# Anthropic Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/anthropic
> Markdown URL: https://aitinkerers.org/technologies/anthropic.md
> Technology record last updated: 2026-02-22T17:59:34Z
> Generated: 2026-09-20T18:43:51Z

Anthropic is a frontier AI safety and research company, developing the Claude family of large language models (LLMs) via its Constitutional AI framework.

Anthropic is an AI safety and research company, founded in 2021 by former OpenAI executives Dario and Daniela Amodei, and structured as a Public Benefit Corporation (PBC) . The core mission is building reliable, steerable AI systems, with a focus on interpretability and long-term alignment . Its flagship product is the Claude family of LLMs, which are highly capable models designed for complex reasoning and coding tasks . A key technical innovation is Constitutional AI (CAI), a training method that aligns the models with a set of ethical principles to ensure helpful, harmless, and honest outputs . The company has secured significant backing, including up to $4 billion from Amazon and a $2 billion commitment from Google .

- Official technology site: https://www.anthropic.com
- Public AI Tinkerers demos and talks: 36
- Result page: 1 of 2

## Recent Public Talks and Demos

### [Watch 1 hour highly techincal YouTubes in 5 minutes with AI!](https://seattle.aitinkerers.org/talks/rsvp_cjwx88z4AkE)

AG is an agent that watches YouTube podcasts for you so you know which ones to really dig into. With AG, see in 5 minutes a summary of the YouTube, key quotes, see key blackboard / slide / code sections, jump around key passages, and decide if you should spend the full time on the video. Break down highly techincal episodes from Dwarkesh, Lenny, AI Engineer, and more!

- Event context: AI Tinkerers Seattle Summer Bash — 2026-07-29 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_cjwx88z4AkE

### [Six Claude Agents and a Trust Boundary: A Clinical Co-Pilot](https://montreal.aitinkerers.org/talks/rsvp_4qzrWmd9MiM)

A multi-agent clinical co-pilot that runs six specialist Claude agents in parallel on top of a PHI-safe pipeline : every LLM call sees only de-identified text, and re-identification happens server-side after the model returns. Live, I'll load a synthetic 68F new-AFib case where the cardiology plan proposes amiodarone for a patient already on warfarin. The Triage, Differential, Pharmacy, Guidelines, Bias-Check, and Communication agents stream into six panels via asyncio.gather. The Pharmacy agent flags the warfarin–amiodarone CYP2C9/3A4 interaction; Bias-Check independently flags anchoring on rhythm control; the orchestrator detects the cross-agent convergence and elevates it as a high-severity flag. I'll then toggle the Safety Gate off so the audience sees raw PHI hit the LLM and get echoed back — then flip it on and show the audit log assertion (zero raw PHI, only counts + SHA-256 hashes). I'll show the FastAPI/WebSocket code that fans out the agents, the trust-boundary diagram, the structured-field redactor, the live audit log tail, and the keystone pytest (test_pharmacy_catches_warfarin_amiodarone). Repo, logs, and 35/35 passing tests are all open.

- Event context: AI Tinkerers Montreal - May Demo Meetup @ Ubisoft — 2026-05-26 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_4qzrWmd9MiM

### [Boomerang: why I built my own agentic browser infra](https://cologne.aitinkerers.org/talks/rsvp_XEuIAGK7fdA)

I built a replacement for browserbase, notte, firecrawl and the many other agentic web-use browser infra providers. I walk through the story of trying out various systems, then deciding to build my own, the trials and tribulations of battling cloudflare, how agents go wrong, and more.

- Event context: AI Tinkerers Cologne 4: Live Technical Demos — 2026-04-16 — Cologne
- Public talk page: https://cologne.aitinkerers.org/talks/rsvp_XEuIAGK7fdA

### [The Layer Between You and the Model](https://nashville.aitinkerers.org/talks/rsvp_vfOwHHG2DJ4)

When you send a message to an LLM, what happens before the model sees it? Something has to load context, decide what tools are available, shape what the model can and can't do. That's the harness. Everyone building agents has one, most people just don't call it that. This is a code walkthrough of a harness I've been building. I'll show what's actually in that layer: context loading, command constraints, persona switching, conversation branching. Not polished or a product pitch. Just the guts of what sits between me and the model. If you've been building something similar and didn't know the name for it, find me afterwards.

- Event context: AI Tinkerers Nashville – Software Development in the Age of AI — 2026-03-25 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_vfOwHHG2DJ4

### [One to Many - from OpenClaw to organisations of ambient agents](https://berlin.aitinkerers.org/talks/rsvp_JNrCPzSFCMc)

Over the last 2 weeks, I went from n8n, to openclaw, to now paperclipAI, where I run a team of 5 ambient agents working on shared goals, with a common task manager. All of this on the side of our main project, building a multi-agent system for local businesses. I'll share a walkthrough of what the organisation of agents have built over the last week, and talk about where they have failed, and what is still needed in harness development for multi-agent systems.

- Event context: AI Tinkerers Berlin Meetup - March 11, 2026 — 2026-03-11 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_JNrCPzSFCMc

### [Cloud-Hosted, Multi-Agent Workspaces (or: Gas Town in the Sky)](https://seattle.aitinkerers.org/talks/rsvp_mVgQoXtoVzE)

A live walkthrough of a multi-agent software development loop in the cloud: Head of Engineering (agent) receives a request from Discord, writes the code, opens a PR, goes to Head of Infra to deploy, and then finally hands the change to Head of QA for review and merge, all without any intervention from the user. The presentation will cover how I created the best way to make easy, configurable, multi-agent workspaces without the infrastructure hassle or security risks of self-hosted solutions. This includes setting up persistent, isolated workspaces, configurable prompts and variables, cross-agent messaging, and deep session analytics, all managed through a custom-built MCP server and my local Claude Code. In addition, throughout the demo I'll share exciting developments I've seen so far in terms of emergent behavior, cross-agent coordination, and workspace management.

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — March 9th, 2026 — 2026-03-10 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_mVgQoXtoVzE

### [Finance Agent Evals - How to implement evals to a financial agents using A2A protocol](https://bogota.aitinkerers.org/talks/rsvp_5aCGjZcNjqA)

I’ll be presenting the project developed during the 'Papers' program, where we built an Analyst-Judge agent system via A2A. We will see how the Judge system initiates an evaluation scenario and engages the Financial Analyst agent. This agent asynchronously answers questions using different reasoning models, passing the results back to the Judge to compare the responses across all questions and models.

- Event context: AI Tinkerers Bogotá: El Primer Meetup de 2026 — 2026-02-26 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_5aCGjZcNjqA

### [What's behind OpenClaw - The innards of my AI assistant!](https://toronto.aitinkerers.org/talks/rsvp_5P5cU8gF4qQ)

OpenClaw has become my AI assistant. I've been using it daily, over the past few *weeks* (so there's long history!). In this session, I’ll walk through how it’s actually built at a high-level and dig deep into how it works behind the scenes (i.e. the file system). I'll start with a brief overview of my setup: architecture, orchestration layer, memory structure, and the tooling stack that makes it reliable. In the background a long running task will hopefully complete! Then I'll walk through the filesystem and the two core capabilities: multi-step task orchestration and automated daily news synthesis. This talk is a practical look at what a persistent AI assistant looks like under the hood. I hope to be able to do this all on a Raspberry Pi, but mine is super old and doesn't have wifi, so I might have to buy a new one if my talk gets accepted :)

- Event context: AI Tinkerers Toronto - February 2026 @ Cohere! — 2026-02-26 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_5P5cU8gF4qQ

### [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

### [The Secret to Stunning UI: How AI Helped Me Design and Ship InkyCards in 7 Days](https://cologne.aitinkerers.org/talks/rsvp_EmnVHJCgoK0)

In just one week, I took InkyCard, a conversational language learning app from an idea in my head to a production-ready product. This session isn’t just about generating code; it’s about using AI to solve the "Developer Design Gap" and build a brand with a soul. I will demo the InkyCards workflow, focusing on: The Design Extraction Hack: How to feed UI inspiration (from sites like Dribbble) into LLMs to generate custom design systems, ensuring your app doesn’t look "AI-generated." Building the "Soul": Using Gemini Nano and Higgsfield to create a unique app mascot and custom iconography, overcoming creative blocks and building an emotional connection with users. Production Speed-running: A look at the "Plan-First" prompting strategy and context management that allowed me to build complex features—like real-time AI conversations (Firebase Vertex AI) and "Tap-to-Learn" flashcard generation—without losing code quality. Technical Deep-Dive: State Management & AI: How to use Claude and AntiGravity to scaffold architecture that stays clean as the project grows. The Fresh Convo Rule: My framework for managing LLM context to prevent "code rot" and quality degradation.

- Event context: AI Tinkerers Cologne #2: Let's Build. — 2026-01-21 — Cologne
- Public talk page: https://cologne.aitinkerers.org/talks/rsvp_EmnVHJCgoK0

### [Practical LLM Integration: Lessons from Building a SEC Filing Analysis Project](https://houston.aitinkerers.org/talks/rsvp_Vt9RZstb_VY)

A live coding demo walking through an LLM-powered document analysis system. I'll run the pipeline live and show the code that makes it work. Using regex and rule-based filters to reduce LLM API costs by 80%+ Extracting structured data from unstructured documents with Claude Implementing semantic caching with Qdrant to avoid redundant API calls Tracking LLM costs and latency with Langfuse

- Event context: AI Tinkerers Houston: Working Code, Live Demos, and Architectures for 2026 — 2026-01-13 — Houston
- Public talk page: https://houston.aitinkerers.org/talks/rsvp_Vt9RZstb_VY

### [From Prompt to Product: Exploring AI-Assisted Hardware Design](https://sydney.aitinkerers.org/talks/rsvp_zcnB5Ar74Sk)

A walkthrough of an AI system designed to take natural language and generate manufacturable hardware outputs. Built at a recent hackathon. I'll show the vision, what we actually got working (LLM-generated CAD models), what we hardcoded for the demo, and the honest gaps between the dream and current reality. Lessons on scoping AI hardware projects and where the real technical challenges lie.

- Event context: Trust and Security in AI - Sydney Demo Night — 2025-12-11 — Sydney
- Public talk page: https://sydney.aitinkerers.org/talks/rsvp_zcnB5Ar74Sk

### [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

### [How to lose in fantasy football (A tutorial for programmers)](https://nyc.aitinkerers.org/talks/rsvp_wIsF1SMces8)

I'll be presenting a full-stack MCP application that enables Claude to autonomously manage ESPN Fantasy Football teams through natural conversation. This system demonstrates advanced MCP patterns including real-time tool execution monitoring, optimized context management (achieving 77% faster response times through static week context injection), and comprehensive API integration (36 specialized tools spanning roster management, trade proposals, waiver claims, and live player analytics). The live demo will showcase Claude analyzing rosters, making lineup decisions, and executing transactions against real ESPN leagues—illustrating the end-to-end workflow from user query to API write operations.

- Event context: NYC October Demo Day — 2025-10-02 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_wIsF1SMces8

### [CodeRabbit - Leading in AI Code Review, helping you to ship better quality code...faster and safer!](https://atlanta.aitinkerers.org/talks/rsvp_S7jWzuc5W5s)

CodeRabbit is the industry's leading AI Code Review platform that helps software developers automate the first pass of code reviews and catch bugs that manual reviews miss. With CodeRabbit you can merge PRs in 50% less time, with 50% fewer bugs before they hit production.

- Event context: AI Tinkerers Atlanta Meetup – August 28, 2025 — 2025-08-28 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_S7jWzuc5W5s

### [ValueSpotter](https://nyc.aitinkerers.org/talks/rsvp_N_ruuSgF2LY)

We built ValueSpotter to help small businesses, and their financial partners. Insurance adjuster, bankers, lawyers, and auctioneers spend countless hours manually cataloging and valuing assets. That inefficiency drives up costs and delays recoveries. That’s why we built ValueSpotter. In just seconds, our platform uses computer vision to identify items from a simple walk through video. The items are valued using AI services with grounded results providing a low-high range for each item with primary source links.

- Event context: AI Tinkerers August Demo Day ft. Auth0 and Comet. Demo what you've built! — 2025-08-26 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_N_ruuSgF2LY

### [Building an Agentic AI System That Replaces Digital Ad Agencies: Multi-Stage LLM Architecture with Recursive Planning, Multimodal Analysis, and Novel Optimization Strategies](https://orange-county.aitinkerers.org/talks/rsvp_y1ihXS44YRA)

I'll demonstrate how I built AdRes, a sophisticated agentic AI system that eliminates digital ad agencies through advanced multi-stage Lambda architecture. The demo will showcase our recursive planning system that uses Anthropic Claude 3.5 Sonnet with custom fine-tuned prompts, vector embeddings for campaign similarity matching, and a multimodal creative analysis pipeline using OpenCV and computer vision. I'll walk through the code that powers our unified context system, agentic workflow with tool selection and self-correction, and real-time campaign optimization engine that processes complex multi-source data analysis.

- Event context: AI Tinkerers - Orange County Meetup- Thursday July 31st 2025 — 2025-08-01 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_y1ihXS44YRA

### [A "course" as an MCP Server](https://sf.aitinkerers.org/talks/rsvp_fx3PTLW2j78)

We wanted to build a course for new Mastra devs to get started quickly. However, we knew videos would go out of date and be more difficult to maintain. We decided to launch our "course" as an MCP server. This way your coding agent actually teaches the course content to you and can help you write the code. We think this is a really interactive way to learn. Using an editor with MCP support (such as Cursor, Windsurf, or VSCode), your code agent will call the appropriate MCP tools which will return context for the agent. This context tries to instruct the agent that it should be teaching you the content, not just doing the work for you. We will walk through the code of how it works, what limitations we found, and how we are aiming to further improve this "course."

- Event context: AI Tinkerers - Advanced MCP Showcase — 2025-06-19 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_fx3PTLW2j78

### [The internal infrastructure (datasets, backtests, scorecards) we built to create our AI investigation system](https://london.aitinkerers.org/talks/rsvp_bnGsgK9KQeA)

I've been part of the AI team at incident.io from its inception, working on an AI product to automate the investigations into incidents - we're nearing customer release. As part of this, and particularly at the beginning, we had an immensely frustrating time working to get this thing built - we'd make a change one place, and performance would fall off a cliff in another. We then rearchitected everything from the ground up around our backtesting system - which I'd like to demo. This became not just a tool to check our working - but an active accelerant for development, something the team has come to trust, I'd like to show it off.

- Event context: AI Tinkerers London - May Meetup — 2025-05-27 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_bnGsgK9KQeA

### [The AI Agent Feedback Loop](https://toronto.aitinkerers.org/talks/rsvp_Do816urC66Y)

How Ada creates a feedback loop for its AI Agents to get better over time with more usage.

- Event context: AI Tinkerers Toronto - May 2025 Meetup: AGENTS at Ada — 2025-05-22 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_Do816urC66Y

### [Zero Trust-Proofing and Containerizing AI Agents for Enterprise Deployments](https://toronto.aitinkerers.org/talks/rsvp_9fibOugPX6M)

Identity Machines' SDK and CLI tool for AI agent developers, the Iron Book API for agentic multi-vector security, compliance, and privacy testing (vulnerability scanning with Claude Sonnet 3.7 on Bedrock and OSV, sentiment analysis, security scoring, foundational model and behavioral testing per OWASP LLM Top 10, cryptographic attestation, SBOM creation), AI agent packaging into an OCI-container deployed on EKS, and ongoing work with Google on trust-related enhancements for the A2A protocol (the Iron Vow mechanics).

- Event context: AI Tinkerers Toronto - May 2025 Meetup: AGENTS at Ada — 2025-05-22 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_9fibOugPX6M

### [Code Fixer](https://santiago.aitinkerers.org/talks/rsvp_EpwO1i06ilM)

El agente de IA "Code Fixer" es un resultado de Globant Enterprise AI y su capacidad para mejorar la eficiencia y efectividad en múltiples industrias, en este caso, el desarrollo de software, a través de agentes de IA personalizados. Este agente de IA, que ya está siendo utilizado por Globers en todo el mundo, es fundamental en el ciclo de vida del desarrollo de software (SDLC), donde la optimización del proceso de depuración puede aumentar significativamente la productividad.

- Event context: AI Tinkerers-Santiago / Capitulo #2 — 2025-03-27 — Santiago
- Public talk page: https://santiago.aitinkerers.org/talks/rsvp_EpwO1i06ilM

### [agents.txt](https://dublin.aitinkerers.org/talks/rsvp_X3vSJuK81Ss)

The MCP protocol paves the way for creating Business to Agent APIs. However, Agents currently have no straightforward method to locate these MCP endpoints. While many startups are developing a marketplace for MCP APIs, we advocate for an open approach that allows everyone to publish and be discovered without relying on third-party marketplaces.

- Event context: AI Tinkerers Dublin (March) — 2025-03-26 — Dublin
- Public talk page: https://dublin.aitinkerers.org/talks/rsvp_X3vSJuK81Ss

### [AI Junk Removal Workflow Hack](https://montreal.aitinkerers.org/talks/rsvp_pZb_wImr5iE)

In this talk, Marie Pelletier from Kanastruk shares how they integrated AI and cloud technologies to enhance junk removal and recycling processes, offering practical insights on automating workflows and improving customer interactions.

- Event context: AI Tinkerers Montreal - March 2025 Meetup at Shopify — 2025-03-12 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_pZb_wImr5iE

## Related Technologies

- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Sonnet](https://aitinkerers.org/technologies/sonnet) ([Markdown](https://aitinkerers.org/technologies/sonnet.md)) — 25 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [AGENTS](https://aitinkerers.org/technologies/agents) ([Markdown](https://aitinkerers.org/technologies/agents.md)) — 20 public demos
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [AWS Bedrock](https://aitinkerers.org/technologies/aws-bedrock) ([Markdown](https://aitinkerers.org/technologies/aws-bedrock.md)) — 9 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [Playwright](https://aitinkerers.org/technologies/playwright) ([Markdown](https://aitinkerers.org/technologies/playwright.md)) — 32 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Firebase](https://aitinkerers.org/technologies/firebase) ([Markdown](https://aitinkerers.org/technologies/firebase.md)) — 23 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Linear](https://aitinkerers.org/technologies/linear) ([Markdown](https://aitinkerers.org/technologies/linear.md)) — 9 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [n8n](https://aitinkerers.org/technologies/n8n) ([Markdown](https://aitinkerers.org/technologies/n8n.md)) — 45 public demos

## More Results

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