The open web is splitting into gated pockets: robots.txt walls, login walls, paid APIs and private licensing deals. What the data shows, where it complicates the story, and what builders and readers should do about it.
Open web · AI · Data · Business8 min read
Around 2012 and 2013, knowing how to operate the tools stopped being enough to hold a job on the web. You had to be able to build. The AI shift feels like that again, only faster. What I saw then, what's different now, and what I'd do about it.
Careers · AI · Front-end · Leadership6 min read
In my agent rig, prompts, routes, skills and even fine-tuned models all start in shadow. Promotion is a separate, evidence-backed step that a person takes. Here's the lifecycle, and why it matters more as the number of moving parts grows.
Agents · AI · Local LLMs · Delivery6 min read
For months I've been quietly building a pipeline that takes raw HL7 v2 messages and C-CDA documents, repairs them, maps their codes to standard vocabularies, and turns them into FHIR and OMOP. Why healthcare interop data is so messy, and the approach that's working.
Healthcare · Interoperability · Data · AI8 min read
A rock tumbler doesn't make a stone smooth in one pass. It uses coarse grit, then finer grit, then polish, and checks between stages. That's how I build agent loops in Starship: bounded retries, deterministic gates, and lessons that are only allowed to hurt once.
Agents · AI · Architecture · Delivery7 min read
Starship runs its coding and planning agents on a small fleet of Apple Silicon Macs I own. Here is when local models beat the cloud, what it cost me in operational lessons, and where I still reach for a hosted model.
AI · Agents · Architecture · Local LLMs6 min read
How Starship's coding agents go from a planned task to a merged pull request without a human driving each step, and the gates, retries and postmortems that make that safe to leave running.
AI · Agents · Architecture · Delivery6 min read
A coding agent is only as good as what it's handed. Here is how Starship curates its skill library, enforces standards, and keeps the context it feeds models grounded and current, including where that loop was still open.
AI · Agents · Architecture · Local LLMs6 min read
Public records live on thousands of county and city websites, each built differently. Writing a scraper for every one by hand doesn't scale. So I built a tool that visits a site, works out how its search actually behaves, scores whether it's worth automating, and has a model draft the parser. Here's how it's put together and where the model stops.
AI · Data · Architecture6 min read