Skip to content
Releases.

Claude Managed Agents permission policies add an auto mode

UpdateVerifiedAdded Sep 22, 2026

A new auto permission policy lets the server evaluate each agent or MCP tool call and run it, deny it, or pause for approval. agent.tool_use and agent.mcp_tool_use events now report how each call was evaluated.

Topics: AI agents, LLMs, MCP, Governance, Security

Anthropic's release notes

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More Claude Platform releases

Every Claude Platform release
DateRelease
Sep 10ant CLI 1.32.0 adds sessions connect for live Managed Agents sessions
Beta
Sep 14Messages API adds on-demand conversation compaction in beta
Beta
Sep 14Claude API input_transformations adds thinking_mismatch_allowed entries in beta
Beta
Sep 3ant CLI 1.30.0 adds ant apply to manage agents and resources as code
Update
Sep 3Per-message effort changes beta expands to Claude on Google Cloud
Beta
Sep 18Compliance API adds Claude in Chrome session transcripts in beta
Beta
Sep 1Claude Fable 5.1 launches alongside Claude Mythos 5.1 with 1M token context
GA
Sep 1Prompt cache reads on Claude Fable 5.1 and Mythos 5.1 drop to $0.25 per MTok
Pricing

Also shipped on Sep 10, 2026

Anthropic in September 2026
DateRelease
Sep 10BigQuery conversational analytics adds ML.CORRELATION in preview
Google CloudBigQueryPreview
Sep 10BigQuery ML.METRICS evaluates predictions without a stored model
Google CloudBigQueryPreview
Sep 10You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data
Google CloudBigQueryPreview
Sep 10BigQuery Data Engineering Agent integrates with BigQuery Graph
Google CloudBigQueryGA
Sep 10Using dbt artifacts for Slim CI and defer to production in dbt Projects on Snowflake (General availability)
SnowflakeSnowflakeGA
Sep 10External secret providers (Preview)
SnowflakeSnowflakePreview

Weekly: the week's data and AI releases, Tuesday mornings.