Aug 29, 2026
Local service businesses already pay to make their phones ring. A voice agent can turn their missed calls into a sellable service.
Aug 21, 2026
Building software before you have distribution is risky. Building software as proof for an expertise changes the equation.
Aug 14, 2026
I wrote Claude's watermark detector and its remover in the same file, to find out why both fit in one afternoon.
Aug 7, 2026
I automated a monetized Benable list through an undocumented API, and half of it stayed invisible to the people it was built for.
Jul 31, 2026
I audited 595 runs from July. 61% of my compute proved something the next run was about to prove again.
Jul 26, 2026
11 AI-built products, 6 months of audits, the same 5 mistakes every AI crawler trips over.
Jul 24, 2026
A 50,000-row SEMrush export explains why some Benable lists pay $60 a month, others $2.
Jul 17, 2026
Two tasks from the same Claude Code run, same mid-tier model: one cost 76K tokens, the other 970K. The gap wasn't the model.
Jul 10, 2026
My agent was driving the browser like a cautious intern. One tool swap later, the same task went from 40 seconds to 1.5. Here's why, benchmark included.
