Monte Carlo announced new Agent Observability capabilities that give AI and data teams unified visibility across the full lifecycle of AI agents.
Monte Carlo’s Agent Observability provides unified visibility across four critical pillars that determine whether AI agents can operate reliably in production: context, performance, behavior and outputs. By monitoring these interconnected elements within a single platform, AI and data teams can understand not only what an agent produces, but also why it produced it and whether the underlying system is operating as intended.
“AI agents are moving into production faster than most companies are prepared for,” said Barr Moses, co-founder and CEO of Monte Carlo. “The future isn’t coming — it’s already here. If you’re deploying agents without a production-grade observability system that monitors context, performance, behavior and outputs, you’re flying blind. The companies that build trustworthy AI systems will move ahead quickly, and everyone else will fall further behind.”
With Monte Carlo’s newest capabilities, enterprises can evaluate agents before deployment, monitor performance and costs in production, validate complex agent workflows and continuously assess output quality — enabling organizations to deploy AI agents with greater confidence and control.
New capabilities include:
Context: Validating the Data and Signals Agents Rely On
AI agents are only as reliable as the data and context they retrieve. Monte Carlo now enables teams to evaluate AI-generated fields directly against source data stored in their data warehouse, helping organizations verify that AI outputs accurately reflect the underlying data.
Teams can configure custom prompt-based evaluations on warehouse tables, automatically detecting errors and hallucinations before they impact downstream systems.
Expanded support for Google BigQuery and AWS Athena enables organizations building agents on GCP and AWS to implement agent observability directly within their existing cloud data environments.
Performance: Monitoring Cost, Latency and Operational Efficiency
New Agent Metric Monitors track signals such as latency, token usage, duration and error rates, helping teams detect performance regressions and operational anomalies early. Trace-level monitoring surfaces cost and telemetry across entire agent workflows rather than individual steps.
Behavior: Ensuring Agents Follow Intended Workflows
As agent workflows grow more complex, verifying that agents execute tasks as intended becomes increasingly difficult. Nearly one-third of organizations say they could not disable or roll back a harmful AI agent within minutes, and 14% say they could not do it at all, Monte Carlo’s survey found.
Monte Carlo introduces Agent Trajectory Monitors, which allow teams to validate the order, frequency and relationships between steps within agent workflows. These monitors ensure required tools are used, expected steps occur and unintended loops or skipped tasks are detected early.
This gives teams confidence that agents are operating safely within defined workflows and governance policies.
Outputs: Evaluating Agent Quality Before and After Deployment
To ensure consistent output quality, Monte Carlo now supports pre-production agent evaluations that test agents against a “golden dataset” of prompts and expected outputs before deployment.
Integrated into CI/CD workflows, these evaluations help teams detect regressions caused by prompt changes, model updates or code modifications.
In production, Agent Evaluation Monitors continuously assess output quality using LLM-based or rule-based checks, alerting teams when quality thresholds are not met.
Monte Carlo also introduced a Monte Carlo-hosted OpenTelemetry deployment option for Agent Observability in AWS. This allows organizations to onboard agent observability without deploying and managing their own OpenTelemetry collectors, reducing infrastructure complexity while enabling telemetry data to remain within the customer’s AWS environment.
The Latest
Enterprises today operate in a real-time environment where uninterrupted access to trusted data has become a baseline expectation for users, applications and automated systems. Traditional DataOps models, built on manual effort and human triage, cannot keep pace with this always active demand. AI agents are emerging as the operational backbone, ensuring consistent data availability, reinforcing trustworthiness and enabling a level of scale that manual processes cannot achieve ...
For decades, trust in the digital workplace rested on familiar signals. We trusted faces on video calls, voices on the phone, and emails that appeared to come from people we knew. These cues felt human and intuitive. They anchored how decisions were made, approvals were granted, and access was authorized. AI-powered deepfakes have quietly broken that model ...
Cloud migration was supposed to be a one-way door. For most enterprises, it turns out it isn't. Cloud data repatriation is a real and growing trend. A new survey ... finds that 89% of organizations plan to expand their on-premises infrastructure footprint over the next two years — and 75% have already moved at least some workloads back from public cloud in the past 24 months. The findings point to a broad rethinking of where data belongs ...
Over the past few years, large language models (LLMs) have revolutionized the software industry. Given their ability to excel at multi-step reasoning, LLMs have helped enterprises streamline workflows and adapt to the unknown. However, employing such models comes with sky-high costs, latency issues, and limited flexibility. In the realm of IT operations, it is generally wiser to employ smaller, domain-specific models instead ...
For years, DevOps teams operated under a simple assumption: collect enough telemetry, and you can find and fix any problem. That assumption is breaking down. Modern enterprises now operate across microservices, hybrid cloud environments, APIs, Kubernetes, and highly automated delivery pipelines. Releases happen continuously, dependencies shift constantly, and failures spread faster than teams can diagnose them ...
New Relic surveyed IT and engineering leaders from the media and entertainment (M&E) sector to understand what's working — and where challenges persist with their observability practices. The findings reveal how M&E organizations are navigating rising platform complexity, audience expectations, and AI-driven change. Below are five takeaways that stand out ...
Let me start with something I've seen play out more times than I can count. A team hits a wall with the cloud. Costs creep up, then spike. Performance starts to feel inconsistent. Someone in finance asks a simple question like "why did this double?" and nobody has a clean answer ... Maybe this isn't the right place for everything. That realization feels like a breakthrough, like you've identified the problem. In reality, you've just identified the starting line ...
In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ...
In cloud-native systems, scaling is often as simple as moving a slider. For on-premise databases, the stakes are different. Over-provisioning hardware is expensive. Under-provisioning leads to performance bottlenecks that are difficult to fix once the equipment is in the rack ...
When most people think about cybersecurity, they picture firewalls, encryption, and access controls — technical tools designed to protect systems and data. But beneath the technology lies a deeper set of principles about trust, decision-making, and resilience ... The best leaders don't eliminate risk. They manage it intelligently. And in many ways, cybersecurity offers a surprisingly useful playbook for doing exactly that ...