Claude

14 posts on this topic.

• Aug 22, 2026

  The green test that lied — two types of false pass your CI can't catch

  You wrote the gate that stops bad builds. The gate went green. The bug shipped anyway. It wasn't a fluke — it was measuring the wrong thing the whole time.

• Aug 5, 2026

  I Audited Every 'Done' My AI Reported — All Three Were Wrong

  Every "done," "already measured," and "wired into the build" my AI handed me — I ran three of them back against the primary record.

• Aug 1, 2026

  I Automated My YouTube Channel with 8 AI Agents — and It Stopped Silently for 7 Days

  Eight AI agents handle every step from script to publish-ready packet — overnight, without me. My only job: open the daily brief and upload the finish. But last week, that "once a day" setup sat stopped for seven days, and nobody noticed.

• Jul 19, 2026

  3 AIs, One Afternoon: Claude vs GPT vs Gemini on Real Work (Scored)

  I gave Claude, GPT, and Gemini the same afternoon of real work. Same 32-page report, same instruction: extract it, analyze it, write the brief. I built the answer key before anyone ran. Then I scored all three.

• Jul 14, 2026

  I let a separate AI veto my own videos — a multi-agent pipeline (Part 2)

  Same AI writing it, same AI stamping "OK" — quality doesn't move. So on this channel's video line I gave a separate-personality reviewer real veto power, and it stamped "fail" and sent the work back nine times, on record.

• Jul 13, 2026

  Make AI attack its own draft 5×: the self-critique loop's blind spot

  I don't read the first draft an AI writes. First I make the AI tear its own draft apart — up to five times — and I read what's left.

• Jul 12, 2026

  I Gave Claude, Gemini & GPT the Same Landing-Page Brief — Here's What They Built

  I handed the exact same one-line prompt to Claude, Gemini, and GPT — build a landing page for a fictional app called "PlantPing" — and compared them on design, code, and generation speed.

• Jul 12, 2026

  Claude Skills: 3 real recipes + the rule that makes them fire

  Most people use Claude Skills like a "remember this for me" feature. Used right, they become something else entirely: a security boundary, a guardrail, a logbook of every landmine you've stepped on.

• Jul 12, 2026

  How Claude becomes an agent: 3 MCPs + 1 rule

  Most people think MCP is just "how Claude talks to Notion or Slack". It isn't. MCP is the moment your chatbot becomes an agent that actually does things — across your real tools, with your real data.

• Jul 12, 2026

  You don't always need MCP (here's what I use instead)

  A lot of people think you need MCP to connect Claude to your tools — Gmail, Notion, your own server. You don't. It's the most common misconception going around right now.

• Jul 12, 2026

  Loop Engineering, explained (it's not the /loop command)

  "Loop Engineering" is everywhere right now — but most people think it's a command or a coding trick. It isn't. It's a way of using AI: instead of being the person who prompts the agent every time, you design the system that does the prompting for you.

• Jul 12, 2026

  Why AI agents get stuck in infinite loops — and 3 rules to stop it

  On a human team, "thanks!" and "no, thank you!" is harmless. On a multi-agent AI team, that same politeness quietly loops — and melts your bill.

• Jul 12, 2026

  I built an AI-agent platform without touching a dashboard (Part 1)

  I stood up a whole crew of AI agents — a researcher, a writer, a checker — and never opened the admin dashboard once. No console, no forms, no GUI.

• Jul 12, 2026

  Why your AI ignores the rules you write — and where to put them instead

  You wrote the rule that fixes the mistake. The next week your AI shipped the exact same mistake anyway. It wasn't laziness — it was where you put the rule.