# Code Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/code
> Markdown URL: https://aitinkerers.org/technologies/code.md
> Technology record last updated: 2026-03-10T01:34:17Z
> Generated: 2026-09-20T17:49:20Z

Code.org is the premier global nonprofit platform for computer science education, reaching over 80 million students and 2 million teachers worldwide.

Code.org leads the charge in democratizing computer science through its comprehensive K-12 curriculum and the viral Hour of Code initiative. The platform supports 55 million student accounts and provides high-quality, free resources to help learners master foundational logic, JavaScript, and AI integration. By partnering with major school districts and global governments, Code.org has successfully integrated computer science into the core academic experience for millions of underrepresented students.

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

## Recent Public Talks and Demos

### [Robot Picks Grapes Based on Spatial World Model](https://seattle.aitinkerers.org/talks/rsvp_hwjgpFnwm2M)

We built a new model that is based on the human brain. Right now it can navigate and reason to play Pac Man but we are working on connecting it to a robot and having it pick grapes.

- Event context: AI Tinkerers Seattle Summer Bash — 2026-07-29 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_hwjgpFnwm2M

### [Harness for ARC-AGI-3](https://zurich.aitinkerers.org/talks/rsvp_DuQxaJngv4g)

At Tufa Labs, we built a top-performing harness for the ARC-AGI-3 challenge. We will be releasing it open-source and would like to present it at the event.

- Event context: AI Tinkerers Zürich: July Build Night with Swisscom Ventures — 2026-07-01 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_DuQxaJngv4g

### [Orquestração multi-agente em n8n: sub-workflows virando tools dinâmicas](https://curitiba.aitinkerers.org/talks/rsvp_F61Msr-AenQ)

Construí um sistema multi-agente que opera o assistente de WhatsApp de uma marca brasileira de suplementos "clean label" com catálogo de 20+ SKUs em 8 categorias (sono, estética, emagrecimento, imunidade, saúde feminina 40+, entre outros) e dois canais ativos de WhatsApp para quiosque físico e delivery. O problema real: volume de perguntas simultâneas sobre produtos específicos (composição, indicação, contraindicação, disponibilidade), mix de intenções radicalmente diferentes: consumidora final comprando pela primeira vez, cliente em recompra, nutricionista prescrevendo e a necessidade de escalar atendimento sem perder o tom consultivo que a marca construiu. Em vez de LangGraph ou CrewAI, usei n8n como orquestrador e Claude como motor de decisão. Mensagens chegam via Evolution API num webhook do n8n; o Claude classifica a intenção (tool use) e roteia para a tool certa; mas cada "tool" é um sub-workflow n8n separado, chamado via Execute Workflow. Cada sub-workflow tem seu próprio prompt, seu próprio acesso ao Supabase (RAG sobre o catálogo completo com pgvector, histórico de pedidos, perfil do cliente) e seu próprio guard-rail. Quando a confiança do Claude cai especialmente em perguntas clínicas sobre contraindicações, o agente passa para humano via Chatwoot. Tudo self-hosted na Hetzner (Docker Swarm + Traefik). Na demo ao vivo mostro: uma mensagem real chegando no WhatsApp, o painel do n8n executando nó a nó, o sub-workflow correto ativando como tool, e os logs no Supabase. Compartilho o padrão "sub-workflow-as-tool" e o JSON exportado.

- Event context: AI Tinkerers Curitiba: Evento Inaugural — 2026-06-10 — Curitiba
- Public talk page: https://curitiba.aitinkerers.org/talks/rsvp_F61Msr-AenQ

### [AI-Assisted WordPress Vulnerability Hunting: From Plugin Code to Verified Findings](https://dallas-fort-worth.aitinkerers.org/talks/rsvp_ryp2dvTokTM)

I built a repeatable AI-assisted workflow for finding and validating vulnerabilities in WordPress plugins. In the demo, I’ll show the process end-to-end: selecting a plugin, launching a controlled test environment with a custom harness, then using Codex and a tailored AGENTS.md to scan the source, trace risky execution paths, validate the finding with a proof of concept, and generate a disclosure-ready report.

- Event context: AI Tinkerers Dallas-Fort Worth: June Meetup with Rasa — 2026-06-04 — Dallas Fort Worth
- Public talk page: https://dallas-fort-worth.aitinkerers.org/talks/rsvp_ryp2dvTokTM

### [What Is Your Coding Agent Actually Searching?](https://columbus.aitinkerers.org/talks/rsvp_t4IMPq7lJnc)

I built SearchBench, a harness for running controlled evaluation rounds over coding-agent search behavior. A SearchBench round takes real bug-localization tasks, gives an agent access to a repository, and checks whether it found the files that were actually changed in the human fix. The harness compares an incumbent search strategy against one or more challengers, then writes a static evidence bundle with exact-hit, hop-distance, token-usage, failure, and report artifacts. For the demo, I’ll run a small live ablation round over three cases. I’ll reuse cached Bash/native-search results as the incumbent, then run a few IC challenger policies in parallel. The question is: when IC succeeds or fails, was the important factor anchor quality or graph lookahead? I’ll show the actual workflow: preflight cost prediction, run planning, parallel execution, actual spend, cost-prediction error, generated bundle artifacts, and a short report explaining what changed. One thing I want to show explicitly is how much information the harness can derive from a small, bounded run: exact hits, hop distance, token usage, failure modes, and the next optimization target.

- Event context: AI Tinkerers - Columbus June Meetup — 2026-06-01 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_t4IMPq7lJnc

### [Singularity Machines - Fast Software Services | Sovereign Compute Systems | Agentic Automation](https://boston.aitinkerers.org/talks/rsvp_tHXNfsOaH-E)

Maximum control, minimum abstraction... Over time, the economic center of software moved away from owned machines and into controlled services. Singularity Machines are a return to first principles: start with hardware, build upward locally, and restore real ownership of computation to the person using it. This offline, privacy-first, low-level stack gives you total ownership and full autonomy inside a closed-source system, with granular control down to the hardware by default and intentional, transparent online access only when necessary—so you can build, operate, and communicate on your own terms without unnecessary external dependencies or exposure. And of course, your personal local AI controls the whole damn thing for you.

- Event context: AI Tinkerers Boston: a16z BOS Tech Week 2026 Edition — 2026-05-26 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_tHXNfsOaH-E

### [Stop Cloud Waste: AI Checks Costs Before Deploy in AWS](https://raleigh.aitinkerers.org/talks/rsvp_MX33E7LzJoM)

Ever had your IT team spin up cloud resources that cost way more than expected? I've developed an AI-powered assistant that reviews cloud infrastructure plans before deployment - like having a financial advisor check your shopping cart before checkout. Instead of finding out you spent $10,000 after the fact, teams get instant feedback: "This database is oversized for a dev environment - similar projects in your company use something 5x cheaper" or "You forgot the required cost tags that finance needs for billing." In this 5-minute demo, I'll show: Upload a cloud infrastructure plan (Terraform file) AI analyzes it against your company's cost policies written in plain English Get a breakdown: estimated monthly cost, policy violations, and smart suggestions See how it learns from your organization's past projects to give better recommendations The magic? It understands context - not just "this violates rule 247" but "this looks expensive for what you're building, here's what similar teams did."

- Event context: AI Tinkerers Raleigh Meetup — February 11, 2026 — 2026-02-11 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_MX33E7LzJoM

### [From Chatbots to Sandboxes: Why AI Needs an Execution Layer](https://singapore.aitinkerers.org/talks/rsvp_5A7Kmd5lcps)

The audience at this event is already fluent in AI hype. This talk is designed to cut through that by focusing on what actually works in practice: shipping AI systems that can reliably execute tasks in the real world. Founders, operators, and developers experimenting with agents or automations often hit the same wall. Chat-based tools are impressive, but they fall apart when tasks require memory, state, files, or time. By sharing lessons from building Mogra’s persistent sandbox, this talk gives attendees a clearer mental model for where agentic AI breaks today and how to design around those limitations.

- Event context: AI Tinkerers - The Age of AI & Infrastructure (Singapore) — 2026-02-11 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_5A7Kmd5lcps

### [Teaching Generative AI to K-12 Students](https://seattle.aitinkerers.org/talks/rsvp_hH1rzLAN0ak)

In this demo, I'll showcase the work we've been doing at Code.org, creating a Generative AI curriculum for students (due for release end of Oct). The demo will show how students can use Code.org to explore SLMs (Mistral), select different fine-tuned models, learn about system prompts, temperature, model cards, RAG, and other aspects of Generative AI. I'll also cover how we've implemented a "guard LLM" to ensure a safe student experience in the classroom.

- Event context: AI Tinkerers - Seattle - October 2024 Meetup — 2024-10-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_hH1rzLAN0ak

## Related Technologies

- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [AGENTS](https://aitinkerers.org/technologies/agents) ([Markdown](https://aitinkerers.org/technologies/agents.md)) — 20 public demos
- [AI](https://aitinkerers.org/technologies/ai) ([Markdown](https://aitinkerers.org/technologies/ai.md)) — 55 public demos
- [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
- [ARC-AGI-3](https://aitinkerers.org/technologies/arc-agi-3) ([Markdown](https://aitinkerers.org/technologies/arc-agi-3.md)) — 1 public demo
- [Assembly Language](https://aitinkerers.org/technologies/assembly-language) ([Markdown](https://aitinkerers.org/technologies/assembly-language.md)) — 1 public demo
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [Base](https://aitinkerers.org/technologies/base) ([Markdown](https://aitinkerers.org/technologies/base.md)) — 2 public demos
- [bash](https://aitinkerers.org/technologies/bash) ([Markdown](https://aitinkerers.org/technologies/bash.md)) — 12 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [Browser automation](https://aitinkerers.org/technologies/browser-automation) ([Markdown](https://aitinkerers.org/technologies/browser-automation.md)) — 3 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 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