Showing archive results for May 2026

May 28, 2026
Post comments count0
Post likes count4

Improve your agentic developer tools by grounding in Microsoft Learn

Pieter de Bruin

Development workflows span terminals, IDEs, background agents, and custom assistants. What matters is whether they draw from the same current source. Learn MCP Server gives any MCP-compatible agent direct access to current Microsoft documentation - one endpoint, nothing to install, no authentication required. What does that look like in practice...

AIMicrosoft for DevelopersGitHub Copilot
May 27, 2026
Post comments count0
Post likes count1

How AI coding agents actually use your technology

Waldek Mastykarz

You ship an SDK, a CLI, an API, and developers use it. Now AI coding agents use it too, except they use it differently than humans do. Most of the time you have no idea what's actually happening between "developer types a prompt" and "agent generates code with your technology." Is the agent reading your docs? Is it calling your MCP server? Is it ig...

AI
May 21, 2026
Post comments count0
Post likes count3

How to improve AI coding agent support for your SDK, API, or CLI

Waldek Mastykarz

AI coding agents use your SDK, API, or CLI, but often get it wrong. The stack has layers you can't change and one you can: agent extensions. Learn how to measure whether yours are helping or hurting.

AI
May 19, 2026
Post comments count6
Post likes count7

Agentic-Agile: Why Agent Development Needs Agile (Not Just Prompts)

Daniel Epstein

"A bad system will beat a good person [or agent] every time" ~Dr. William Edwards Deming (with apologies) I started vibe coding by writing prompts (often dictated into my phone), refining them with an agent in M365 Copilot, and creating handoff files to use with GitHub Copilot CLI. The results were predictably non-deterministic. Prompt-driven d...

AI
May 5, 2026
Post comments count0
Post likes count0

Azure Cosmos DB Conf 2026 Recap: Lessons from Production

Mark Brown

A team was running at 100% RU utilization. Throttles were compounding into retries. P99 latency was degrading. The assumption was obvious: provision more throughput. They didn’t. Instead, they found a single logical partition absorbing more than 80% of traffic. After fixing the data model—without scaling the database—RU utilization dropped to...

Microsoft for DevelopersDeveloper Events