Agents
-
Research
CordisBench shows where agent harnesses should replace reasoning with verification
CordisBench finds that models struggle with growing harness lifecycle interactions even when software can compute the tested state consequences exactly.
-
New Models
GPT-6 Astra launches with critical cyber capability and staged access
OpenAI launches GPT-6 Astra with staged access, Critical cyber classification and runtime safeguards that can interrupt agent tasks.
-
Agents
Zoho Catalyst 3.0 gives coding agents controlled access to cloud infrastructure
Catalyst 3.0 connects coding agents to cloud infrastructure through MCP, with scoped permissions, audit logs and reversible changes.
-
Agents
GitHub lets Copilot approvals count toward merge requirements
Copilot code review can now count as a required pull-request approval, with enterprise, repository and path controls around where AI approval applies.
-
Agents
GitHub extends Copilot content exclusions to app and CLI, but gaps remain
Copilot app and CLI now respect content exclusions, while GitHub still documents gaps in IDE agent modes, symlinks and remote filesystems.
-
Agents
Cursor moves agent execution on-prem, but its control loop stays in the cloud
Cursor Self-Hosted Machines move tool execution into customer infrastructure while inference and planning remain in the Cursor cloud.
-
Research
HarnessDev shows why self-improving agents need release gates
HarnessDev shows why evolving AI agent harnesses need hidden-task validation, executor checks, runtime evidence and rollback before promotion.
-
Agents
CrowdStrike moves AI agent security from prompts to runtime execution
CrowdStrike Falcon Guardian links prompts and tool calls to endpoint actions, adding runtime controls for enterprise AI agents.
-
⚙️ The Executable Policy Layer: Why AI Governance Dies Before Runtime (4/10)
How runtime policy decisions, enforcement points, state-aware rules and evidence turn AI governance from documentation into operational control.
-
🏗️ Why Most Teams Stall at Action Controls: The Hidden Systems Behind Real Agent Governance (3/10)
Why identity and approval controls are not enough for AI agents, and how knowledge, execution and evaluation systems make governance operational.