Anthropic released Agent Skills today as an open standard in an attempt to make a “universal instruction manual” for AI agents so they can perform complex jobs consistently across different apps and platforms. Agent Skills creates a unified SKILL.md specification to define these complex agent tasks, reports TNS Senior Editor for AI Frederic Lardinois. Find out what else Anthropic released today by reading Frederic’s full post.

In other technology we’re exploring today:

• Khushboo Nigam, a principal cloud architect at Oracle, outlines a different framework for end-to-end observability that moves away from isolated telemetry silos. Instead, she advocates for integrating application traces, Kubernetes metrics and CI/CD pipeline data into a single unified view. Khushboo explains how her approach can help developers perform a root cause analysis on all the relevant factors.
• Hashbrown is a delicious breakfast staple, but it’s also now an open source agent framework that enables generative user interfaces and interactive assistants by running AI agents directly in the browser. The framework uses a specialized schema library called Skillet to support high-performance JSON streaming and incorporates a WebAssembly-based QuickJS runtime to safely execute LLM-generated code. Find out more about what the framework can do for the frontend.

The systems we rely on are inherently complex. Everything from advanced driver assistance systems (ADAS) and sophisticated medical devices to complex aerospace controls needs to be highly performant, extremely reliable, and most of all, keep us safe. The safety-critical market is massive. The automotive sector alone is projected to reach $6.9...

In this insightful webinar, GE HealthCare and Spectro Cloud joined TNS to explore how GE HealthCare leverages cloud native and edge technologies to improve care for 1 billion patients.

Join Skyflow’s CPO and Head of Solutions Engineering for a fast-paced session on securing sensitive data. They’ll share real-world customer architectures and demo how to build privacy-preserving AI, protect payment data with tokenization, and ensure data residency at scale.