# Pydantic AI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/pydantic-ai
> Markdown URL: https://aitinkerers.org/technologies/pydantic-ai.md
> Technology record last updated: 2026-09-18T15:13:56Z
> Generated: 2026-09-21T09:48:26Z

PydanticAI is a type-safe Python agent framework for building production LLM applications with structured data validation.

PydanticAI brings the rigor of Pydantic to agentic workflows. It supports major models including GPT-4o and Claude 3.5 Sonnet through a unified interface. The framework handles structured output validation, tool calling, and dependency injection natively. By using standard Python type hints, it eliminates runtime errors in data extraction (a common pain point in AI development). It is built for engineers who prioritize reliability and clean code in their production AI stack.

- Official technology site: https://ai.pydantic.dev/
- Public AI Tinkerers demos and talks: 7
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Goals MCP for preventing agents from reporting "Fake Done"](https://missoula.aitinkerers.org/talks/rsvp_bd91Kk9nVv8)

Show case of the goals mcp ( https://github.com/brucepro/goals_mcp ) in real time on a project using claude code. The primary purpose of the MCP is to prevent an agent from providing a done message when the work has not been completed.

- Event context: AI Tinkerers – Missoula Inaugural Meetup · 26 August 2026 — 2026-08-26 — Missoula
- Public talk page: https://missoula.aitinkerers.org/talks/rsvp_bd91Kk9nVv8

### [From Local Agent to Emergent Data Scientist](https://nurnberg.aitinkerers.org/talks/rsvp_T0ZyJGZ5BE0)

A local agent gets a stateful Jupyter kernel and a DuckDB database connection instead of fixed tools, giving it a full Python code execution environment. It has to predict outcomes for head and neck cancer patients from cohort data alone, with the current patient's outcome hidden. What I didn't design: the agent trained its own ML models and weighted their outputs based on the patient's individual features, unprompted. Live: I'll show agent traces and behavior in Logfire, walk through the system design, and explain the sandboxed code execution setup.

- Event context: AI Tinkerers Nürnberg: June Meetup (Community Hub) — 2026-06-24 — Nürnberg
- Public talk page: https://nurnberg.aitinkerers.org/talks/rsvp_T0ZyJGZ5BE0

### [AI for people who still print their email: how we put a 25-tool agent in front of 50-year-old accountants without a single hallucinated delete](https://poland.aitinkerers.org/talks/rsvp_d3AEfot6ruQ)

Numonis is an accounting SaaS in Spain and Portugal where the primary users are 40–60-year-old SMB owners and accountants, and we shipped a pydantic-ai conversational agent with 25+ tools (invoicing, documents, banking, P&L, tickets) as the main interface. Live demo: I run a demo of the system's features all over one typed SSE stream. Between beats I flip to DevTools to show the raw frames so the wire protocol is visible end to end.

- Event context: AI Tinkerers Poland #3 - Meetup in Wrocław — 2026-05-06 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_d3AEfot6ruQ

### [Semantic Data Deduplication: HNSW, MNN, and LLM](https://montreal.aitinkerers.org/talks/rsvp_3hHtv5BiXF4)

I built a semantic deduplication pipeline designed to identify, validate, and merge duplicate event records across noisy datasets. The system operates in three layers: Vector Indexing (HNSW), Mutual Nearest Neighbors, and Agentic Reconciliation (LLM) ensuring no data is lost by aggregating all unique attributes and data points across sources.

- Event context: AI Tinkerers Montreal - March Demo Night — 2026-03-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_3hHtv5BiXF4

### [Playing with Multi-agent User Interfaces](https://nyc.aitinkerers.org/talks/rsvp_eRYOqSoiYFo)

I've been playing around with multi-agent systems, how they fit in to using multiple frameworks and what various pieces of UI could look like with it.

- Event context: November Demo Day ft. Google Cloud and CopilotKit — 2025-11-17 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_eRYOqSoiYFo

### [Pydantic AI & Pydantic Graph - Cooperative and Competitive Agents](https://nashville.aitinkerers.org/talks/rsvp_pXQAQhp-NlM)

Fundamentals of Pydantic AI and Pydantic Graph with examples of cooperative and competitive agents.

- Event context: AI Tinkerers Nashville – October 28th, 2025 — 2025-10-28 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_pXQAQhp-NlM

### [Survaize: using vision models to generate apps from survey forms](https://dc.aitinkerers.org/talks/rsvp_kO8RY4RziiM)

Building apps for electronic data collection of surveys and censuses usually involves a manual process. Subject matter experts create the survey forms on paper (or in word processor) and then someone has to copy each question into a survey authoring tool. This process can take days or weeks and is error prone. Survaize is a proof of concept of using LLM vision models to read a PDF of a survey form and extract the questions, responses and other details and automatically generate an application for electronic data collection that can be run on a mobile device.

- Event context: AI Tinkerers - DC Metro Meetup (July 10th 2025) — 2025-07-10 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_kO8RY4RziiM

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Agent Orchestration](https://aitinkerers.org/technologies/agent-orchestration) ([Markdown](https://aitinkerers.org/technologies/agent-orchestration.md)) — 2 public demos
- [AG-UI](https://aitinkerers.org/technologies/ag-ui) ([Markdown](https://aitinkerers.org/technologies/ag-ui.md)) — 4 public demos
- [AI frameworks](https://aitinkerers.org/technologies/ai-frameworks) ([Markdown](https://aitinkerers.org/technologies/ai-frameworks.md)) — 1 public demo
- [Amazon Bedrock](https://aitinkerers.org/technologies/amazon-bedrock) ([Markdown](https://aitinkerers.org/technologies/amazon-bedrock.md)) — 20 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [Claude Sonnet 4](https://aitinkerers.org/technologies/claude-sonnet-4) ([Markdown](https://aitinkerers.org/technologies/claude-sonnet-4.md)) — 18 public demos
- [CopilotKit V2](https://aitinkerers.org/technologies/copilotkit-v2) ([Markdown](https://aitinkerers.org/technologies/copilotkit-v2.md)) — 1 public demo
- [DuckDB](https://aitinkerers.org/technologies/duckdb) ([Markdown](https://aitinkerers.org/technologies/duckdb.md)) — 9 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [goals_mcp](https://aitinkerers.org/technologies/goals-mcp) ([Markdown](https://aitinkerers.org/technologies/goals-mcp.md)) — 1 public demo
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [HNSW](https://aitinkerers.org/technologies/hnsw) ([Markdown](https://aitinkerers.org/technologies/hnsw.md)) — 7 public demos
- [Jupyter](https://aitinkerers.org/technologies/jupyter) ([Markdown](https://aitinkerers.org/technologies/jupyter.md)) — 8 public demos
- [Jupyter kernel](https://aitinkerers.org/technologies/jupyter-kernel) ([Markdown](https://aitinkerers.org/technologies/jupyter-kernel.md)) — 1 public demo
- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 67 public demos
- [llama](https://aitinkerers.org/technologies/llama) ([Markdown](https://aitinkerers.org/technologies/llama.md)) — 48 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos