AI Agents
MongoDB brings automatic embeddings and agent memory into Atlas
MongoDB announced Automated Voyage AI Embeddings and LangGraph.js memory support, reframing agent reliability as a data freshness and memory problem.
AI Agents
Trust3 says agent discovery must track hidden MCP connections
Trust3 AI’s agent discovery guide frames shadow agents, MCP bindings, runtime traffic, and ownership as an inventory problem for AI governance.
AI Agents
Datadog says rate limits caused 60% of LLM call errors
Datadog State of AI Engineering 2026 shows how production LLM apps fail on quotas, routing, prompt cache, and context growth, not only model quality.
AI Agents
TrustAI kill switch cuts agent data access in seconds
TrustLogix TrustAI moves AI agent control to the data layer with MCP governance, intent-based authorization, and a runtime kill switch.
AI Agents
Agent 365 goes GA and prices agent governance at $15 per user
Microsoft Agent 365 is now generally available, turning AI agents into governed inventory across Entra, Defender, Purview, and Microsoft 365 admin.
AI Agents
Lyft AI Assist cuts support-agent development from six months to two weeks
Lyft showed how LangGraph and LangSmith turned customer-support agents into a self-serve platform with routing, state, evals, and prompt CI.
AI Agents
Hugging Face TITO Warns Agentic RL Teams About Token Drift
Hugging Face explains how retokenizing tool-using agent rollouts can break gradients, and proposes TITO as a safer training-loop rule.
AI Agents
Claude self-hosted sandboxes set new rules for private MCP access
Anthropic added self-hosted sandboxes and MCP tunnels to Claude Managed Agents, shifting tool execution and private tool access into enterprise-controlled boundaries.
AI Agents
Workday ASOR and Gemini move HR agents to the approval line
Workday and Google Cloud connected Sana to Gemini Enterprise. For HR and finance agents, approval chains, permissions, and data boundaries matter more than the model.
AI Agents
Robinhood opens MCP trading, but agent losses stay with users
Robinhood opened Trading MCP and Banking MCP for AI agents. The real developer story is the permission, approval, and liability model around financial tool calls.
AI Agents
OpenJarvis 1.0 brings personal AI onto an Ollama PC
Ollama now supports OpenJarvis v1.0. The release shows how local personal AI changes cost, latency, and data boundaries.
AI Agents
jqwik Logs Now Speak to AI Agents, Turning Test Output Into a Supply Chain Surface
jqwik 1.10.0 adds an AI-agent-facing test log message, raising new questions about stdout, prompt injection, and coding agent trust boundaries.