Reading room.
Engineering blogs & AI research
A reading room from engineering teams and AI labs: titles, short feed excerpts, and links to the originals. For my own essays, explore the writing archive.
- 1359 articles tracked
- 37 sources
- Refresh scheduled daily
Sources
Do AI coding agents care about SemVer?
We gave AI coding agents the same breaking upgrade twice. Labeled 2.0.0, Claude Sonnet 5.5 checked it in all 10 runs. Labeled 1.4.3, it checked in two and often left the app broken. Nearly 1,000 runs show which agents st…
Your best AX fixes are hiding in agent trajectories
All five agent runs produced a working script, and nothing in the eval score looked wrong. The trajectories told a different story. Every run read a DLL as raw bytes to find plugin names, and three scripts would quietly…
Does ‘eval’ in the workspace path change what your agent does?
Your eval might be telling the agent it s a test before the agent reads a single instruction. Eval tools need a fresh folder for every run, and the easiest way to get one is a temp directory with a random name like /tmp/…
Publish Visual Studio Marketplace extensions securely with Trusted Publishing
Publish Visual Studio Code and Visual Studio extensions from GitHub Actions or Azure Pipelines without storing a long-lived personal access token. The post Publish Visual Studio Marketplace extensions securely with Trust…
PostgreSQL Like A Pro: Build, query, and troubleshoot without leaving VS Code
Build, query, and troubleshoot without leaving VS Code. The post PostgreSQL Like A Pro: Build, query, and troubleshoot without leaving VS Code appeared first on Microsoft for Developers .
Can a local git remote replace GitHub in your agent eval?
We swapped GitHub for a local git remote in our agent evals. Rebasing and pushing on request were unaffected, but the agent pushed on its own 11 points less often. Here's when a local remote is a safe shortcut, and when…
Introducing the Agent Experience (AX) Practitioner Playbook
AI coding agents now pick the SDK, the version, and the pattern for your developers. The AX Practitioner Playbook is our method for finding out whether they get your technology right, and for fixing the sources they rely…
From Spec-First to Enterprise-Ready: Extending GitHub Spec Kit
How presets, extensions, bundles, workflows, and governed catalogs make Spec-Driven Development adaptable at scale This article continues Spec-Driven Development: A Spec-First Approach to AI-Native Engineering, which int…
Build Azure canvases with the Canvas authoring plugin
Learn how the Canvas authoring plugin helps you build Azure canvases with Microsoft Canvas Toolkit, from a read-only starter to a working app you can inspect, test, and adapt. The post Build Azure canvases with the Canva…
What is Agent Experience (AX)?
Your agent says it's done, and the code compiles, but did it pick your technology? Did it use it correctly? Learn what Agent Experience (AX) is, how to measure it, and why the obvious fix isn't always the right one. The…
Build with Azure Canvases: a shared workspace for agents
See how Azure Canvases bring plans, code, previews, and deployment feedback together in a collaborative workspace for agent-assisted development. The post Build with Azure Canvases: a shared workspace for agents appeared…
Enabling Consistent AI-Assisted Engineering with GitHub Copilot Plugins
When an engineer or team creates useful agentic artifacts for their daily work (e.g., instructions, skills, and MCP configurations), others naturally want to adopt them when they see how those artifacts could help with t…
Get started with the GitHub Copilot app: a free, hands-on course
Learn to direct AI coding agents, review their work, and build reliable development workflows with this free GitHub Copilot app course. The post Get started with the GitHub Copilot app: a free, hands-on course appeared f…
Knowledge cutoff is a poor proxy for model capability
A model can fail on features released before its knowledge cutoff, then succeed on ones released after it. We tested hundreds of product changes and found that the date tells you far less than the work does. The post Kno…
Your AI coding agent evaluation is only as good as its sandbox
Your AI coding agent passed the eval. But did the model know the answer, or did it find it somewhere on your machine? A correct answer can still invalidate your measurement. The post Your AI coding agent evaluation is on…
Build an interview coach app with the GitHub Copilot SDK
An interview coach has to do more than ask questions. It needs to read a resume, follow up on an incomplete answer, and save enough context to give useful feedback at the end. Some of that work is conversation. Some of i…
Your work might not need the smartest model
The smartest model can cost five times more and deliver the same result, or even a worse one. See how evaluating your own work helps you get more value from your agent budget. The post Your work might not need the smarte…
Start here: Azure SQL Foundations series
Most developers I talk to aren t asking whether Azure SQL Database can handle their next app. They re asking where to start when it comes to modernization, migration, and AI in the database. If you re reading this, you r…
Try Azure SRE Agent with no always-on charges
We are happy to announce a 30-day trial experience for Azure SRE Agent. New customers can create and configure the SRE Agent at their own pace, with no charges for setup time or keeping agents ready. During the trial, yo…
The Microsoft 365 Copilot Agent’s Playbook: A Practical Livestream Series for Building Better Agents
Building on Microsoft 365 Copilot? Here s your playbook. Declarative agents are quickly becoming one of the most exciting ways to extend Microsoft 365 Copilot and bring organizational knowledge, workflows, and tools dire…
How to test agent experience changes without shipping them
Most changes you think will improve AI agent behavior won't. We tested a dozen hypotheses on a real project upgrade scenario and the majority failed. Learn how to emulate documentation, API, and MCP server changes locall…
How to test agent skills without hitting real APIs
Your agent skill calls an API. The moment you start evaluating it, every run either costs money or mutates production data. Learn how to mock APIs transparently so you can run evals without changing your skill or hitting…
Building AX evals that actually work
This is the eighth and final article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent sta…
Building AX evals that actually work
This is the eighth and final article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent sta…
Let’s Learn GitHub Copilot App – Free Virtual Training Event
Join us for a free online event series kicking off July 16 to learn how to get started with the GitHub Copilot App! The post Let’s Learn GitHub Copilot App Free Virtual Training Event appeared first on Microsoft for Deve…
Let’s Learn GitHub Copilot App – Free Virtual Training Event
Join us for a free online event series kicking off July 16 to learn how to get started with the GitHub Copilot App! The post Let’s Learn GitHub Copilot App Free Virtual Training Event appeared first on Microsoft for Deve…
The hidden variables in your agent eval
This is the seventh article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how t…
The hidden variables in your agent eval
This is the seventh article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how t…
Don’t rewrite your CLI for agents
There s advice making the rounds: replace your CLI args with a single --json payload so agents can use your tool more effectively. The thinking being, that agents already think in structured formats, and nested data maps…
Don’t rewrite your CLI for agents
There s advice making the rounds: replace your CLI args with a single --json payload so agents can use your tool more effectively. The thinking being, that agents already think in structured formats, and nested data maps…
Not all model upgrades are upgrades
A new model drops with lower per-token pricing and better benchmarks. You switch. A week later someone asks why the agent is burning 12x more tokens on the same task while producing worse output. We ran 150 agent tasks a…
Not all model upgrades are upgrades
A new model drops with lower per-token pricing and better benchmarks. You switch. A week later someone asks why the agent is burning 12x more tokens on the same task while producing worse output. We ran 150 agent tasks a…
What AI benchmarks are not telling you
This is the sixth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how to…
What AI benchmarks are not telling you
This is the sixth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how to…
Your agent already has a plan
If an agent isn t doing the right thing, the obvious move is to make the docs clearer. Add a tip, spell out the correct command, describe the right approach more prominently. You do all of that, and the agent still ignor…
Your agent already has a plan
If an agent isn t doing the right thing, the obvious move is to make the docs clearer. Add a tip, spell out the correct command, describe the right approach more prominently. You do all of that, and the agent still ignor…
Learn from Microsoft: Transform software development through an agentic platform
See how Microsoft is transforming software development with agentic workflows, AI-powered automation, and specialized agents across the engineering lifecycle. The post Learn from Microsoft: Transform software development…
Learn from Microsoft: Transform software development through an agentic platform
See how Microsoft is transforming software development with agentic workflows, AI-powered automation, and specialized agents across the engineering lifecycle. The post Learn from Microsoft: Transform software development…
When the model has never seen your code
This is the fifth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how to…
When the model has never seen your code
This is the fifth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how to…
Models don’t have preferences, they have context
You open a fresh chat, type What framework should I use for a web app? , and the model says React. You screenshot it, share it, and write Claude prefers React. It gets engagement. People nod along. A few reply with their…
Models don’t have preferences, they have context
You open a fresh chat, type What framework should I use for a web app? , and the model says React. You screenshot it, share it, and write Claude prefers React. It gets engagement. People nod along. A few reply with their…
Stop overloading your skills
You built a skill for your technology. API references, authentication flows, SDK patterns, error handling, version info, all packed into one skill. The agent calls it, gets all that context, and generates code. The kicke…
When your agent extensions fight each other
This is the fourth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how to…
Competing against yourself
You shipped a new CLI: better developer experience, modern architecture, and optimized for agents. You deprecated the old one, updated the docs, and blogged about it. Developers are migrating. Then someone asks an AI cod…
Your agent just scaffolded a project from 2020
Your agent ran a scaffold command. Project generated, dependencies resolved, no errors. Everything looks fine. Except it s based on the project structure from 2020, and neither you nor the agent noticed. How npx picks th…
Is your agent extension actually working?
This is the third article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can t control in the agent stack, how to…
Spec-Driven Development: A Spec-First Approach to AI-Native Engineering
AI has made software delivery faster, but speed alone does not guarantee better outcomes. As teams adopt AI-native development, the real challenge is keeping requirements, design, implementation, and validation aligned s…
Stop skillmaxxing, save your tokens
You built a dozen skills for your technology: authentication, CRUD, error handling, deployment, testing, monitoring. Then you installed a cloud platform bundle with 15 more covering diagnostics, storage, compliance, and…
Microsoft Build 2026 recap: vision, launches, and top sessions
Catch up on Microsoft Build 2026 with the vision lead-off, top developer announcements, and must-watch sessions across the Microsoft developer ecosystem. The post Microsoft Build 2026 recap: vision, launches, and top ses…