Lead Software Engineer at a NASDAQ-listed SaaS group: end-to-end ownership of product areas and the internal platform the squads ship on, AI-natively, under one rule: never merge code you can't explain.
What's here:
- agentweft - multi-agent runner for software delivery: gates that are programs, journalled and resumable runs, a call and token budget with a hard stop, MCP client and server. Runs the delivery workflow at work and my own pipeline.
- warpmap - Go audit CLI that maps a codebase for humans and coding agents: dependency graph, churn x complexity hotspots, blast radius, a baseline diff, a GitHub action that fails a risky PR, an MCP server.
- react-formkit - define a form once as config and render it through an adapter for any React UI library, on React Hook Form and Zod; extracted from production work.
- weftworks, tare, efquerykit - Claude Code skills and workflow patterns, a .NET writing-integrity CLI, an EF Core query kit for MySQL.
Upstream: 100+ merged pull requests, in the OpenAI and Hugging Face SDKs, Microsoft's onnxscript, docling, deepset's haystack, vite, react-router and a dozen more.
Writing: HackerNoon articles and recorded webinars, from system architecture to agentic development:
- From idea validation to scale: how to choose the right architecture
- Turning a messy codebase into something you can actually work with
- Legacy in months, not years: keeping AI-written code safe to change
Judge at AI Slop Scan 2026.
Happy to connect on LinkedIn.
