GitHub Copilot review effort has a dial. Agent adoption has a counter
GitHub added Lite and Balanced Copilot review effort plus third-party agent usage metrics. Here is how to control review depth without mistaking activity for value.
Read more
GitHub added Lite and Balanced Copilot review effort plus third-party agent usage metrics. Here is how to control review depth without mistaking activity for value.
Read more
LangChain's hosted Deep Agents runtime is now public beta. Here is what it manages—and the memory, identity, tool, trace, and schedule policies teams still own.
Read more
California's AI transparency duties became operative August 2. Here is the provider threshold, disclosure system, platform calendar, penalties, and builder checklist.
Read more
Claude Code sessions can now exchange plain-text messages. Here is how delivery, permissions, remote replies, held messages, and administrative controls work.
Read more
Burp AT keeps scope, tool access, approvals, and the activity record in the Burp layer. That is the right boundary for an AI security agent—but the beta still needs testing.
Read more
Tools directory
Editorial shortlist from the tools directory — tools worth opening twice.
From the newsroom
Microsoft's Project Perception routes cyber tasks across specialized agents, models, verifiers, and people. Its reported numbers justify a test—not blind trust.
Open storyThree evergreen guides plus the tools directory — the fastest way into Musthave.AI.