Roadmap
Three pipelines. Curating and collating verifiable data.
Why build these at all
The data that decides whether a site can get power is public, and almost none of it is usable. It sits in ISO queue spreadsheets with inconsistent column names, in RTEP planning documents as prose, and in PSC dockets as scanned PDFs.
Each of these projects takes one of those sources and turns it into something a person can check in a minute instead of a week. That is the whole thesis: not new data, just public data made legible, with every figure traceable to the filing it came from.
Queue Wire
Which interconnection queue projects are advancing and which are not? This is a weekly diff report on generation projects.
Substation Expansion Tracker
Parsing PJM RTEP and TEAC filings for planned substation additions and upgrades.
Large-Load Regulatory Tracking
The Large Load Registry is live for BPA — 291 live requests, 50.5 GW. The regulatory-docket piece is still taking shape.
Large Load Registry is live →How this gets built
Phil builds these with Scout, an AI research agent. Every pipeline follows the same rule as the Site Scanner: a figure ships only when it traces to a named public source with a retrieval date. Where a signal is indirect, it is labelled as an indicator rather than a determination, and where a dataset cannot answer a question, the page says so instead of estimating.