Category: AI Engineering
-
Build an App with the Copilot Managed Runtime CLI
In the last post I explained why Copilot Managed Runtime exists and what it adds to the Code Apps feature. This post will be the technical guide to setup and publish an app. You install the Copilot Managed Runtime CLI, create an app, run it on your machine, connect it to a SharePoint list or Dataverse tables,…
-
Copilot Managed Runtime (Managed Apps)
Copilot Managed Runtime is the name Microsoft put on the thing Code Apps was growing into. It went into public preview on 25 September 2026, and my first reaction on launch day was three things: another app type, another CLI, another admin center? Copilot Managed Runtime is the third name installment for an existing Power…
-
Basic Loop concepts with agents in Claude Code
Autonomous agents in Claude Code sound scarier than they are. Underneath, autonomous agents run on one simple idea that repeats, wrapped in a few commands you can learn over a coffee break. Here is the thing, explained for someone who has just started. The patterns to understand first Let me start with the foundation, because…
-
Self-improving AI skills: what to automate, and what to keep human
If I were setting up an AI agent with a writing skill today, the one that drafts my blog posts and content, I’d start with one thing: whatever it writes has to sound like me. My words, my voice, the way I think, not generic AI prose with my name on top. That goal has…
-
Claude Fable 5: New Tier Above Opus, Safety as API Surface
What changed with Claude Fable 5 compared to Opus? A new tier above the older model at twice the price, and safety that now lives in the API itself. Anthropic shipped it on June 9, 2026, alongside a sibling model, Claude Mythos 5. What Claude Fable 5 and Claude Mythos 5 are Claude Fable 5…
-
Claude Opus 4.8 for builders: reliability over IQ
Anthropic released Claude Opus 4.8 today, 28 May 2026, a few weeks after Opus 4.7. Standard-tier pricing didn’t change. Fast mode dropped to a third of what it used to cost. Anthropic’s pitch this time is long-horizon reliability: multi-step, multi-tool runs where one early mistake compounds for the next hour. They claim Opus 4.8 is around 4×…