Added a dedicated Auto-review page covering the reviewer lifecycle, trigger conditions, failure behavior, and local or managed configuration.
Also updated the Agent approvals & security and Sandbox docs so they explain more clearly how Auto-review relates to the sandbox boundary.
Fetched May 12, 2026
Admins can now define which Workspace Studio steps and starters are available to users by domain, organizational unit, or group level, with…
Google · Workspace
New guide compares guardrail placement options in Amazon Bedrock Agents versus self-orchestrated agents using Datadog AI Guard, demonstrate…
Datadog · Datadog BlogUpdated the Codex enterprise governance guide with more detailed coverage of the Analytics dashboard charts, data export options, and enter…
OpenAI · CodexOpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agent…
OpenAI · Product Releases