What Is AI Automation? The Operator’s Three-Tier Definition (No Vendor Spin)
What is AI automation? A model doing a step in a process that runs without you. Here are the three tiers, and a rule for telling which one your task needs.
-
-
Tip Tuesday: Ship the Query With the Number (My AI Agent Metrics Had 16 Right Answers Between 12 and 197)
One bug, one question, and 16 defensible answers between 12 and 197 — all from the same file on the same morning. The fix costs one log line.
-
Monday Myth-Busting: “AI Agents Learn From Their Mistakes” (Mine Logged the Same Bug 65 Times and Fixed None)
My agent recorded the same four bugs 221 times in 105 days and fixed none of them. The memory worked perfectly. Here is what AI agents actually need in order to learn.
-
“AI Consultant Near Me” Is the Wrong Search — Here’s the Filter That Actually Works (2026)
Page one of “ai consultant near me” is city landing pages and paid directories. Proximity is the wrong filter — here are six questions that replace it.
-
Sunday Setup: Check Your AI Agent Queue’s Age, Not Its Depth (Mine Was 107 Rows and a Median of 103 Days Old)
My queue said 107 ideas ready to go. Sorted by date instead of priority, the median was 103 days old and 60 rows had been passed over for three months. The Sunday check that finds a reject pile pretending to be inventory.
-
AI SEO Agency in 2026: What They Actually Do, and How to Test One Before You Sign
Every ranked list of the best AI SEO agency puts its own publisher first. Here is what the work actually is, what it costs, and six questions that test a vendor before you sign.
-
Saturday Shortcuts: 3 Ways to Find Out What a Failed AI Agent Run Already Did (Before You Retry It)
A run of mine died after 40 minutes and left a 320-byte log. It had already sent five emails and filed its own success report. Three shortcuts for finding out what a failed AI agent run already did — before you retry it.
-
FAQ Friday: What Can’t My AI Agent Do? (1,399 Runs, 49 Failures — None of Them About Intelligence)
I audited 1,399 runs of my own autonomous agent fleet. 49 failures — 48 were one expired token. The real AI agent limitations aren’t about intelligence.
-
How to Update Claude Code Without Breaking a Running Agent Fleet (2026)
How to update Claude Code correctly on every install method, why most guides recommend the one command the docs warn against, and the pinning, rollout and rollback discipline you need if your agents run unattended.
-
Tool Thursday: Replicate — Rent Any AI Model by the Run (My Real Cost Was Double What My Own Docs Said)
Replicate rents you any AI model by the run, no GPU and no subscription. This morning it charged me double what my own documentation claimed, and the documentation was the thing that was wrong.
