Practical, no-fluff writing on IT leadership, CRM & revenue plumbing, attribution, and AI automation — from someone who still ships the code.
30 posts · 4 categories · 23 tags
A branch-satisfaction survey for a multi-branch aesthetic clinic chain went from sixteen hardcoded questions to an admin-editable form, and the entire design turned on one rule: an edit that would change what a past answer means has to fork the question, not overwrite it, and the fork boundary is enforced by what the code can't do.
Auditing 263 API routes for AI spend found three image- and video-generation endpoints gated only by 'is this user logged in.' Any tier, any role, any tenant could burn two paid providers with no cap and no way to tell whose bill it was.
A Biome lint fix renamed a Playwright fixture's empty-object parameter to silence a dead-pattern lint error — a no-op for the function body, but Playwright reads that exact syntax shape to resolve fixture dependencies, and the rename crashed every end-to-end test before a single one ran.
A Docker Compose healthcheck gate held the ingestion worker back until the simulator had already fired a full day of factory telemetry at nobody — MQTT's clean:false plus QoS 1 only replay into a session that already exists, and none did yet.
WhatsApp status counts tallied from a vendor's delivery log are exclusive latest-state buckets, not a running total — dividing every rate by raw sentCount produced a 177.8% reply rate and a 2,881% delivered rate in production, and the fix needed no new column, only different arithmetic.