I help enterprises ship AI that actually works.
I help engineering organizations move from AI autocomplete to governed, autonomous delivery. Three fixed-scope engagements, built on an open-source framework I maintain and use every day.
$ cat services.yml
What I do
Three engagements, usually in this order. Most clients start with the audit because it scopes everything after it.
01
AI SDLC Audit
Find out where AI is helping your delivery, where it's hurting, and what to change first. Interviews, a lifecycle map, governance gaps, and a prioritized roadmap.
2 to 3 weeks, fixed fee
02
North Star Pilot
A governed AI software factory running on your codebase, on real backlog work. Isolated agents, independent review with signed attestations, before and after metrics.
6 to 8 weeks, one team
03
Decision Context Engine
Turn institutional knowledge into context agents and people can query. Ontology, hybrid retrieval with evals, persistent agent memory, and signals feeding the Definition-of-Ready gate.
Scoped from the audit or pilot
$ ls ./work --recent
Selected work
Major HVAC Manufacturer
RAG System for Technical Documentation
Built an enterprise RAG system to make thousands of complex technical PDFs searchable and queryable by field technicians.
Automotive Financial Services Company
AI Readiness & Strategy Assessment
Led a comprehensive AI readiness assessment and developed an implementation strategy for SDLC tooling and AI adoption.
Global Management Consultancy
Knowledge Graph Proof of Concept
Built a knowledge graph with MCP agents and ontology-driven classification, outperforming vector search on precision metrics.
built in the open
Creator and maintainer of AI-SDLC, an open-source governance framework for AI-driven software delivery.
git clone ai-sdlc →Let's talk about your AI challenge.
Whether you're exploring AI for the first time or scaling an existing system, I can help you ship something that works.
book --consultation