Skip to content

Editorial

Writing

Stories from the masthead, plus notes from the desk. Bylines are the authors we defined — not one voice on every URL.

Tool Deep Dive

Agents Are Not Automations: The Decision That Saves Ops Teams Six Months

Operations teams are deploying AI agents using automation logic—and breaking their systems within weeks. The fix isn't better tools. It's understanding where agents belong in your stack.

Jules Marchetti · September 15, 2026

Tool Deep Dive

One writer, one editor, one claims list

Most writing stacks fail by buying three generators and no editor. Pick one model for drafts, one layer for cleanup, and a list of words Legal will not sign. Everything else is a subscription looking for a job.

Gary Stanton · September 11, 2026

Tool Deep Dive

The 70% Draft Problem: How to Make Claude Do the Thinking You Keep Postponing

Most teams treat Claude like a search engine with manners. A simple diagnostic framework reveals whether your AI prompts are generating real first drafts or just polished filler you'll rewrite anyway.

Pete Callahan · March 3, 2026

Tool Deep Dive

The Draft-Then-Judge Stack: Why Two Cheap Tools Beat One Expensive AI Writer

After routing 147 blog posts through different AI tool combinations, one pattern kept repeating: separating the drafting tool from the editing tool produced measurably better content than any single all-in-one platform.

Pete Callahan · March 3, 2026

Tool Deep Dive

Your Team Already Has ChatGPT Logins. Here's Why Nobody's Using Them.

Most teams signed up for ChatGPT months ago. Seats are paid, logins are active, and usage dashboards show near-zero adoption. The fix isn't more training—it's giving people a repeatable prompt structure and one workflow to prove it works.

Pete Callahan · March 3, 2026

Tool Deep Dive

GitHub Copilot After 6 Months: The Productivity Trap

One fintech team's code velocity jumped 34% after deploying Copilot. Then their security audit found 47 credential-handling violations. The real problem wasn't the tool—it was optimizing for the wrong metric.

Jules Marchetti · October 25, 2025