Pydantic Graph and CopilotKit: A Minimal Full-Stack Workflow Demo
A practical walkthrough for connecting a Pydantic Graph workflow to a CopilotKit frontend with FastAPI and AG-UI.
Available for consulting · subcontracting
Build production-ready AI systems
Ian Cunningham · AI systems builder
I design and build AI workflows, data pipelines, and copilots that hold up in real-world use, not just demos.
Built with LangGraph, CopilotKit, and modern tooling, with a structure designed for reliability from day one.
Services
AI systems built
for real-world use
I design and build AI workflows, data pipelines, and copilots that are reliable, maintainable, and integrate seamlessly into real-world systems.
AI Workflow Automation
Multi-step workflows that combine LLM reasoning with structured logic, validation, and clear, trackable execution.
Data Processing Pipelines
Pipelines that ingest messy content, clean it, structure it, and turn it into reliable data for downstream use.
Custom AI Copilots
Custom copilots and internal assistants designed around real tasks, business context, and interfaces people trust.
Testimonials
“You need look no further than Ian.”
Debbie, senior project stakeholder
Featured Demo
AI Realtor Copilot
Answer real estate questions with a production-ready AI copilot
Let users ask questions about listings, coverage areas, and business operations, and get structured, reliable answers in real time.
Multi-agent orchestration coordinating specialized tasks behind the scenes
Live progress visibility so users can see how answers are generated
Dynamic UI updates that surface listings, details, and structured results
Copilot UX designed around real business tasks, not generic chat
A practical example of how AI can combine structured data, business logic, and responsive interfaces to deliver useful answers in production.
FEATURED INSIGHTS
Practical notes on AI systems that need to hold up
Thoughts on building AI systems that are reliable, observable, and grounded in real-world constraints.
Pydantic AI and CopilotKit: A Minimal Full-Stack Agent Demo
A practical walkthrough for connecting a Pydantic AI agent to a CopilotKit frontend with FastAPI and AG-UI.
What It Takes to Build Production-Ready LangGraph Systems
A production-oriented checklist for LangGraph systems: deterministic tests, evaluations, parallel workflows, control flow, and observability.
Progress Indication with LangGraph and CopilotKit
A practical pattern for rendering progress cards in CopilotKit chat while LangGraph runs long-running agent workflows.
PostgreSQL: The Swiss Army Knife for Agentic Databases
Modern AI systems increasingly tempt developers toward specialized databases for every problem. In practice, PostgreSQL can often handle far more than people realize.
In the AI Regulatory Landscape, Agentic Graphs Can Make a Lot of Sense
When legal requirements, human approvals, sensitive data, operational guarantees, and governance concerns enter the picture, deterministic workflows start looking a lot more like responsible system design.
Work together
Most AI demos don’t survive real use. Let’s build one that does.
I help teams design and build AI systems with clear architecture, pragmatic implementation, and a fast path to real-world use.