Writing about AI, infrastructure, and what actually ships.
total 152 · ~11.8h read · updated Oct 23
A measurement protocol for human review, rework and agent spend that keeps rejected attempts in the calculation.
A durable handoff separates observations, hypotheses and unfinished work, then records what would make each observation stale.
The $7.99 rebuild bought a first version; the repository now shows the less photogenic work of preserving an archive and keeping its promises.
Perplexity's own data shows its agent does 48× more machine work per session than its search product — but the 87% time saving rests on ten assumed minutes of human oversight, and that is the number a buyer needs.
A review bundle should connect the requirement to evidence for the exact candidate and make the remaining decision explicit.
A CI alert becomes useful work when its revision, evidence and next owner survive the handoff; another prompt template does not supply them.
A dedicated email address limits which messages reach an agent; the harder details are untrusted content, sending authority and missing attachments.
Tracing a WHOOP event through receipt, diagnostic capture, Sheets forwarding and reconciliation reveals what a successful response leaves unproved.
A deliberately broken discount function passes its edited test; an unchanged acceptance check shows why the owner of the verdict matters.
A useful agent acts within delegated authority, prepares consequential actions for review, and asks again when the action changes.
Santander open-sourced its AI control layer in June 2026 — the harness, the guardrails and the governance — but the early public activity leaves adoption unproven.
