Posts on Agentic Engineering in Action (agentprose demo)

Where Is the Gate? A Practical Look at AI Engineering Systems

Wed, 30 Sep 2026 05:15:04 +0000

By an AI engineering system, I mean how a team uses agents to take an idea all the way to a reliable change: the context agents can use, the actions they can take, the tests and approvals a change must pass, and the signals that come back from production. A coding agent is part of that system, not the whole thing.

One corpus, many harnesses: what it took to keep our AI consistent

Mon, 28 Sep 2026 05:15:20 +0000

👋 Guest post: This edition is written by Einar Ingebrigtsen, sharing his own perspective and experience. I’m also open to featuring more guest voices in future editions, so if you have something relevant to share with this community, feel free to reach out.

What I learned building 6 apps and solving 10 related engineering problems for the OpenAI WebMCP Challenge

Fri, 25 Sep 2026 05:30:17 +0000

I built six working app prototypes in a short time for the OpenAI WebMCP Challenge. I wanted to explore workflows where an agent could do repetitive work while a person could see the plan on the page and review it before approving consequential changes.

GitHub Agentic Workflows: The Five-Minute Version + Free Book

Mon, 21 Sep 2026 05:45:47 +0000

What gh-aw is, where it fits, and what to expect from my new interactive book

Note: this article is not a book itself (see below) but a quick introduction to GitHub Agentic Workflows so you could take decision on exploring this topic further.

Your Agent’s Context Has a Supply Chain. Manage It.

Tue, 08 Sep 2026 20:14:00 +0000

Building a supply chain for agent context with Microsoft Agent Package Manager

An AI coding agent’s working environment starts taking shape before we send the first prompt. We equip it with project conventions, reusable skills, specialized agent definitions, workflow automation, and connections to external tools and information. Together, these customizations influence what the agent knows how to do and which capabilities are available to it.

Giving AI agents a real computer

Thu, 23 Jul 2026 06:32:10 +0000

How I built Sandcastle on the new GitHub Copilot provider for Microsoft Agent Framework — and what the feature actually unlocks

▶️ Live demo: https://sandcastle.isainative.dev

Most “AI app” demos boil down to the same thing: a prompt goes in, a wall of text comes out, and you still have to copy it, run it, fix the three things that don’t compile, and host it. The GitHub Copilot provider for Microsoft Agent Framework flips that: instead of returning text about code, an agent gets a real, sandboxed computer — it can run shell commands, read and write files, fetch URLs, and call MCP servers — and it uses that computer to actually build and run the thing you asked for.

The Best AI Coding Model Is a Moving Target. Build a Selection System Instead

Wed, 15 Jul 2026 05:15:06 +0000

Choosing an AI coding model from a leaderboard is like choosing a route from a screenshot of yesterday’s traffic.

The route may have been fastest when it was measured. That does not mean it is fastest from your starting point, with your constraints, under today’s conditions.

The First 80% Takes Nine Minutes. The Last 20% Takes Two Days.

Mon, 13 Jul 2026 05:15:03 +0000

Picture a product team at 9:07 on a Tuesday morning.

A product manager asks an agent to add saved views to an internal dashboard. By 9:16, there is a new sidebar, a polished dialog, and a satisfying little animation when a view is saved. The happy path works. The team gathers around the screen, clicks through the demo, and has the same thought:

You can't tune what you can't see: prompt‑cache observability for GitHub Copilot with OpenTelemetry

Wed, 08 Jul 2026 12:42:31 +0000

Open VS Code, ask Copilot Chat one question, and if you crack open the debug view you can watch prompt‑cache tokens tick past for that single call. That’s exactly enough visibility for one developer, on one machine, for one prompt. It stops being enough the moment you want to answer a sharper question:

Design, but with tests: an engineering approach to UX with Impeccable

Wed, 01 Jul 2026 14:50:55 +0000

Impeccable — now built into the GitHub Copilot app — treats design quality the way we treat code quality. This is what that looked like on a real app that was already shipping.

We have version control, code review, linters, profilers, and prioritized backlogs for our code. For the design of the things we build, most of us have “looks good to me.” This is the story of what happened when I closed that gap — by pointing a skill at my aurora app that brings an engineering discipline to UX.

The model is a commodity. The harness is your advantage. A hands-on experiment with GitHub Copilot app's Canvas

Tue, 30 Jun 2026 12:29:09 +0000

The teams getting the most out of AI agents are not the ones with the best model. They are the ones building a custom layer on top of it. This is a short, hands-on look at one new surface for that layer - GitHub Copilot app’s Canvas - learned by building a small internal tool end to end.

Stop Putting a Raw LLM in Your CI Pipeline — Put a Sandbox Around It

Mon, 29 Jun 2026 14:00:15 +0000

Welcome to the very first issue of Agentic Engineering in Action! Subscribe to get every new issue straight to your inbox — and share it with your team.

There’s a seductive idea floating around every engineering org that has discovered GitHub Actions and GitHub Copilot in the same quarter: what if I just run the Copilot CLI inside an Action and let it triage my backlog? It feels like free leverage. You already automate builds, releases, and labels in Actions; bolting an agent onto that machinery looks like a weekend project.