Amy Kate Boyd

Foundry Developer Relations Lead in CoreAI @ Microsoft. I chat about AI, Data Science and Machine Learning 😊👩🏼‍💻⭐️ Opinions are my own

[Amy Kate Boyd @AmyKateNicho]

Good morning from #MicrosoftFrontierTour #London ☀️ Prepped behind the scenes yesterday, today we're live!

Join me: 🛠️ 12:45 Optimize agents with Microsoft Foundry & #GitHubCopilot (BRK330) 🧠 14:55 Building context-aware agents with #MicrosoftIQ (BRK240)
https://t.co/KV9jxoHujQ

[Marlene Mhangami @marlene_zw]

Had so much fun getting to demo during @satyanadella’s keynote in Paris today 🇫🇷 Showed a live walkthrough of building an autopilot in Python with Foundry!

I was on the Pareto frontier of stress with this live demo, but thankfully the demo gods were in a good mood🥳

[Amy Kate Boyd @AmyKateNicho]

Building with #HuggingFace or #openmodels ?

Today I’m joined by Jeff Boudier, VP of Product at Hugging Face, for #ModelMondays as we get into Hugging Face + managed compute.

Bring your questions 👀

⏰ 1:30 PM ET / 6:30 PM UK
🔗 https://t.co/s62VKJcWb6

[Amy Kate Boyd @AmyKateNicho]

@MSFTMechanics More hands on options check out @nitya workshop on this! https://t.co/6BUiJiZ8GS

[Amy Kate Boyd @AmyKateNicho]

@mdnazeel @jeffhollan Sure thing check out the docs here: https://t.co/cROPtbRH7T

And a hands on option from @nitya here: https://t.co/6BUiJiYARk

[Jeff Hollan @jeffhollan]

With the pace of innovation in AI, how do you make sure your agents and agent platform are equipped to evolve with the state of the art? 🤔 Check out this demo below to see how Microsoft foundry gives you automatic observability, insights, and optimization for your agent fleets - so no matter if its GPT 6 or GPT 60 you can ensure you have high quality, long running agents running securely for the enterprise. Check it out! 🧑‍💻

[Visual Studio Code @code]

📝 Your Entire Agentic AI Workflow Now Inside VS Code

In this video, we run through installation, logging to Microsoft Foundry and an overview of the UI.

[Microsoft Developer @msdev]

Introducing Microsoft-Decision-1

Our model for fast decision-making that delivers top performance in latency and quality on structured decision tasks to outperform both LLMs and other decision models.
https://t.co/jjtqKq34kV

[Amy Kate Boyd @AmyKateNicho]

@DanWahlin @dorkitude @satyanadella @hboelman @chris_noring @nitya Hi @dorkitude if you seeing 0 capacity you can request it in the Foundry Portal under Management -> Quota 👍

[Marlene Mhangami @marlene_zw]

Here's the talk! Will be experimenting!!!
https://t.co/thd2thOPIw

[Marlene Mhangami @marlene_zw]

Watched a really nice talk from the @MicrosoftAI team on how they're fine-tuning models to get better at knowledge work (like using Excel.)

I think the Jev/decision model hype is pointing to specialised, efficient models/agents being the next wave. Will link the talk below

[Mustafa Suleyman @mustafasuleyman]

We're launching the most accurate real time transcription model in the world... #1 !!!
55% faster and 60% cheaper than ElevenLabs.
Come build agents on our platform!

[Amy Kate Boyd @AmyKateNicho]

@boardyai Hope to see you there!

[Amy Kate Boyd @AmyKateNicho]

🔴 Live today: #MistralAI on #ModelMondays

➡️ Mistral OCR-4.
➡️ Building AI agents with Mistral.
➡️ Microsoft Foundry.

Fewer slides about models. More show me what I can build.

I’m hosting at 1:30pm ET 👇

Join us live https://t.co/ln7wtis2Aw

[contextmaxxing @nicholasdbrady]

Loving the video content for building agents in Microsoft Foundry.

Special thanks to @AmyKateNicho, @nitya, @carlottacaste, and @BethanyJep! Keep it rollin' 🎥🎬🤘

https://t.co/c1sIZhplyy

[Amy Kate Boyd @AmyKateNicho]

@boardyai Yep live demo of using Mistral in Foundry and then the OCR4 model in action 👍

[Amy Kate Boyd @AmyKateNicho]

Less talking about models. More building with them.

I’m hosting #Mistral on #ModelMondays next week.

We’re getting hands-on with:
→ Mistral OCR-4
→ Building AI agents with Mistral
→ #MicrosoftFoundry

Join us live https://t.co/ln7wtis2Aw

[Jeff Hollan @jeffhollan]

Microsoft Foundry is the best platform for running agents in the enterprise - and one reason is the observability and governance features to keep your agent within the bounds you define 🔐🔎

Long running agents can reason, act, and use tools to help transform so many parts of a business - but doing so responsibly means you need to be able to confidentially answer: What can it access? What can it influence? Where can data go? Can I reconstruct what it's doing? Can I control and budget costs?

Check out the demo below to see how Foundry provides a platform to answer all of these questions for you, and gives you a slick agentic developer experience to get it all up and running faster than ever before 🎉🧑‍💻

[Amy Kate Boyd @AmyKateNicho]

None of these quotes are really about Gen AI 'features'.
They're about: Engineering decisions
The conversation has shifted from: "Can we build agents?" to "How do we run them safely, reliably, and cost-effectively in production?"
AI is an engineering discipline.

[Amy Kate Boyd @AmyKateNicho]

As host, I had a weirdly privileged view of #AgentCon #London. I got to hear every session, audience question, and hallway conversations. Flicking through my notes afterwards, these were the lines I'd highlighted ...

#AgentCon #MicrosoftFoundry #DevRel #GlobalAICommunity

[Amy Kate Boyd @AmyKateNicho]

📝 "Don't ask whether a model is better. Ask whether it's better for your workload."
📝 "Stop token-maxxing. Start value-maxxing."
📝 "Too many tools can be as big a problem as too few."