# OpenAI GPT Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/openai-gpt
> Markdown URL: https://aitinkerers.org/technologies/openai-gpt.md
> Technology record last updated: 2026-02-26T19:01:49Z
> Generated: 2026-09-21T04:44:53Z

OpenAI's Generative Pre-trained Transformer (GPT) is the flagship series of multimodal AI models, defining the state-of-the-art for agentic task performance and professional knowledge work.

The Generative Pre-trained Transformer (GPT) is OpenAI's foundational model series: a family of large multimodal models (LMMs) that includes the current frontier model, GPT-5.2, and the efficient GPT-4o. These models are not just chatbots; they are engineered for complex, real-world tasks, demonstrating superior performance in areas like code generation, long-context understanding (e.g., GPT-4 Turbo's 128,000-token window), and advanced agentic tool-calling. GPT systems power applications like ChatGPT, delivering human-like, structured responses for everything from creative writing to high-value professional tasks (building spreadsheets, drafting presentations, and executing multi-step projects).

- Official technology site: https://openai.com/
- Public AI Tinkerers demos and talks: 3
- Result page: 1 of 1

## Recent Public Talks and Demos

### [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

### [ibaAgent: Agentic time-series analysis.](https://nurnberg.aitinkerers.org/talks/rsvp_DcXjk1ibxVU)

I developed an agentic system using LangGraph to analyze high-resolution time-series data via natural language. Since high-resolution data is too token-intensive for LLMs, the agent operates "blind" by dynamically writing and executing Python analysis scripts to process data locally. This is supported by a specialized memory architecture that allows the agent to iteratively build an internal map of undocumented, messy data stores, and a rigorous Langfuse experiment pipeline used to tune hyperparameters and prompts for predictable reasoning and precise tool use. Currently transitioning from proof-of-concept to product at iba AG, my demo will showcase LangGraph traces of the agent’s execution and its self-correction within the Python environment. I will also highlight our Langfuse evaluation workflow and how the memory layer enables the agent to navigate complex data structures over time. I’m looking to exchange ideas with fellow tinkerers specifically on memory persistence, planning strategies, and robust evaluation for agentic workflows.

- Event context: AI Tinkerers Nürnberg: April Meetup — 2026-04-22 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_DcXjk1ibxVU

### [How We Built an AI-Native Business Factory Anyone Can Run From Their Phone. From Phone to Empire in Hours, Not Years! English Is the New Interface.](https://san-diego.aitinkerers.org/talks/rsvp_GvNDHEXsW_s)

In 2026 the bottleneck isn’t coding—it’s execution. This talk shows how we built NetShow IQ1, an AI-native business factory designed for real operators: the small business owner who barely does email, the busy parent, the non-technical founder with a clear idea. I’ll walk through how a plain-English idea becomes a complete business stack in one orchestrated run—validated offer, branded web presence, working product/service flow, marketing assets, and operational agents for sales/support/admin—plus the practical engineering discoveries that made it reliable: agent handoffs, “agents test agents” quality gates, and cost/safety controls so normal people can run it without becoming technical.

- Event context: AI Tinkerers San Diego: January Meetup — 2026-01-23 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_GvNDHEXsW_s

## Related Technologies

- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Agent](https://aitinkerers.org/technologies/agent) ([Markdown](https://aitinkerers.org/technologies/agent.md)) — 12 public demos
- [Code](https://aitinkerers.org/technologies/code) ([Markdown](https://aitinkerers.org/technologies/code.md)) — 9 public demos
- [debounce de mensagens](https://aitinkerers.org/technologies/debounce-de-mensagens) ([Markdown](https://aitinkerers.org/technologies/debounce-de-mensagens.md)) — 1 public demo
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Embeddings](https://aitinkerers.org/technologies/embeddings) ([Markdown](https://aitinkerers.org/technologies/embeddings.md)) — 22 public demos
- [Evolution API](https://aitinkerers.org/technologies/evolution-api) ([Markdown](https://aitinkerers.org/technologies/evolution-api.md)) — 2 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [JavaScript](https://aitinkerers.org/technologies/javascript) ([Markdown](https://aitinkerers.org/technologies/javascript.md)) — 40 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Langfuse](https://aitinkerers.org/technologies/langfuse) ([Markdown](https://aitinkerers.org/technologies/langfuse.md)) — 13 public demos
- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 67 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [Monitoring](https://aitinkerers.org/technologies/monitoring) ([Markdown](https://aitinkerers.org/technologies/monitoring.md)) — 2 public demos
- [n8n](https://aitinkerers.org/technologies/n8n) ([Markdown](https://aitinkerers.org/technologies/n8n.md)) — 45 public demos
- [OpenAI GPT models](https://aitinkerers.org/technologies/openai-gpt-models) ([Markdown](https://aitinkerers.org/technologies/openai-gpt-models.md)) — 2 public demos
- [Orchestration](https://aitinkerers.org/technologies/orchestration) ([Markdown](https://aitinkerers.org/technologies/orchestration.md)) — 7 public demos
- [pgvector](https://aitinkerers.org/technologies/pgvector) ([Markdown](https://aitinkerers.org/technologies/pgvector.md)) — 25 public demos