# Claude Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/claude?page=5
> Markdown URL: https://aitinkerers.org/technologies/claude.md?page=5
> Technology record last updated: 2026-09-18T15:14:01Z
> Generated: 2026-09-22T06:52:40Z

Claude is Anthropic's flagship family of large language models (LLMs): a high-performance, Constitutional AI system built for safety, complex reasoning, and expert-level collaboration.

Claude is a next-generation AI assistant developed by Anthropic, a research firm prioritizing AI safety. The models (including Opus, Sonnet, and Haiku) leverage Constitutional AI to ensure helpful, honest, and harmless outputs, a key differentiator from competitors. Claude excels at complex enterprise tasks: processing massive context windows for in-depth data analysis, generating and reviewing code, and providing expert-level summarization for documents up to 200,000 tokens. It is deployed as a conversational chatbot and via API, offering scalable AI solutions for developers and businesses.

- Official technology site: https://claude.ai/
- Public AI Tinkerers demos and talks: 174
- Result page: 5 of 8

## Recent Public Talks and Demos

### [Universal Context Layer](https://chicago.aitinkerers.org/talks/rsvp_m5aSvRoAkqc)

A unified context layer that makes long AI threads usable across tools. It stores key facts and conversation history in Pinecone, auto-compresses before token limits, and lets Claude retrieve the exact slice you need—decisions, constraints, summaries—without re-explaining threads.

- Event context: AI Tinkerers Chicago December Meetup ft Turing — 2025-12-09 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_m5aSvRoAkqc

### [MindServe AI: Real-Time GPU-Powered Computer Vision + RAG Coaching Pipeline](https://nyc.aitinkerers.org/talks/rsvp_GzawB-Spyz0)

MindServe AI is a fully-deployed real-time inference system that analyzes tennis match video on GPU and streams structured coaching insight back to the user. The backend runs YOLOv8 + MediaPipe pose models in parallel, detects rallies using a state machine, and pushes frame overlays via WebSockets as processing happens. At the same time, structured match data is fed into a retrieval-augmented coaching engine using Pinecone + LLM reasoning to provide mental-performance feedback. This talk will walk through the full infrastructure stack — from GPU scheduling to async model serving to vector-database-driven reasoning — all demonstrated live with running code.

- Event context: The Future of AI Infrastructure (Ft. Oracle & NVIDIA) — 2025-12-09 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_GzawB-Spyz0

### [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

### [The End of Fake News: How AI is restoring trust in media](https://bogota.aitinkerers.org/talks/rsvp_iCS09eSf7ts)

VeloBlanco is the AI-powered co-pilot for fact-checkers and media professionals. We automate the manual bottlenecks of verification—extracting claims, conducting multi-source research, and scoring source credibility—in seconds rather than hours. Equipped with advanced detection for AI-generated audio and video, VeloBlanco handles the heavy lifting of investigation so you can focus on critical analysis and the final editorial decision.

- Event context: AI Tinkerers Bogotá - Nov 2025 — 2025-11-27 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_iCS09eSf7ts

### [Why I dropped using REST for MCPs and started using GraphQL.](https://poland.aitinkerers.org/talks/rsvp_ZT1zz0ewZj8)

GraphQL offers huge benefits over REST for querying relational data. Yet almost no examples online use it. i'll present how huge impact on quality of tool calling, reducing the network load & tokens usage GraphQL has when implemented as MCPs. I'll cover: - when should MCP use GraphQL - how to implement MCP with GraphQL-like interface - how to use MCPs that use GraphQL-like interface - real-life impact on development speed, infrastructure, llm costs.

- Event context: AI Tinkerers Poland #6 - Meetup in Warsaw (26th November) — 2025-11-26 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_ZT1zz0ewZj8

### [Your own Cursor Tab: Reverse Engineering Tab Completion](https://london.aitinkerers.org/talks/rsvp_qU6onR12gGY)

I decompiled Cursor's tab completion (originally Supermaven's) to figure out how it actually works. There's a surprisingly large gap between "predict the next line" and what you experience in production editors. I'll walk through several implementations: starting from the vibe-code, show why it fails and how to fix it. Each iteration gets closer to Cursor's behaviour. Hopefully it'll save people a lot of time if they're working in editor integrations or context-aware AI systems.

- Event context: AI Tinkerers London Meetup - 25th November 2025 — 2025-11-25 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_qU6onR12gGY

### [From Error to Prod in 3 Minutes: My Replit → Sentry → GitHub → CodeRabbit Ship Loop](https://seattle.aitinkerers.org/talks/rsvp_9nHH45wrtts)

I’ll demo a real developer workflow where an error in production is detected in Sentry, triaged, and fixed end-to-end using AI-assisted tooling. The loop: (1) trigger a live bug and open the Sentry issue with stack trace + breadcrumbs; (2) use Replit (with AI assist) to generate the patch and a unit test; (3) push a branch to GitHub; (4) CodeRabbit reviews the PR; (5) CI runs tests, static analysis, and coverage gates; (6) on merge, GitHub Actions creates a Sentry Release and deploys; (7) Sentry auto-resolves the issue and links the fix to the release. One measured improvement I’ll show: lead time from error → fix → deploy.

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — November 3, 2025 — 2025-11-04 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_9nHH45wrtts

### [Automating error analysis - what works and what doesn't](https://liverpool.aitinkerers.org/talks/rsvp_9LjshIDL1Do)

Error analysis is known to be the highest ROI step in building reliable agents that work. However, as agent & task complexity grow, manual approaches to it become prohibitive, and naive ways of automating it remain unsatisfying. How *should* developers scale up this key step in agent evaluation? Here, I'll present our recent findings on what works - and what doesn't - when automating error analysis. TL;DR: we can do a lot better than stuffing everything into an LLM, with a bit of intentional context engineering and task decomposition.

- Event context: AI Tinkerers Liverpool HITL Meetup at FACT Lab — 2025-10-28 — Liverpool
- Public talk page: https://liverpool.aitinkerers.org/talks/rsvp_9LjshIDL1Do

### [AI in Global Logistics - Moving the World](https://st-louis.aitinkerers.org/talks/rsvp_ZpNwboe2ENs)

I’ve been developing general and single use apps using no-code and low-code tools to facilitate certain tasks required for international shipping - a duty/tariff calculator to keep abreast of changing Customs rates, an app for handling trade show logistics, and others to facilitate certain trade activities. The first publicly released tools was a logistics wrapped AI chat tool used to do everything from tracking international containers to sourcing new carriers and built around Grok’s API.

- Event context: AI Tinkerers - St. Louis October Meetup — 2025-10-22 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_ZpNwboe2ENs

### [An abecedary of AI: towards 26 generative vibe coded AI experiments](https://montreal.aitinkerers.org/talks/rsvp_dOrV87JYvVM)

xx-c.art is a living abecedary of experimental AI subdomains. each letter of the alphabet becomes its own lab, hosting autonomous scripts, generative rituals, and protocol-driven artworks. the project explores how an artist-developer can treat infrastructure as medium: cron jobs as performance, protocols as dramaturgy, and system folders as narrative space. this talk will focus on a handful of subdomains (doxa, eco, flux, latent) that demonstrate how simple linux stacks orchestrate multimodal LLMs (gpt-5, claude, ollama), audiovisual synthesis engines (strudel, hydra), and generative media APIs. i’ll walk through the system architectures behind these letters—how outputs are chained across services, how model latency and scheduling are managed, and how long-running autonomous scripts stay alive. code snippets and diagrams will show exactly how these experiments are scaffolded.

- Event context: AI Tinkerers Montreal – Spooky October 2025 Meetup — 2025-10-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_dOrV87JYvVM

### [What I Learned Building a Ride Share Platform for RoboTaxis](https://amsterdam.aitinkerers.org/talks/rsvp_bcWgooXQCbE)

What happens when autonomous vehicles need to communicate with passengers, dispatchers, traffic systems, and each other in real time? Building a RoboTaxi platform taught me that traditional AI architectures crumble under the complexity of large-scale multi-agent communication. In this talk, I'll share hard-won lessons from architecting a distributed AI system where hundreds of autonomous agents coordinate thousands of rides daily. You'll discover why point-to-point agent communication creates a brittle mess, and how event-driven architecture (EDA) becomes the nervous system that keeps everything connected. Through a live demo of the RoboTaxi platform, I'll show you: - How AI agents can communicate asynchronously without tight coupling - The architecture decisions that separate toy demos from production-ready AI systems Whether you're building chatbot networks, autonomous systems, or multi-agent AI applications, this session will give you the architectural foundation to scale beyond the prototype phase. Let's take this ride together.

- Event context: AI Tinkerers Amsterdam — October Edition: Agents in production — 2025-10-10 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_bcWgooXQCbE

### [Test2Synth: controlling hardware music geart from text](https://tokyo.aitinkerers.org/talks/rsvp_gicqjGFQ-wc)

A dirty attempt at interfacing LLM and test-based interface with music hardware. Hardware synthesizer have seen a resurgence. They can be fairly complex to build. We will show how to build a simple LLM-based system to program synthesizer from text input. By interfacing LLM to hardware synth through MIDI, the underlying principle can in theory control any MIDI-enabled system. Depending on the A/V capabilities at the demo, I will have either a video to present, or demonstrate live with actual hardware how to make sound from the system.

- Event context: AI Tinkerers Tokyo Kickoff – October 10, 2025 — 2025-10-10 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_gicqjGFQ-wc

### [AI Music Video in 5 minutes](https://london.aitinkerers.org/talks/rsvp_-YlHX_A6hjI)

I will go from idea to a completed minute long music video in 5 minutes using an AI video production platform I'm working on: Story Machine (https://storymachine.ai). Here is my latest speedrun which clocks in at 8 minutes: https://youtu.be/68X1H2am9D8 As you can see from the video I can talk and work at the same time.

- Event context: AI Tinkerers x MongoDB - Demopalooza — 2025-10-07 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_-YlHX_A6hjI

### [Turning Spreadsheets AI Native](https://london.aitinkerers.org/talks/rsvp_M86M8841Uus)

I will be presenting a spreadsheet application with AI native features. Think of it like if Lovable and Excel had a baby. The demo will revolve around creating financials depicting if the business models of Lovable and Cursor can sustain over time with unlimited messages.

- Event context: AI Tinkerers x MongoDB - Demopalooza — 2025-10-07 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_M86M8841Uus

### [Lightning talk on 1) google jules GA, 2) z.ai GLM-46 coding model](https://seattle.aitinkerers.org/talks/rsvp_vCSmDNFhd7U)

lightning talk on 1) google jules GA - prompt to PR in github 2) z.ai GLM-46 coding model in Claude code

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — October 6, 2025 — 2025-10-07 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_vCSmDNFhd7U

### [Building Working Code Live: Documentation-First AI Development](https://seattle.aitinkerers.org/talks/rsvp_ctw_B2iINIQ)

I'll demonstrate the spawn-experiments methodology - a systematic approach to AI-assisted code generation using documentation-first prompting with Claude models (Sonnet 4 and Opus) through Claude Code's Task tool. Live demo: building a functional CLI tool from scratch in real-time, showing how structured specifications generate better AI outputs than vague prompts. Based on spawn-experiments research comparing 4 AI development methodologies across multiple experiments, findings show methodology significantly impacts AI development patterns and outcomes, with trade-offs between development speed and code quality. You'll see the actual "code-like prompting" techniques that treat prompts as executable specifications, parallel code generation across multiple threads, and comprehensive quality control including syntax validation, automated test generation, and real-time error handling.

- Event context: AI Tinkerers Seattle September Meetup — September 30, 2025 — 2025-10-01 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_ctw_B2iINIQ

### [Orquestación y especialización de agentes código](https://medellin.aitinkerers.org/talks/rsvp_53m46l-k0-k)

Un camino en como de manera personal orquestro reviso y especializo agentes para ser 10x developer.

- Event context: AI Tinkerers Medellín #16 - Lean Solutions Group - 25 de Septiembre — 2025-09-26 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_53m46l-k0-k

### [Copywriting y redacción creativa. No es lo que preguntas, es con quién conversas.](https://manizales.aitinkerers.org/talks/rsvp_hSaAP7Bb4fU)

Cómo uso 4 modelos de IA (Chat GPT, Gemini, Claude y Perplexity) como mis partners creativos para desarrollar mis tareas del día a día.

- Event context: 🚀 ¡Octavo Encuentro de AI Tinkerers Manizales! — 2025-09-24 — Manizales
- Public talk page: https://manizales.aitinkerers.org/talks/rsvp_hSaAP7Bb4fU

### [How to remove yourself from the LLM design loop](https://nyc.aitinkerers.org/talks/rsvp_XfntTaAG5tQ)

I'll show the code and run through TextEvolve, which I built to automate the iteration loop that someone performs when they're working on some LLM-based applicaiton or system.

- Event context: Demopalooza @ The Javits Center with MongoDB — 2025-09-17 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_XfntTaAG5tQ

### [Citation - AI Reporting Automation](https://brisbane.aitinkerers.org/talks/rsvp_JLUvlImoyRI)

Citation is an AI-powered platform designed to automate and accelerate report writing, starting with civil engineering. It takes on the repetitive, time-consuming tasks—like data collection, formatting, image markup, and table creation—so engineers can focus on analysis and decision-making.

- Event context: AI Tinkerers – Brisbane Inaugural Meetup · 11 September 2025 — 2025-09-11 — Brisbane
- Public talk page: https://brisbane.aitinkerers.org/talks/rsvp_JLUvlImoyRI

### [SourceWizard - Setup Wizard for dev tools and libraries](https://sf.aitinkerers.org/talks/rsvp_5BmRomv4MSU)

I'm building a specialized coding agent for integrating dev tools and libraries into the codebase. The agent is designed to run as a subagent via MCP and it should follow a specialized instruction that will detect the repo and integrate the library into the codebase. The demo I can present is setting up a simple web app repo and integrating stuff like auth live.

- Event context: Coding Agents Stack Share — 2025-09-11 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_5BmRomv4MSU

### [Agentic Claude code using bmad-method](https://seattle.aitinkerers.org/talks/rsvp_Od0YHoOD1oc)

Agentic development in Claude code cli using bmad-method developed by Brian https://github.com/bmadcode. Dave will demo bmad method of analyst->product brief->prd->architecture->user stories->dev implementation all in Claude code agents.

- Event context: AI Dev Tool Track — Seattle Meetup (Sept 8, 2025) — 2025-09-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_Od0YHoOD1oc

### [AI Slop Factory: One Prompt to Infinite Brainrot](https://london.aitinkerers.org/talks/rsvp_frOmFuaMHfU)

We’re living in an era where content never sleeps — and neither do the AIs cranking it out. In this demo, I’ll show how I built a fully automated AI “slop factory” that turns a single input (even a dry Wikipedia page) into a fully fledged TikTok-style short, complete with: Scriptwriting Scene planning and “direction” Character creation & visual generation Voiceovers with AI personalities Final cut and transitions All automated. I’ll run a real-time demo — starting from a random Wikipedia page and ending with a finished short-form video ready to feed the endless scroll. Along the way, I’ll dive deep into the pipeline’s architecture, my code orchestration in Python, API juggling, and the hacks I used to keep latency and unit cost low.

- Event context: AI Tinkerers London Meetup - 28th August 2025 — 2025-08-28 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_frOmFuaMHfU

### [What I Built With The Mullet Method: One Flask App, Multiple Sites](https://seattle.aitinkerers.org/talks/rsvp_fnZ5nydIp_k)

The Mullet Method: Business rules in the front, AI party in the back. I'll show you three completely different websites (see URLs below), then reveal they're all running on a single Flask backend on a $20/month server. The secret? Use AI in the back to create deterministic, ordinary websites up front - no need to run the AI meter for users. This is pure show-and-tell: live sites → single backend reveal → development theory → architectural patterns. Simple, clean, and focused on the core insight that makes it all work. What I'll show: - Three completely different live websites - Single Flask backend reveal (one process, one database) - Development theory: AI in back → deterministic sites up front - Key architectural patterns that make it work - Why this approach beats running AI for every user request Key insights: - Use AI during development, not during user requests - Database-driven routing eliminates hardcoded patterns - Single codebase, infinite customization possibilities - Super low-cost scaling without AI infrastructure overhead

- Event context: Summer on the Lake - August Tinkerers Meetup! (Demos, Food, Friends) — 2025-08-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_fnZ5nydIp_k

## Related Technologies

- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 220 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [Sonnet](https://aitinkerers.org/technologies/sonnet) ([Markdown](https://aitinkerers.org/technologies/sonnet.md)) — 25 public demos
- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) — 74 public demos
- [GPT](https://aitinkerers.org/technologies/gpt) ([Markdown](https://aitinkerers.org/technologies/gpt.md)) — 26 public demos
- [GPT-4o](https://aitinkerers.org/technologies/gpt-4o) ([Markdown](https://aitinkerers.org/technologies/gpt-4o.md)) — 57 public demos

## More Results

- Previous: https://aitinkerers.org/technologies/claude.md?page=4
- Next: https://aitinkerers.org/technologies/claude.md?page=6