# OpenAI GPT models Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/openai-gpt-models
> Markdown URL: https://aitinkerers.org/technologies/openai-gpt-models.md
> Technology record last updated: 2026-04-06T16:57:43Z
> Generated: 2026-09-21T16:42:28Z

OpenAI's Generative Pre-trained Transformer models: the industry standard for advanced AI reasoning, code generation, and multimodal task execution.

The GPT model series (Generative Pre-trained Transformer) represents a family of large, powerful AI models, fundamentally changing natural language processing. Flagship versions, like GPT-5.2, excel at complex problem-solving, offering sophisticated reasoning efforts for technical and scientific tasks. These models are multimodal, processing and generating text, image, and audio content. Developers leverage the API to integrate capabilities—from high-accuracy coding assistance to large-scale content generation—with specific versions optimized for speed (e.g., GPT-5 nano) or deep reasoning (e.g., GPT-5.2 pro).

- Official technology site: https://platform.openai.com/docs/models
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [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

### [IncluLearn Global: An AI-Powered School & Health Recommendation Engine with Explainable Suggestions](https://nairobi.aitinkerers.org/talks/rsvp_B-IPKFMSVxo)

I’ll demo how I built IncluLearn, a recommendation system that helps families in Kenya discover schools and health specialists tailored to their needs and location. The demo walks through the backend logic, how user data is stored in Supabase, queried, and matched using AI. I’ll also show how I experimented with vector search and explainable AI prompts to generate human-friendly reasons for recommendations. The goal is to unpack the messy but practical steps of going from a raw idea to a working prototype

- Event context: AI Tinkerers Nairobi – Sep 25, 2025 Meetup — 2025-09-25 — Nairobi
- Public talk page: https://nairobi.aitinkerers.org/talks/rsvp_B-IPKFMSVxo

## Related Technologies

- [Agent](https://aitinkerers.org/technologies/agent) ([Markdown](https://aitinkerers.org/technologies/agent.md)) — 12 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Google Maps API](https://aitinkerers.org/technologies/google-maps-api) ([Markdown](https://aitinkerers.org/technologies/google-maps-api.md)) — 3 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
- [Monitoring](https://aitinkerers.org/technologies/monitoring) ([Markdown](https://aitinkerers.org/technologies/monitoring.md)) — 2 public demos
- [Netlify](https://aitinkerers.org/technologies/netlify) ([Markdown](https://aitinkerers.org/technologies/netlify.md)) — 4 public demos
- [OpenAI GPT](https://aitinkerers.org/technologies/openai-gpt) ([Markdown](https://aitinkerers.org/technologies/openai-gpt.md)) — 3 public demos
- [Orchestration](https://aitinkerers.org/technologies/orchestration) ([Markdown](https://aitinkerers.org/technologies/orchestration.md)) — 7 public demos
- [Postgres](https://aitinkerers.org/technologies/postgres) ([Markdown](https://aitinkerers.org/technologies/postgres.md)) — 12 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [Vector databases](https://aitinkerers.org/technologies/vector-databases) ([Markdown](https://aitinkerers.org/technologies/vector-databases.md)) — 9 public demos