Releasesby GlyphCatch agents stuck in a loop with trajectory monitors
Monte Carlo added a repeats condition to trajectory monitors to detect when an AI agent makes consecutive identical tool calls with identical inputs and outputs within a single run.
Also shipped Nov 10, 2026Monte Carlo in November 2026 →
Amazon Bedrock AgentCore now offers a Web Search API
AWS launched the InvokeWebSearch API on Amazon Bedrock AgentCore, enabling direct web search execution billed at $7 per 1,000 queries.
Flagship - Evaluate Flagship feature flags from Rust
Cloudflare released an official Rust SDK (`cloudflare-flagship`) for Flagship, enabling async Rust applications to evaluate feature flags via OpenFeature with remote or in-process local evaluation.
BigQuery generative AI functions support gemini-4-carbon
Google Cloud announced general availability for the gemini-4-carbon model across BigQuery generative AI functions.
Amazon OpenSearch Service announces managed cross-Region disaster recovery
AWS introduced managed cross-Region disaster recovery for Amazon OpenSearch Service, providing continuous data replication with an RPO under one minute and RTO under 20 minutes.
Amazon Bedrock adds bedrock-runtime endpoint support for Daybreak models
AWS added support for OpenAI Daybreak Red and Daybreak Blue cybersecurity models on Amazon Bedrock runtime endpoints via US and Global cross-Region inference profiles.
Gemini Enterprise: Gemini 4 Carbon available in web app, mobile app, Workflow Builder, and AI developer tools
Google Cloud generally released Gemini 4 Carbon across Gemini Enterprise web and mobile apps, Workflow Builder, and AI developer tools with multi-region availability.
More from Monte CarloEvery Monte Carlo release →
Agent pages now open on the issues Bayes found
Monte Carlo updated agent pages to display issues found by Bayes in a dedicated view. Users can now access health, monitoring, and activity metrics through side panels without leaving the main interface.
See what your end users think of the agents you build in code, on the trace behind each one
Monte Carlo added end-user feedback tracking for code-based AI agents, attaching ratings, categories, and user comments directly to corresponding traces, runs, and conversations.
Eval datasets, curated by Bayes from your agents' real conversations
Monte Carlo introduced automated evaluation dataset generation by Bayes, creating Golden and Improvement datasets from an agent's scored conversations across intent and issue clusters.
Bayes now tracks every Reinforcement Loop fix and catches it when an issue comes back
Monte Carlo updated Bayes to track Reinforcement Loop issue statuses and automatically flag regressed issues if identical problems occur after a fix is marked complete.
Data products can now include your agents, not just their data
Monte Carlo data products now allow users to include AI agents, providing end-to-end lineage from source tables to the agent. This enables monitoring of both agent health and upstream data health in a single view.
Analytics 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.
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.