Releasesby GlyphAnalytics API (Public preview): report on the health of the data behind your agents, from your AI tool
The Monte Carlo Analytics API is now in public preview, allowing users to query data health, alert status, and cost metrics directly from AI tools via the Monte Carlo MCP server.
Also shipped Nov 4, 2026Monte Carlo in November 2026 →
[Launched] Generally Available: Azure Database for PostgreSQL stable REST API version 2026-10-01
The Azure Database for PostgreSQL Flexible Server REST API version 2026-10-01 is now generally available, introducing new capabilities for maintenance, immutable backups, and encryption.
Twice the included embedding tokens through December 31
Pinecone is doubling the included monthly embedding tokens for Starter and Builder organizations through December 31, 2026.
Gemini Enterprise: Switch between teams in the mobile app
The Gemini Enterprise mobile app now supports switching between multiple teams without re-authentication, and allows renaming or removing teams from the list.
Compare AI agent changes with Online Experiments in Agent Observability
Datadog Online Experiments allows engineers to test AI agent changes against production traffic. It enables comparison of response quality, cost, latency, and error rates.
Postmortems End of Life Completed
The Postmortems feature has been retired in favor of the upgraded Post-Incident Reviews in the PagerDuty web UI.
MongoDB CDC connector for ClickPipes is now generally available
The MongoDB CDC connector for ClickPipes is now generally available. It supports parallel snapshotting, structured ingestion into typed columns, and provides lag and resource metrics.
More from Monte CarloEvery Monte Carlo release →
Match dbt Cloud runs by warehouse account, host or database
Monte Carlo now allows dbt Cloud integrations to match runs based on warehouse account, host, or database fields. This improves lineage and alert accuracy for environments where multiple connections share the same warehouse.
Monte Carlo's Terraform provider is now on the OpenTofu registry
Monte Carlo has published its Terraform provider and agent modules to the OpenTofu registry, enabling users to manage Monte Carlo infrastructure as code using OpenTofu.
Your agents’ end-user ratings, tied to the trace behind each answer
Monte Carlo now tracks end-user feedback for Snowflake Cortex and Databricks AI/BI Genie agents, displaying ratings and comments directly on traces.
Rate the issues Bayes finds through the Reinforcement Loop
Users can now provide feedback on issues identified by Bayes, Monte Carlo's AI agent. This allows users to ignore irrelevant issues and flag false positives, helping the agent improve its focus on actionable problems.
Agent summaries now show how conversations went, and every metric opens the records behind it
Monte Carlo's agent summary tab now includes conversation metrics such as duration, error rates, and token usage. Users can drill down from these metrics to view the underlying traces and conversations for improved observability.
REST API v2 (Public preview): onboard Monte Carlo from your AI tool, Terraform or a script
Monte Carlo's REST API v2 is now in public preview, enabling automated onboarding and deployment of collection agents via scripts, Terraform, or AI tools.
Scope domains to individual custom agents
Monte Carlo now supports scoping domains to specific custom code agents. This allows administrators to restrict user access to traces, conversations, and issues associated with particular agents.
Filter dbt Cloud events by environment
Monte Carlo now allows filtering dbt Cloud events by environment. This enables production accounts to ingest only production runs, ensuring that alerts and lineage accurately reflect the production state.