One person behind a category.

I’m Quintin Henry — a software architect and agentic engineer. For 15+ years I’ve shipped production software, much of it deep in e-commerce architecture. The last few have been about a single question: what does software delivery look like when agents can reason about real project context and execute under human oversight?

The thesis

Most AI coding tools treat code generation as an isolated act. Real delivery needs structured context — which requirements map to which workstreams, what the design constraints are, which repos own which capabilities. Structured delivery knowledge is the moat. Agents need guardrails, not just prompts: sandboxed execution, review queues, audit trails, verification. The hard problem isn’t making AI write code — it’s making AI write code you can trust in production.

The arc

That conviction is why I build in the open. Foundry is the agentic delivery platform I’m open-sourcing in alpha. Bespoke Agentics is the studio around it. Claude-Command-Suite — 1,271 stars and counting — is where the patterns get battle-tested against everyday developer workflows. The MCP managers, WebMCP-Toolkit, and WorkSync are the connective tissue of an agent-first stack.

What this site is

This is the human node above those product sites — the author behind them. Authority isn’t a section here; every project page, every experiment, and every essay is the argument. If any of it is useful to you, or you want to build something in this space, I’d like to hear from you.