Brian Wald
Notes on building software with AI.
I'm a technology leader with a software engineer's instincts. I've worked as a Field CTO and executive advisor, helping engineering leaders make decisions about software development, AI, and cloud infrastructure.
I write about how engineering teams use AI to build, review, and ship software. Most pieces start with something I've tried myself or a conversation with someone doing the work.
I also cook, sail, and tinker with robotics, and occasionally write about whatever else holds my attention.
I'm exploring Field CTO and AI leadership roles. You can reach me at [email protected].
Latest Writing
What Your Agent Logs Can Actually Prove
I tried to check which documents a coding agent had received. The records and text matches could support a much more reassuring account of the work than the evidence justified.
The Agent Harness Belongs in Your Release Process
A coding agent can pick up a changed document halfway through a task. That behavior needs to be part of how we test and approve it for engineering work.
The Next Golden Path Is for Agents
Platforms have always served two kinds of users. The organization standardizes most teams onto a managed path and trusts a few to work directly with the primitives. Agents are a third user that fits neither path, and the next golden path has to be designed for them.
All posts →