Track your agents' spend at the rates you actually pay
Agent Observability shows the token and query cost of every trace from the AI agents you've connected to Monte Carlo. Those costs can now use your own negotiated per-model rates instead of list price.
Also shipped Oct 2, 2026Monte Carlo in October 2026 →
PagerDuty Advance team-level permissions now Generally Available
Building on team-level permissions, Account Admins can now choose which AI agents are enabled for each team. This further empowers teams to roll out AI adoption with confidence. Learn more.
AI Gateway, Web Search API - Introducing Web Search API
Web Search API is now available in beta. Web Search API lets your AI agents and applications search the Internet and ground their responses in live information, instead of guessing URLs or relying on a model's training cutoff. At launch, you can choose between three search providers: Ceramic.ai, Exa, and Linkup .
KV - Workers KV namespace jurisdictions are now generally available
Jurisdictions for Workers KV namespaces are now generally available. When you create a namespace, you can set a jurisdiction to make sure the namespace's data is only durably stored within that region. Jurisdictions can help you comply with data localization regulations such as GDPR or FedRAMP. Supported jurisdictions are eu , us , and fedramp .
Repository security advisory comments API in public preview
You can now read, add, and edit comments on repository security advisories using the REST API, including advisories created from private vulnerability reports. Until now, the discussion on an advisory was only reachable in the web UI, even though it often holds the most useful triage context on a vulnerability report.
Note : Your clusters might not have these versions available
Note : Your clusters might not have these versions available. Rollouts are already in progress when we publish the release notes, and can take multiple days to complete across all Google Cloud zones. Version 1.36.4-gke.1495000 is now the default version for cluster creation in the Rapid channel.
You can use Vertical Pod Autoscaler (VPA) with Horizontal Pod Autoscaler (HPA) to automatically optimize...
You can use Vertical Pod Autoscaler (VPA) with Horizontal Pod Autoscaler (HPA) to automatically optimize container CPU requests for workloads that scale replicas based on CPU utilization. This feature is available in Public Preview on clusters running GKE version 1.36.3-gke.1630000 or later. For more information, see Rightsize HPA workloads with VPA .
More from Monte CarloEvery Monte Carlo release →
See every request your agent couldn't answer, and what it needed
Agent Observability has a new Issue cluster, Out of scope requests. It flags every conversation where your agent couldn't answer because it was missing something: a permission, a document, a table or a tool.
Add a reason when enabling, disabling, or snoozing monitors
Updating a monitors status now includes an optional "Reason" field. (Disable, Snooze, Change Snooze & Enable) Anything you enter is saved as a comment on the monitor's Activity tab, alongside the status change, so the context behind the decision stays with the monitor. Reaso...
Measure failure rate in Custom SQL & Validation monitors
Validation and Custom SQL monitor runs can now record the total rows evaluated behind each result, alongside the rows that failed.
Define a domain in a few clicks: bulk-select assets, add a whole integration, filter scope by tag
Domain creation and editing got a rework aimed at large domains and scale. You can now add hundreds of assets at once, add an entire integration to a domain, and use tags to filter a selection.
Filter the Monitors list by database
Database is now a filter on the Monitors list, matching the filter already on Alerts and Assets.
Trace Salesforce Data 360 AI and marketing objects in the catalog and lineage
The objects that describe how your Data 360 data gets prepped for AI and pushed out to marketing are now supported in the catalog and in lineage, each with its own group in the Assets tree:
Monitor and trace lineage for Delta Sharing tables
Databricks Delta Sharing catalogs are now supported.
Trace a table back to the job and task that produced it
Job asset pages now show lineage across your ETL and orchestration integrations, including Airflow, Databricks Workflows, Snowflake Tasks, GCP Dataform, Power BI Dataflows, and custom ETL integrations.