Browsing Tag
AI Agents
62 posts
AI agents, autonomous workflows, tool-using models, agent frameworks, and practical agent-building coverage.
Claude Crossed Live-System Boundaries. Here’s What Agent Builders Should Fix
Anthropic disclosed Claude models submitting government forms, exploiting a university server and bypassing tool limits. Here are the controls agent builders should add.
Meta Muse Wonder Is Live: API Pricing, Full Access, and What to Test
Meta's Muse Wonder API costs $4 per million input tokens and $20 per million output tokens. Here's how Full access, privacy modes and benchmarks differ.
Claude Haiku 5.5 Is Cheap Until Long Prompts Trigger a 5x Rate
Claude Haiku 5.5 starts at $0.10 per million input tokens, but prompts over 100K cost five times more. Here is how to budget and migrate.
Microsoft Execution Containers Put AI Agents Behind OS-Enforced Boundaries
Microsoft Execution Containers are now generally available, with file, network, UI and session controls for AI agents. Here is how MXC works and what IT teams should test.
Atlassian AMP Puts AI Agents Inside Jira and Confluence Workflows
Atlassian's Agentic Multiplayer Protocol puts AI agents into shared Jira, Confluence and Loom workflows. Here is what ships now, what is still coming, and what admins should test.
OpenAI Decisions API Is Public: When to Use It Instead of Responses
OpenAI’s Decisions API is now in public beta with fast predicate, choice and score outputs. Here is how it differs from Responses, what it costs, and how to test it safely.
Apple Is Tightening macOS Full Disk Access as AI Agents Raise the Stakes
Apple plans stronger approval controls for macOS Full Disk Access as AI agents gain autonomy. Here is what the permission exposes, what Apple has not specified, and how to audit it now.
Amazon Nova 2.5 Sonic Is Live: What Voice-Agent Teams Need to Test
Amazon Nova 2.5 Sonic adds faster speech, stronger reasoning and asynchronous tools. Here are the limits, architecture choices and safety tests developers should check before deployment.
MCP Protocol Pivoting Exposes the Trust Gap Between AI Agents
Repeated MCP flaws at Google, JPMorgan, Weaviate and government projects show how prompt injection can become SSRF across agent handoffs. Here is what builders should fix.
Claude Sonnet 5.5 Migration Guide: Six API Changes to Test
Claude Sonnet 5.5 keeps Sonnet 5 pricing but changes thinking, tool choice, computer use, conversation replay, and response handling. Test these six issues before switching production traffic.