Contextual Policies in Omnigent: Using session state to better govern AI agents
Databricks just introduced contextual policies in Omnigent to manage AI agents using session state. This allows for better governance and control over how agents operate based on their context.
More in Agents
The /wayfinder Skill: Navigating the “Fog of War” of Planning
Latent Space just launched the /wayfinder skill to help users navigate complex planning scenarios. This tool aims to simplify decision-making in uncertain environments, making it easier for users to strategize effectively.
smolmachines / smolvm as a sandbox for untrusted Python & JavaScript
smolmachines just launched smolvm, a sandbox for running untrusted Python and JavaScript code safely. This allows developers to test and execute potentially harmful code without risking their main environment.
Domain and publish date filters for Web Search on AgentCore
AWS just added domain and publish date filters for Web Search on AgentCore. Users can now refine their search results more effectively by filtering based on specific domains and publication dates.
Asynchronous patterns for calling Amazon Bedrock AgentCore agents in serverless pipelines
AWS just introduced asynchronous patterns for calling Bedrock AgentCore agents in serverless pipelines. This update allows developers to integrate AI agents more efficiently into their workflows, enhancing scalability and performance.