
I'm Steven Diamante, a technical coach based in Raleigh, NC. For years before coding agents existed, I was coaching software teams in XP practices: test-driven development, refactoring, pairing, and ensemble programming. The pattern was always the same. When a team learns to work in small, safe steps, the fear goes away, the defects drop, and the work gets fun again.
I still code every day. I'm an Anthropic certified architect, I've spoken at CodeMash on working with coding agents, and I write the Refactor to Grow newsletter. The story below is how I went from AI skeptic to shipping production LLM products in half the time, using the same discipline I teach.
Six months of shipping scalable, maintainable applications with Claude Code


In April 2025, I joined a company building LLM-powered products and started pairing with Claude Code. I was skeptical, treating it like a code generator while I refactored by hand in WebStorm. Six months later, I barely touch my IDE. The agent does it all: TDD, code reviews, refactoring, even exploratory testing.
"My biggest breakthrough? Planning with the agent before coding. ASCII wireframes, test plans, architecture diagrams: it avoids bugs and unwanted features before a single line of code is written."
I've built RAG-powered chatbots, MCP-enabled AI tools, evaluation test suites, and complex React UIs, all in microservices serving multi-tenant SaaS customers with vastly different requirements. The domain is complex (manufacturing with literal moving parts), but the quality remains high because I apply XP practices: TDD, continuous refactoring, small batches, tight feedback loops.
Curious what this looks like for your team? Start with the half-day workshop.