Agentic systems people can trust
I build with LangGraph, LangChain, Pydantic AI, and MCP servers. To that I add tool calling, structured outputs, human-in-the-loop controls, evaluations, and guardrails.
Gary Butler
Software engineer. AI builder. Always learning.
More than 30 years developing software and now bringing that experience to hands-on work with AI.
30+Years building software
17Years leading teams
4Projects in the open
01What I do
A builder's depth. A leader's perspective.
My work spans applied AI, enterprise systems, technical leadership, and the projects that connect them.
View full experience →RAG that cites its work
Vector databases and retrieval pipelines built around enterprise data, so every answer traces back to its source.
Teams that ship and support
Seventeen years leading developers and analysts through enterprise delivery, modernization, and production support.
Legacy systems, brought forward
Agentic AI coding tools pointed at aging applications, rebuilding them rapidly on a modern stack.
Rapid prototypes and proofs of concept
Built quickly with agentic AI, so a rough idea becomes something you can actually put in front of people.
02AI Projects
Small builds. Useful evidence.
Each one exists to answer a question I could not answer by arguing about it.
View all projects →HazardAI
Can a vision model turn job-site photos into a useful first draft of a job hazard analysis without taking the final decision away from a person?
Vision AIReact NativeHuman review
View project ↗Querent
Can a natural-language query tool get safer and faster over time by reusing governed, certified answers instead of asking an LLM every time?
LLM safetyQuery registryPython
View project ↗Course Intelligence Studio
Can a desktop app turn a live online course, audio, screen, and slides, into notes and flashcards worth reviewing later, without ever saving the raw recording?
Speech to textDesktop appLocal-first
View project ↗Call Coach
Can an AI voice conversation give customer-service trainees practice and feedback worth their time?
Realtime voiceReactSupabase
View project ↗03Tools
The tools behind the work.
Most of my building runs through AI coding agents. These are the ones I use, what I add to them, and the libraries that end up in the applications.
View all tools →More than one agent, on purpose.
Most changes begin as a conversation with an agent and end with me reviewing the diff. If the problem matters, I will often hand it to a second agent before I trust the first answer.
Claude Code · Cowork · Codex · ChatGPT Work ↗Skills, tools, and plugins I use.
Below are some of my favorite skills, plugins, and MCP servers that I use to make building applications more productive.
Stripe MCP · Context7 MCP · Playwright CLI · Engineering skills · Ponytail · Impeccable · Claude Design · Graphify ↗How I build agentic workflows.
Pydantic and Pydantic AI give my agents typed data, tools, and outputs. LangGraph is my preferred tool for coordinating those parts when the application needs a workflow I can inspect and control.
Pydantic · Pydantic AI · LangGraph ↗04Experience
Software has to keep working after the demo.
I have spent more than 30 years building software and 17 years leading development and analyst teams. That work taught me to care about permissions, failure paths, handoffs, and the people who support the system later.
View my experience →Built around real systems
My background is in enterprise applications, integrations, modernization, and production support. I build on the systems a team already runs rather than ripping them out and starting over.
AI with a visible boundary
My recent work covers LLM applications, retrieval, tool-using agents, structured outputs, evaluations, and human approval. I use those tools when they fit the job.
Beyond the résumé
The work matters.
So does how I think.
The projects show what I have built. The tools show how I work: which agents I trust with what, and where I decide a person has to stay in the loop.
See my tools ↗