A newsletter by Maxim Salnikov · demo copy
Agentic Engineering in Action
Hands-on notes on building software with AI agents: harnesses, evaluation, CI gates, context supply chains and WebMCP. 12 issues, republished here to show how agentprose lets AI agents read a blog through WebMCP.
Where Is the Gate? A Practical Look at AI Engineering Systems
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…
One corpus, many harnesses: what it took to keep our AI consistent
Guest post: This edition is written by Einar Ingebrigtsen, sharing his own perspective and experience.
What I learned building 6 apps and solving 10 related engineering problems for the OpenAI WebMCP Challenge
I built six working app prototypes in a short time for the OpenAI WebMCP Challenge.
GitHub Agentic Workflows: The Five-Minute Version + Free Book
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…
Your Agent’s Context Has a Supply Chain. Manage It.
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.
Giving AI agents a real computer
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.
The Best AI Coding Model Is a Moving Target. Build a Selection System Instead
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.
The First 80% Takes Nine Minutes. The Last 20% Takes Two Days.
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.
You can't tune what you can't see: prompt‑cache observability for GitHub Copilot with OpenTelemetry
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.
Design, but with tests: an engineering approach to UX with Impeccable
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.
The model is a commodity. The harness is your advantage. A hands-on experiment with GitHub Copilot app's Canvas
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.
Stop Putting a Raw LLM in Your CI Pipeline — Put a Sandbox Around It
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
