Who spent all the tokens? Real-time, run-scoped cost control for AI agents
Budget caps and gateways can’t stop a runaway AI agent mid-run. TokenOps enforces one shared, run-scoped budget in real time, before the bill arrives.
🌿 Agent Terrarium: Bringing AI agents to life
An open-source desktop companion app, this weekend project questions whether working with agents should simply feel transactional.
Tool search: Finding the right tool at the right time
As you add more tools to AI agents, the advantage comes from making the right tools discoverable at the right moment without paying the full cost of exposing everything upfront.
From research to reality: An interview with Microsoft VP of Security Research Taesoo Kim
The leader of the new Microsoft Security FORGE (Frontier Offensive Research & Generative Exploitation) Labs, Kim takes us behind the scenes of codename MDASH and explains why a multi-model agentic approach may be the key to winning the security game.
A wind farm you can talk to: Building a real-time 3D digital twin on Microsoft Fabric
With geometry, telemetry, and language feeding into a single simulation, it’s the time spent making architectural decisions that matters.
How my dev machine built 1,111 word-processing features and forgot to add a ruler
What happens when one of the founders of Writely sets up a complex agentic loop and lets it run largely independently in pursuit of an online, collaborative word processor?
Where the agent decides, and where the tools actually run
Where does a judgment step go inside an app that already has a deterministic state machine, a tool surface, and a CI pipeline?
The durable asset is the loop you own. OpenEnv is its protocol.
In the agentic AI era, the real durable asset isn’t the model you rent. It’s the learning loop you own. And OpenEnv is the right protocol for reinforcement learning environments (RLEs).
Introducing the Agentic Resource Discovery specification
Developed in collaboration with GoDaddy, Google, Hugging Face, and others, this new open specification lets AI clients find resources relevant to a given task automatically.
Information-flow control: Moving toward secure, autonomous agents
A deterministic security system, information-flow control (IFC) offers a promising path towards secure and autonomous agents.
Watch Satya Nadella on a No Priors x Latent Space crossover special
Long-time listener, first-time caller. Dive into a detailed conversation that breaks down the news from Build and what it means for the developer ecosystem.
Five ways we’re confusing AI capability and AI reality—and how to bridge the gap
Microsoft partnered with Lectures on Tap to present Build on Tap, where CTO Kevin Scott addressed a growing perceptual disconnect in the tech industry.
Introducing Command Line, and the new rules for builders
Agentic AI is here, and the traditional software development lifecycle is broken. Get ready for what comes next by shifting your workflows and your mindset.
Composing a new platform for agent-first devices
New interaction technology enables new types of computers.
Microsoft Scout: From personal project to enterprise-ready personal agent
Omar Shahine and Jakob Werner talk shop about building an always-on, enterprise-secure, personal AI agent.
The agent optimization loop and how we built it in Foundry
By reframing the challenge of AI agent optimization, we arrived at a new understanding of what moves the needle and built out a plausible and novel solution.
Grounding at scale: Engineering the retrieval system for the agentic web
Today at Build, we introduced Web IQ, a new grounding system for the agentic web.
Turn specs into evals for any agent with ASSERT
Adaptive Spec-driven Scoring for Evaluation and Regression Testing (ASSERT) is an open-source framework for converting natural language behavior requirements into executable evaluations of AI models and agents.
Introducing Agent Control Specification: Portable runtime governance for AI Agents
ACS is an open, vendor-neutral standard that defines how runtime governance is applied across the agent lifecycle, independent of framework, runtime, or policy engine.
Disposable agents, durable memory: The architecture behind Squad
What we learned building Squad: a file-backed, human-led agent team where memory is inspectable, orchestration is explicit, and governance moves from prompts into code.
Inside the Microsoft Agent Framework: How we designed a layered SDK
Agent loops, workflows, and harnesses let developers choose the right architecture to support simple assistants and complex multi-agent systems.
Introducing Microsoft’s EngThrive framework: Understanding developer productivity in the agentic AI era
By looking at Speed, Ease, Quality, and Thriving, EngThrive aims to make it faster and easier for engineers to do great work.
How Excel got agentic: An interview with Microsoft Director of Science Mukul Singh
We sat down with Microsoft Director of Science Mukul Singh to learn how his team leveraged two years of research to bring agentic capabilities to Excel and beyond.