Microsoft

Implementing Least Privilege for AI Agents Enhances Security

As AI agents gain autonomy, enforcing strong identity, access, and auditing controls is essential to maintain security. Microsoft emphasizes the importance of least privilege principles for AI tool binding.

Why it matters: Ensuring AI agents operate with minimal necessary permissions reduces risks of unauthorized actions or data breaches. Robust identity and access management helps maintain control over increasingly autonomous AI systems.

AsyncAPI npm packages compromised to deliver malware via CI/CD workflows

Threat actors compromised AsyncAPI npm packages and exploited trusted CI/CD workflows to distribute malware through import-time payload delivery. Microsoft Security Blog provides an analysis of the attack chain and recommended defenses.

Why it matters: This supply chain compromise highlights vulnerabilities in widely used developer tools and the risks of automated CI/CD pipelines. Understanding the attack helps developers and organizations strengthen their security posture against similar threats.

Reader impact: Teams using AI at work may want to compare this against current productivity and review workflows.

Final article in series on improving AI coding agent evaluations

The eighth article in Microsoft's series on Agent Experience (AX) discusses how to effectively evaluate AI coding agents and improve their integration with technology. It covers controlling the agent stack, measuring extension impact, and iterating for better results.

Why it matters: Understanding how to properly evaluate AI coding agents helps developers ensure these tools work correctly and efficiently with their systems. This leads to more reliable AI-assisted coding workflows.

Reader impact: Teams using AI at work may want to compare this against current productivity and review workflows.

GPT-5.6 Powers Microsoft 365 Copilot for Enhanced Productivity

Microsoft 365 Copilot now uses GPT-5.6, delivering stronger AI capabilities across Word, Excel, PowerPoint, Chat, and Cowork. This update enables faster and higher-quality work within these applications.

Why it matters: Upgrading to GPT-5.6 enhances the AI assistance in widely used productivity tools, potentially improving user efficiency and output quality. It reflects ongoing advancements in integrating AI models into everyday software.

Let’s Learn GitHub Copilot App – Free Virtual Training Event

Join us for a free online event series kicking off July 16 to learn how to get started with the GitHub Copilot App! The post Let’s Learn GitHub...

Flint: AI-powered visualization language for expressive charts

Flint is an open-source visualization language that enables AI agents to generate expressive charts from compact, human-editable specifications. It offers a balance between ease of writing and visual quality.

Why it matters: By leveraging AI to enhance chart expressiveness without sacrificing simplicity, Flint can improve data visualization workflows. This approach helps users create more insightful visuals with less effort.

The hidden variables in your agent eval

This is the seventh article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can’t control in the agent stack, how to measure whether your extensi...

Reader impact: Teams using AI at work may want to compare this against current productivity and review workflows.

Not all model upgrades are upgrades

A new model drops with lower per-token pricing and better benchmarks. You switch. A week later someone asks why the agent is burning 12x more tokens on the same task while producing worse output. We ran 150 agent tasks across 15 scenarios on two models, Cl...

What AI benchmarks are not telling you

This is the sixth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can’t control in the agent stack, how to measure whether your extension...

SkillOpt: Training AI Agent Skills Without Changing Model Weights

SkillOpt introduces a method to treat AI agent skills as trainable parameters, enabling skill improvement through training rather than manual editing. This approach enhances agent behavior reliability without altering the underlying model weights.

Why it matters: By converting skill editing into a training process, SkillOpt addresses the common failure point of manual skill modification in AI agents. This can lead to more consistent and dependable agent performance in various applications.

Memora Enhances AI Agents' Memory with Scalable Context Retrieval

Memora introduces a scalable memory system for AI agents that separates storage from retrieval, improving efficiency in handling long and complex tasks. This approach addresses the challenge of AI agents' limited ability to remember past conversations.

Why it matters: By enabling more efficient context management, Memora can help AI agents perform better in extended interactions and complex tasks. This advancement could lead to more coherent and context-aware AI applications.

Learn from Microsoft: Transform software development through an agentic platform

See how Microsoft is transforming software development with agentic workflows, AI-powered automation, and specialized agents across the engineering lifecycle. The post <a href="https://devblogs.microsoft.com/blog/learn-from-microsoft-transform-softw...

When the model has never seen your code

This is the fifth article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can’t control in the agent stack, how to measure whether your extension...

Rethinking cloud operations with agentic observability

Cloud operations are entering a new era as AI-driven and autonomous agents become a larger part of modern software systems. As software becomes increasingly agentic, the challenge is no longer just managing greater scale and complexity. Operators must also...

Unlocking a New Way to Build Enterprise Data Apps with Microsoft Fabric

We believe enterprise software should move at the speed of ideas. Today, we’re collaborating with Microsoft to make it dramatically easier for enterprises to build AI-powered apps in Replit and deploy them directly into Microsoft Fabric with enterprise-grade...

Data Formulator 0.7: AI-powered data analytics for enterprise data

Data Formulator introduces AI-powered analytics for enterprise data workflows. Data teams can easily bring enterprise data into an AI-ready workspace where users can explore, analyze, and visualize data with AI agents to turn raw data into actionable insig...