Agent Observability access without access to raw agent content
UpdateUnverifiedAdded Sep 24, 2026
Raw agent content , prompts, completions, tool inputs and outputs, transcripts, and judge rationale , now has its own permission. A user without it still gets the full operational product: summary metrics, span structure, monitors, and alerts.
Topics: AI agents, Security, Observability
More Monte Carlo releases
Every Monte Carlo release| Date | Release | Type |
|---|---|---|
| Sep 9 | Arrange your agent's Summary page the way your team reads itunverified Update | Update |
| Sep 9 | Track agent performance across whole conversations, not single turnsunverified Update | Update |
| Sep 9 | Extend your Monte Carlo permissions to alert actions in Slack and Microsoft Teamsunverified Update | Update |
| Sep 9 | Monitor Snowflake Cortex agents by versionunverified Update | Update |
| Sep 18 | Trace Salesforce Data 360 AI and marketing objects in the catalog and lineageunverified Update | Update |
| Sep 18 | Monitor and trace lineage for Delta Sharing tablesunverified Update | Update |
| Sep 18 | Trace a table back to the job and task that produced itunverified Update | Update |
| Sep 18 | See each of the semantic views your agent actually usedunverified Update | Update |
Also shipped on Sep 9, 2026
Monte Carlo in September 2026
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.