Built
The agentic coding operating system
A practical model for moving from individual tool access to shared, reviewable team practice.
I build AI systems, test them in the real world, and teach what holds up.
Practical AI education for product leaders and teams: decide where AI is useful, what to check, and what to improve next.
Your Team Bought AI Coding Tools. It Still Needs an Operating System.
The hard part is no longer getting access to an AI coding assistant. It is designing the decisions, context, checks, and ownership that turn fast output into dependable work.
Read the field noteThe evidence ladder
See what supports each claim.
These labels show how far the evidence goes, from an early experiment to a result supported by real use. Use them to decide what to explore, what to test, and what needs more work.
Exploring
Active research or experiment.
Built
An inspectable artifact exists.
Tested
Named checks and limitations are available.
Deployed
A current live deployment has been verified.
Proven
An externally supported outcome exists.
What I’m working on now
AI experiments you can turn into better decisions.
I connect hands-on builds with lessons from product leadership and enterprise data work, so you can see the choices behind an AI workflow and apply the useful parts to your own.
Exploring
A2A beyond the protocol diagram
What agent-to-agent communication changes—and does not change—for product and enterprise teams.
Built
Trusted agents need evidence
A lightweight evidence ladder for separating experiments, artifacts, tests, deployments, and outcomes.
For teams
Know what to improve next.
Bring one AI workflow. A focused advisory review gives your team prioritized gaps, recommended changes, and clear criteria for checking the next improvement.
Explore a workflow review