Obsidian expands AI agent security with runtime policy enforcement
www.helpnetsecurity.com — Obsidian Security introduces a runtime policy engine to govern AI agent actions across enterprise apps, coding tools and gateways.
Agent Orchestration
Agent orchestration is the software architecture that plans, routes, and supervises the execution of work by artificial intelligence agents. Truncated covers workflow frameworks, multi-agent coordination protocols, tool integration methods, and operational reliability tools.
Inkbox has launched hosted agents, allowing AI agents to run on Inkbox and have their own email address and phone numbe…
How Workday Built an Enterprise-Scale AI Agent Platform with LangGraph and LangSmith
www.langchain.com — See how Workday used LangGraph and LangSmith to build an internal AI agent platform that cut prototype time from months to less than a day and compliance needs.
Agent Substrate: Advancing Kubernetes for Agents at Scale
developer.nvidia.com — AI agents spend most of their time idle, waiting on a human prompt, a tool result or a model response. Kubernetes wasn’t built for that. Running one Pod per session holds memory for sessions that aren’…
Long-horizon agents and durable execution
martinfowler.com — How to build long-horizon agents that survive failures: what durable execution handles, and what it leaves to the design of the harness.
This startup raised $20 million to keep AI agents in line with more AI agents. Read the pitch deck.
www.businessinsider.com — WhiteMatter says more AI agents are the key to controlling AI agents. Read the pitch deck the startup used to raised $20 million to back its vision.
Lumbra gets $25M in backing to help intelligence community deploy reliable AI agents
siliconangle.com — Lumbra gets $25M in backing to help intelligence community deploy reliable AI agents - SiliconANGLE
The Biggest AI Agent Risk Is The Workaround Nobody Approved
www.forbes.com — AI agents can complete assigned tasks and still cross a line no one authorized. Security teams need to see the execution path, not just the outcome.
AI agents shouldn't grade their own work
www.cio.com — Recent AI incidents show why CIOs need enforceable limits on agent actions and independent evidence before calling the work complete.
Why AI Agents Are Repeating 2019's Microservices Mistake
www.oreilly.com — Microservices changed how we build software by breaking large applications into smaller, independently deployable services. That made systems easier to develop
Perplexity Teammate can be used like a world-class chief-of-staff / executive assistant.
I tried OpenClaw and Perplexity Computer, but ChatGPT Dots finally feels like a personal assistant
XDA — This is what I thought AI assistants were supposed to be
The Agent Management Function: A New Capability For The AI-Native CIO
Forbes — As agents take on more execution pathways, humans will remain responsible for orchestration, judgment, exception management and accountability.
Moving From Prompting to Agent Loops
bitbytebit.substack.com — Whatever your role in building software, understanding how agent loops work is key to finding your place in the new world
Agents are going to be used increasingly by other agents.
AWS launches agentic AI Kiro bots with memory and support for recurring development jobs
Agents Are Going Async
langchain.com — Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.
Kihan launches Constitutional Computing to bring enforceable authority to enterprise AI agents
GamesBeat — Kihan announced its Constitutional Computing math-based architecture designed to make AI governance enforceable at the point of execution.
Container orchestration for AI: Latest trends at KubeCon
SiliconANGLE — Container orchestration is evolving for AI through OpenShell, a Kubernetes-native secure agent runtime, ahead of KubeCon in Salt Lake City.
US Bank Regulator Issues First AI Framework as Banks Battle Rogue Agents
Decrypt — The OCC's first examiner guide weighs autonomy and financial harm, and directly addresses outside AI agents.
Dismiss email signup
Subscribe to 
The top AI news in your email delivered each morning. Choose categories