The One Step I Never Hand to a Subagent
My content routine dispatches a fleet of subagents to gather, then hands none of them the draft. A fleet parallelizes retrieval. It cannot parallelize a voice.
Read articleEngineering Blog
Practical insights on Playwright, self-healing tests, AI-driven QA, and scaling engineering teams. Real lessons from 20+ years in quality engineering.
105 posts
My content routine dispatches a fleet of subagents to gather, then hands none of them the draft. A fleet parallelizes retrieval. It cannot parallelize a voice.
Read articleMy stock engine refuses to open any new position after 2:30 PM ET. It surrenders the most active hour of the day on purpose. Here is the arithmetic behind the refusal.
Read articleMy April posts reported measured numbers you had to take on faith. My recent ones derive every figure from public config. The change was not discipline. It was topology.
Read articleMy bracket risks 3% to make 5%, which reads like a favorable bet. On a price with no drift it is exactly break-even, and the reason is a theorem, not a coincidence.
Read articleThere is a rule I enforce across every agent I run, and it has nothing to do with how good the model is. The model writes the words. It never computes the numbers.
Read articleEvery indicator my engine trusts is computed on fifteen-minute bars. A bar is a summary of those minutes, and the summary throws away the one thing that moved the price: the path.
Read articleEvery day my engine reconciles its own record of open positions against the broker's. Almost every day the two lists match. I do not run the check for those days.
Read articlePage 1 of 15
Get weekly insights on AI-driven QA, engineering leadership, and automation strategies.
No spam, ever. Unsubscribe anytime.
Built with Vite, React, and Tailwind CSS.
View Source