Category: AI & Automation
-
The Date Was Forty Rows Away From the Transaction
I built a tool to catch my overspending. It told me I have an earning problem instead. On layout-encoded data, naming primitives, and hunting…
-
The Agent Passed Its Own Stop Rule
The same agent produced a perfect protocol halt and a forced-pass stop rule in one evening. On overclaim taxonomies, helpful-looking failures, and why the…
-
The PrivyBot architecture: why MCP matters
I keep trying to explain a Convoso MCP server to my boss. He’s the IT Lead. Smart, technical enough to follow the architecture, not…
-
How to Automate YouTube Shorts with Python and FFmpeg
One recording session, a month of Shorts. OBS captures, Python extracts the beats, FFmpeg assembles with title cards and normalized audio. Here’s the full…
-
How to Manage AI Coding Agents Without Losing Control
AI coding agents optimize for appearing done rather than being done. Here’s the three-layer methodology — Director, Pipeline, Agent — with the proof standard…
-
The Boring Layer That Made the Other Two Work
Neither of the other two tools I’ve written about recently would exist without this one, and it’s the one I almost didn’t write about,…
-
Two Numbers That Looked Close Enough to Share a Formula, Until I Checked
The forecasting tool projected two things off the same underlying curve: how many contacts to expect by end of day, and how many of…
-
I Didn’t Build the Pipeline I Planned. I Built the One That Worked.
I set out to build a fully automated AI content pipeline. No recording, no editing, no me. What I actually built was a FFMPEG…
-
The Rule Said 0.25%. The Math Said It Was Actually Enforcing 0.056%.
There was a rule that had been running for a long time: if a list’s contact rate drops below a fixed number after enough…
-
The Number Was Wrong by 2x, and I Found It by Predicting the Wrong Number in Advance
The forecast had been “very inflated” for weeks. Nobody could say by how much, or why — just that the projected end-of-day numbers didn’t…