Microsoft Australia
Sydney, Australia
Joined April 2008
- Tweets3.3K
- Following150
- Followers280
- Likes699
Pinned Tweet
Setting up Azure Chat is now as simple as running these Azure CLI commands:
1. Initialise: azd init -t microsoft/azurechat
2. Deploy: azd up
Hopefully @savostrowski is proud of AZD UP as we are!
github.com/microsoft/azurech…
#ai #azureopenai #openai #azureai #azurechat
Thivy retweeted
Spoiling the reveal: nearly 50% less expensive, 40% faster thanks to fewer turns, and right at the edge of frontier intelligence.
Copilot Fusion Max is the real deal and we’re only getting started. Go give it a try because we’re making it 30% off through the end of
November.
GitHub has released Copilot Fusion in GitHub Copilot, which orchestrates between Anthropic and OpenAI models. It scores 2 points below Opus 5.5 in Claude Code at half the Cost per Task in the Coding Agent Index
GitHub describes Copilot Fusion as a runtime orchestration system, which selects and coordinates models to optimize performance, cost, and latency for each task. Copilot Fusion chooses between a number of models from Anthropic and OpenAI, including Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra, and GPT-6 Sol. We benchmarked its max setting in GitHub Copilot CLI in the Artificial Analysis Coding Agent Index v2.0.
Token costs are charged based on the underlying models used to complete a request.
Key takeaways:
➤ Cost-efficient for near-frontier performance: Copilot Fusion in GitHub Copilot costs $5.59 per task, versus $11.42 for Claude Code with Opus 5.5 (max). Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high) scores 62 at $8.00 per task.
➤ Slight lead in Terminal-Bench 4.0: The Coding Agent Index v2.0 weights its three constituent benchmarks equally. Copilot Fusion in GitHub Copilot leads Terminal-Bench 4.0 with a score of 71. It ranks third on FrontierCode in the chart at 51, behind Claude Code with Opus 5.5 (max) at 56 and Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high) at 54. Its SWE-Atlas-QnA-AA score lags at 57, between GPT-6 Astra in Codex and Gemini 4 Argon in Antigravity CLI.
➤ Half the token use of Opus 5.5 in Claude Code: GitHub Copilot Fusion used 7.2M tokens per task in the Coding Agent Index, approximately half of the tokens used by Claude Opus 5.5 in Claude Code, and 30% less than Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high).
Thivy retweeted
GitHub Agentic Workflows are now generally available for automating reasoning-based tasks inside GitHub Actions.
• Define automation in natural language Markdown, compiled into Actions YAML
github.blog/changelog/2026-1…
Thivy retweeted
GitHub commissioned and funded this evaluation by @ArtificialAnlys. Full results and methodology: artificialanalysis.ai/agents…
Thivy retweeted
GitHub has released Copilot Fusion in GitHub Copilot, which orchestrates between Anthropic and OpenAI models. It scores 2 points below Opus 5.5 in Claude Code at half the Cost per Task in the Coding Agent Index
GitHub describes Copilot Fusion as a runtime orchestration system, which selects and coordinates models to optimize performance, cost, and latency for each task. Copilot Fusion chooses between a number of models from Anthropic and OpenAI, including Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra, and GPT-6 Sol. We benchmarked its max setting in GitHub Copilot CLI in the Artificial Analysis Coding Agent Index v2.0.
Token costs are charged based on the underlying models used to complete a request.
Key takeaways:
➤ Cost-efficient for near-frontier performance: Copilot Fusion in GitHub Copilot costs $5.59 per task, versus $11.42 for Claude Code with Opus 5.5 (max). Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high) scores 62 at $8.00 per task.
➤ Slight lead in Terminal-Bench 4.0: The Coding Agent Index v2.0 weights its three constituent benchmarks equally. Copilot Fusion in GitHub Copilot leads Terminal-Bench 4.0 with a score of 71. It ranks third on FrontierCode in the chart at 51, behind Claude Code with Opus 5.5 (max) at 56 and Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high) at 54. Its SWE-Atlas-QnA-AA score lags at 57, between GPT-6 Astra in Codex and Gemini 4 Argon in Antigravity CLI.
➤ Half the token use of Opus 5.5 in Claude Code: GitHub Copilot Fusion used 7.2M tokens per task in the Coding Agent Index, approximately half of the tokens used by Claude Opus 5.5 in Claude Code, and 30% less than Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high).
Thivy retweeted
🚀 Discover what’s new in GitHub Copilot in @code!
From running agents across devices to comparing model results and customizing your agent workflows, explore the latest updates from @github Universe 2026.
Checkout what's new: aka.ms/VSCode/144
Happy Coding!
Thivy retweeted
Building powerful long running agents requires a powerful agent harness. Now it's easier than ever inside of @Microsoft Foundry with the new Microsoft Copilot harness in Foundry Agent Service! 🧑💻
Build and govern a powerful agent powered by the same harness optimized across GitHub, Microsoft 365, and Copilot scenarios for agents that can accomplish complex and long running enterprise tasks -- no code required. All secured and governed in Foundry 🔐
Check it out:
devblogs.microsoft.com/found…
Thivy retweeted
One of my more controversial bets: the AI feed will be the form factor of 2027!
Most people don’t know what to prompt, and they won’t prompt their way into complicated agentic workflows. With chat, we ask users for digital labor: figure out what AI can do, explain the task, provide the context, repeat. That’s a lot to ask if we want billions of people using agents every day.
Meanwhile, people already spend hours in feeds. Twitter, Instagram, LinkedIn. They know how to scroll, discover something useful, and act on it.
An intelligent system that knows you should bring you the next useful action. Here’s the email you need to answer, already drafted. Here are the latest sales numbers, with an update ready to send to your team. You approve, edit, dismiss, or jump into chat to go deeper. That’s how people will discover what agents can do, without having to invent a prompt first.
And you can put ads in a feed, one of the biggest business models on the internet. A system that understands your plans can recommend a relevant restaurant, product, or service, clearly labeled as sponsored. You get a reason to come back every day, useful work ready to approve, and a business model to fund the agents doing it.
Thivy retweeted
What did you get done this week?
We shipped all of Office in Copilot.
Starting today, the full power of Microsoft Office is rolling out to the Copilot App in Frontier. We're bringing together the capabilities that your business runs on every day within Word, Excel and PowerPoint inside of the new OS for work.
This new experience supports your entire workflow, from the first prompt to the finishing touches. You can collaborate with others, use branded templates, and return to earlier iterations through version history as your work evolves. In the same workspace, you can choose from a robust library of frontier models or use the Auto router to match the right model to the task at hand.
Learn more in my blog post: techcommunity.microsoft.com/…
Thivy retweeted
Introducing Microsoft-Decision-1, our new model for fast decision-making.
It delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality.
We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.
Thivy retweeted
The GitHub Copilot SDK is no longer the CLI/SDK and is now just the Runtime/SDK.
github.blog/ai-and-ml/genera…
Privileged to work daily with the talented @stephentoub @stevensanderson @shayrojansky @MackinnonBuck @edburns @brunoborges @Scott_Addie (and now so many teams) on the shared runtime for so many products/platforms.
Thivy retweeted
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 🎉🧑💻
Thivy retweeted
A new project from GitHub Next!
Chopin is a real-time, multiplayer agentic planning environment. Designed to get your whole team aligned on the plan before you hand it off to agents.
We find our current agent planning tools feel cumbersome, static, lonely, and drown us in walls of text. We're exploring how we can make planning more interactive, shared, and visual 🖌️
It's currently an early prototype but we'll be developing it more over the coming months – and it's open source!
githubnext.com/projects/chop…
Thivy retweeted
#MicrosoftFabric Apps + Rayfin + Copilot Code puts enormous power into the hands of every copilot user, with full IT control. Super inspiring to see what our CEO is doing with all this power :)
Some more detail on the ROIC Intelligence App I built yesterday and mentioned on today's earnings call.
I took the PDF that Brian Nowak at Morgan Stanley put together for Hyperscale ROIC this week and used Copilot code (coming in our new superapp) with a single prompt + skill (/drill-me) to create the plan, then used autopilot in auto to create the full app (with history, lookups, scenarios, what-ifs, etc). And /rubber-duck to test.
And the best part is that all the artifacts are in my enterprise environment. My app is in Copilot, my code is in GitHub Enterprise; all my data pipelines/lake/semantic models are in Fabric. And everything is under Agent 365 IT/Sec/FinOps control!
So this is not about Tokenmaxxing or vibe coding. Every step of the way the rails are engineered to create value, making everything a long-term reusable asset, with governance/security, and cost controls.
This is the full system to drive business value. Disclosures: This is all pulled from public sources, and for illustrative purposes only...not financial advice! :)
Here is the app and architecture...
Thivy retweeted
Thinking Orbs, animated component library
6 types, optimized for large and small sizes, light & dark mode, playground, zero dependencies
orbs.jakubantalik.com
npm install thinking-orbs
Collaborated on this with @a_brinza who did a lot of work
Thivy retweeted
New in Copilot Cowork this month: event-triggered tasks and local browser automation.
Stay up to date with the latest in Cowork here: msft.it/6015vNGvR
ALT Microsoft Teams interface featuring coworking chat and a detailed trigger setup for task automation.
Thivy retweeted
Love this end-to-end example from @jeffhollan of what is now possible when you build long-running agents with Foundry. All now GA.
Hosted Agents in Microsoft Foundry is now Generally Available! This brings agent native compute for your agents with any framework, any language, and any model 🚀
Build with the GitHub Copilot App, connect to Microsoft IQ, run in Foundry, securely interact with Microsoft Teams, govern in Agent 365, and optimize to compound your learnings continuously -- such a valuable combo. Check out the demo / blog below to see it in action!
azure.microsoft.com/en-us/bl…
Thivy retweeted
When we launched our Community-First AI Infrastructure plan in January, we made a promise: we would meet the growing demand for datacenters without straining the resources communities depend on. Water was central to that commitment.
Today we shared our progress. Since our first datacenter designs in the early 2000s, we have improved our water-use effectiveness by nearly 90 percent. We are more than halfway to our 2030 water-intensity goal. And in FY25, we replenished more water globally than we withdrew, a milestone toward becoming water positive.
Digital growth and responsible water stewardship can move forward together, and the communities we call home should be stronger for it. @Microsoft
blogs.microsoft.com/blog/202…
ALT Infographic with a headline reading ‘Inside Microsoft’s 20-year push to cut water intensity while scaling for growth.’ A section labeled ‘By the numbers’ presents four key data points. First, a large ‘90 percent’ indicating a reduction in water use intensity since the early 2000s. Second, another ‘90 percent’ showing that Microsoft’s 2025 owned fleet runs on low- to zero-water cooling. Third, ‘2025’ noting the year Microsoft replenished more water globally than it withdrew. Fourth, ‘500 million dollars’ representing the amount invested since 2020 in more than 75 water and wastewater projects with meaningful community co-benefits. The design uses large serif typography and blue gradient backgrounds for each statistic tile.
Thivy retweeted
/impeccable is now available via experimental settings in the GitHub Copilot App!
It breathes fresh life into design that would otherwise feel AI generated. Give it a try!
.@impeccable_ai earned its way to 40k+ stars on GitHub by delivering exceptional value. Today, we are making design and quality a built-in layer for all creators: Impeccable is now a built-in skill in the GitHub Copilot app.
AI raised the floor. We’re here to help raise the ceiling.
ALT GitHub + Impeccable
