (showcasing the AI agent), and the output of that flow. I think this is a cool topic because people always talk about structuring unstructured data, while I'm showcasing the value of doing the opposite. The value of this operationally is that in a sales pipeline, users down funnel actually really appreciate summarized/unstructured data to review, rather than reviewing fragmented structured data.

- Event context: AI Tinkerers x Google AI Meetup, San Diego — 2025-11-21 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_6SXBaQqZdVg

### [Introducing Youz: Your Smart Travel Guide](https://nurnberg.aitinkerers.org/talks/rsvp_RVnHATk2Uck)

Have you ever visited a historical or scenic site and wondered about the meaning behind its symbols, architecture, or history? Usually, you’d have to rely on tour guides, who may not speak your language fluently or might give rushed, incomplete explanations. If you don’t fully understand them or have follow-up questions, grasping the full story can feel nearly impossible. That’s where Youz comes in! What is Youz? Youz is a smart, AI-powered app that removes language and information barriers while traveling. Just install the Youz app on your phone, point your camera at a historical monument, temple, museum, or scenic site, and Youz instantly delivers detailed, accurate information about the location in your native language — both as clear audio narration and on-screen text. Youz is powered by the latest version of Gemini to answer your questions intelligently. To provide precise and relevant information (for example, about a specific temple), Youz first uses geofencing to detect nearby landmarks. It then queries a specialized vector database containing rich, curated information about historical and cultural sites, building the perfect context to answer your question accurately. With Youz, you’re no longer dependent on tour guides or language skills — you get a personal, expert guide in your pocket, anytime, anywhere.

- Event context: AI Tinkerers Nürnberg Meetup – Nov 20 — 2025-11-20 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_RVnHATk2Uck

### [LLM Gateways, a Software Engineering Perspective](https://amman.aitinkerers.org/talks/rsvp_uFflftd2KAM)

Taking a deep look into LLM Gateways (LiteLLM or similar), and the software engineering concepts behind the scene. We will be looking into the features of an LLM Gateway, from loadbalancing, moderation, abstractive approach and more.

- Event context: AI Tinkerers Amman Meetup — November 15, 2025 — 2025-11-15 — Amman
- Public talk page: https://amman.aitinkerers.org/talks/rsvp_uFflftd2KAM

### [Natural Language to Robot Motions](https://seattle.aitinkerers.org/talks/rsvp_xJ2TlLuu5u0)

Zettaware is an agentic robotics platform for robot motion planning.

- Event context: Frontier Builds Demo Night: Experiments at the Edge of AI — 2025-11-13 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_xJ2TlLuu5u0

### [turn logic into UI](https://berlin.aitinkerers.org/talks/rsvp_QrvkQdcUPWM)

a "grammarly for logic" prototype, exploring how we can use the ability to transform cognitive processes/representations into structured data and interfaces.

- Event context: AI Tinkerers Berlin Meetup - November 12th, 2025 — 2025-11-12 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_QrvkQdcUPWM

### [Multi Agent Business Insights](https://toronto.aitinkerers.org/talks/rsvp_G1JVVCN_B2Q)

Business Insights is an advanced AI-powered web information extraction system that transforms how businesses gather competitive intelligence and market data. Using cutting-edge multimodal AI agents, it automatically extracts comprehensive business information from websites including company names, business classifications, addresses, and brand assets. The Problem We Solve: Hours spent gathering basic business information Inconsistent Data Quality: Human error in data collection and classification Scalability Challenges: Difficulty analyzing hundreds or thousands of businesses Fragmented Information: Data scattered across multiple sources and formats 💡 Our Solution Business Insights automates the entire business intelligence pipeline using specialized AI agents that work together to deliver structured, actionable data at scale.

- Event context: AI Tinkerers Toronto - November 2025 Meetup at Shopify! — 2025-11-10 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_G1JVVCN_B2Q

### [Building Declarative MCP Servers around existing Apps with GenMCP](https://toronto.aitinkerers.org/talks/rsvp_xyvmmZ1klo0)

Starting with a CLI and a REST app I want my agent to be able to interact with, I will use GenMCP live to build a declarative MCP server around these applications within minutes. This demo will show the advantages and disadvantages of this approach when compared to building an MCP server using the SDKs.

- Event context: AI Tinkerers Toronto - October 2025 Meetup at CIBC | Simplii — 2025-10-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_xyvmmZ1klo0

### [Aprendizajes de Vibecoding en Walmart](https://santiago.aitinkerers.org/talks/rsvp_V-VqgGiO4Jw)

Creación de Líder IA, el primer asistente de compras con genAI de Chile, desarrollado mediante sesiones reales de Vibe Coding en Walmart.

- Event context: Estructura, Risa y Ecosistemas: el nuevo ADN de la IA Chilena — 2025-10-29 — Santiago
- Public talk page: https://santiago.aitinkerers.org/talks/rsvp_V-VqgGiO4Jw

### [¿Sueñan los androides con gaviotas de plata?](https://santiago.aitinkerers.org/talks/rsvp_-wALyUM8uek)

Las inteligencias artificiales no pueden comprender plenamente el humor chileno porque este depende de contextos culturales, referencias compartidas y matices lingüísticos únicos. Sin embargo, si logramos que una IA analice y aprenda de nuestro humor, podríamos enseñarle algo más profundo que lenguaje: podríamos enseñarle identidad cultural.

- Event context: Estructura, Risa y Ecosistemas: el nuevo ADN de la IA Chilena — 2025-10-29 — Santiago
- Public talk page: https://santiago.aitinkerers.org/talks/rsvp_-wALyUM8uek

### [Semantic IDs: Building blocks for generative recommendations](https://denver-boulder.aitinkerers.org/talks/rsvp_YvkqmQvZ-1M)

How do you get LLMs to understand vast catalogs of music, podcasts, images, videos, and any other entity that you may be working with? This talk will discuss how we can use Semantic IDs to turn powerful pre-trained item embeddings into tokens that can be interspersed with natural language in order to recommend, describe, or rank things that are too hard to "textify" normally. I'll cover the basic concepts around Semantic IDs and talk about how companies like Spotify, Google, and Meta are leveraging Semantic IDs to build the next generation of AI-powered recommendation experiences.

- Event context: AI Tinkerers Denver Meetup - October 24, 2025 — 2025-10-24 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_YvkqmQvZ-1M

### [AI-Driven Global Admissions: How One Click Can Change Student Mobility](https://seattle.aitinkerers.org/talks/rsvp_rg08rkUArOo)

the past three years, I’ve been working on building an AI-powered platform that simplifies the process of studying abroad. Every year, thousands of students face complex, time-consuming steps just to apply to universities in other countries. My platform allows students to apply to multiple universities worldwide within a few clicks — and receive their offer letters within minutes. On the university side, the AI system instantly reviews documents, verifies eligibility, and generates admission decisions automatically. In this talk, I’ll share how this idea was born, the real-world problems it solves, and how AI automation can transform the global education and admission system into a faster, more accessible, and transparent process for everyone.

- Event context: October Meetup - Science Fair at Foundations — 2025-10-23 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_rg08rkUArOo

### [A few of my vendor-agnostic Open-source projects around LLMs](https://valencia.aitinkerers.org/talks/rsvp_ucen6oeKdKc)

I plan to present my three non-commercial open-source projects relevant to the subject: - https://github.com/Nayjest/Gito (AI Code reviewer) - https://github.com/Nayjest/lm-proxy (LLM Proxy, lightweight minimalistic alternative to LiteLLM) - https://github.com/Nayjest/ai-microcore (Adapter lib for various LLM and VectorDB API's) With emphasis likey on Gito

- Event context: Opening AI Tinkerers Valencia x VDS - 22 October — 2025-10-22 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_ucen6oeKdKc

## Related Technologies

- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 444 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 518 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos
- [Sonnet](https://aitinkerers.org/technologies/sonnet) ([Markdown](https://aitinkerers.org/technologies/sonnet.md)) — 25 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 654 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 187 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 216 public demos
- [Anthropic](https://aitinkerers.org/technologies/anthropic) ([Markdown](https://aitinkerers.org/technologies/anthropic.md)) — 36 public demos
- [GPT-4o](https://aitinkerers.org/technologies/gpt-4o) ([Markdown](https://aitinkerers.org/technologies/gpt-4o.md)) — 57 public demos
- [AWS Bedrock](https://aitinkerers.org/technologies/aws-bedrock) ([Markdown](https://aitinkerers.org/technologies/aws-bedrock.md)) — 9 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 178 public demos
- [Llama 3](https://aitinkerers.org/technologies/llama-3) ([Markdown](https://aitinkerers.org/technologies/llama-3.md)) — 38 public demos
- [AI21 Labs API](https://aitinkerers.org/technologies/ai21-labs-api) ([Markdown](https://aitinkerers.org/technologies/ai21-labs-api.md)) — 1 public demo
- [AI agent](https://aitinkerers.org/technologies/ai-agent) ([Markdown](https://aitinkerers.org/technologies/ai-agent.md)) — 8 public demos
- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos

## More Results

- Next: https://aitinkerers.org/technologies/claude-3.md?page=2