Notes from the workshop.
How we build agents that ship real software: engineering write-ups, product decisions, and what we're learning about codebases in the wild.
Code-grounding
Why agents need to read your codebase before they write to it, and what reliable looks like in practice.
Reliable AI coding agents come from grounding, evaluation, verification, and review, not a smarter model. A practical guide to trusting agents on real code.
Trust and oversight
Approvals, audit trails, and isolation: what has to be true before an agent is allowed near production.
Trustworthy AI agents earn production through oversight, accountability, least privilege, and isolation. A guide to what to demand before one ships your code.
Architecture
How to shape an agent system: handoffs, state, concurrency, and the parts that should stay plain code.
AI agent architecture is what separates a demo from a system you can run. A guide to designing agents for reliability, model fit, and scale, without the hype.
Economics
What agentic coding actually costs, where the money goes, and how to keep the bill predictable.
AI coding agent cost is not a mystery. A grounded guide to what agents cost per task, the levers that cut the bill, and the business model underneath it all.
Problems
The failure modes teams hit with AI coding tools, named plainly and traced to their cause.
AI coding agents fail in production for predictable reasons: weak grounding, no verification, no accountability, brownfield reality. A map of the failures.
Earlier posts
Notes from before the current pillars took shape.