Shayne Boyer

Building & leading Azure dev tools @microsoft — azd, @code, @azure, and the DevEX layer. @OpenJSF Board. Husband, father. Opinions usually wrong, but mine.

[Shayne Boyer @spboyer]

@cinnamon_msft Is it a “Me Mona” or a “Mona Me”?

[Alex Volkov @altryne]

.@satyanadella just put the whole "water" debate to rest.

Datacenters run on a closed loop cooling system, the water usage of a datacenter for an entire year is roughly equivalent to a usage of 1 restaurant!

[Pierce Boggan @pierceboggan]

Introducing the GitHub Copilot app, the desktop home for agent-native software development on GitHub

https://t.co/A7thHEMhWD

[David Fowler @davidfowl]

Check out the new aspire skills repository!
https://t.co/YOw3IUh58T

Learn more about them here:
https://t.co/5UI04Nd6kq

There are skills to add aspire to any existing application or deploy to any supported target!

Try them out!

#aspiredev

[Shayne Boyer @spboyer]

@pierceboggan @github 😲

[Shayne Boyer @spboyer]

@burkeholland

[Shayne Boyer @spboyer]

@davidfowl Windows AI Phone!

[Shayne Boyer @spboyer]

a few icons that are filling my day now with GitHub App

[Shayne Boyer @spboyer]

waza: Go CLI for AI agent skill evals. v0.9.0 adds A/B baselines, pairwise judging, tool-constraint graders, and auto skill discovery. CLI or azd extension.

Star it if you're building skills and want to track where this goes.
https://t.co/BeHptuwPIh

[Josh Cook | Microsoft MVP @FlowAltDelete]

Opus 4.8 in Excel already 🙌 🤯

[Pierce Boggan @pierceboggan]

Claude Opus 4.8 is now rolling out to @code, Copilot CLI, and Copilot app developers!

[Shayne Boyer @spboyer]

@jasondoesstuff @Ferrari @marshal New version look like a Porsche Taycan

[Shayne Boyer @spboyer]

@davidfowl fix -> run -> fail -> repeat.

I have asked for years to be able to run actions local.

[Shayne Boyer @spboyer]

Useful AI skill loop:
waza init
define YAML test cases
waza run --discover

Three commands from zero to a benchmarked skill. Low enough setup to use early, not after a week of wiring.

What's the first skill you'd benchmark?
https://t.co/BeHptuwPIh

[David Pine @davidpine7]

Working on Aspire 13.4 to use the new aspire-skills repo:🚀 thanks for the collaboration @spboyer: AI agents + AppHost guidance = distributed apps that don't need a support ticket after deployment. you're welcome 🤓

https://t.co/QlJGxSFNDj

#aspire @aspiredotdev

[Shayne Boyer @spboyer]

More GitHub App 🔥. Was planning across multiple projects, asks to send each project their specific plan. Sure no problem...

[Shayne Boyer @spboyer]

@ileppane @Yif_Yang Agree with the complimentary @Yif_Yang mentions here. I also built Sensei a while back for skill improvement, token optimization and compliance. https://t.co/ieGlCDiiaV

[David Fowler @davidfowl]

I want developers to embrace filing issues with agents.

[Shayne Boyer @spboyer]

@steipete @toddanglin Should give Sensei a shot - https://t.co/6oCavwuSfN

[Shayne Boyer @spboyer]

Most eval frameworks make you fit their shape.

waza auto-discovers skills with --discover, defines suites in YAML, and lets you plug in custom graders or tool constraints for your domain.

What's the eval you wish existed but doesn't?
https://t.co/BeHptuwPIh