The Agent Trust Blog
The latest trends and news in data observability and agent observability.
Most recent
Describe your orchestrator to Claude, get a real integration
ETL and orchestration is one of the most varied integration categories our customers ask for. Alongside the mainstream tools we cover natively (Airflow, dbt, Fivetran, Azure Data Factory, and more), enterprises run dozens of others: commercial platforms, cloud-native services, and homegrown schedulers. Every one of them runs pipelines that feed what’s downstream: the warehouse, the …
Read more
AI Observability
Circuit Breakers for Agents: Driving Agent Trust with Monte Carlo
Four years ago, Monte Carlo shipped circuit breakers to stop broken pipelines before bad data hit a dashboard. In 2026, the same idea has a new job: stopping an agent before it turns bad data into a confident answer. In electrical engineering, a circuit breaker exists because prevention beats detection. You do not want an …
AI Observability
How AI Anomaly Detection Catches the Problems Your Tests Miss
Every table you monitor has a rhythm. Here's how AI learns it, what happens when that rhythm shifts, and how to build a detector that keeps up.
Featured
AI Observability
New Monte Carlo Research: Two-Thirds of Orgs Ship Agents Before They are Ready to Support Them
The experimentation phase for AI agents is over. For most large enterprises, agents aren’t a pilot project or a proof of concept anymore. Teams are shipping agents live, and they are handling real workloads and touching real customer data. According to a new Monte Carlo study, nearly half of engineers and architects are already running …
AI Observability
The Memory Problem Changes When Agents Stop Waiting to Be Prompted
Moving from “what should I recall?” to “what should I notice?” and other challenges in building a proactive multi-agent system
Announcements
Enterprise AI Confidence with Atlan + Monte Carlo
The problem with your AI Agent’s confidence There’s a failure mode quietly spreading through enterprise AI deployments. You’ve built an agent. The data pipeline runs, the model responds, and the agent – answering a customer, triggering a workflow, or maybe drafting a recommendation. Everything appears to be working, up until someone notices the outputs are …
Editor's picks
AI Observability
What is AI-Ready Data? Redefining AI-Ready for Production.
Building Reliable Foundations for Data + AI Systems It’s no big revelation that data teams are being challenged to do more with AI. But while deploying an AI prototype has never been easier, operating those applications safely in production is harder than ever. Achieving high-quality data remains one of the most critical components for trustworthy …
AI Observability
The Top 5 AI Reliability Pitfalls
Hallucination—when an AI confidently generates false or nonsensical outputs—is the most notorious failure mode for AI applications. But is it really the one you need to worry about? A lot of noise has been made about hallucinations in recent months. As more companies introduce AI into production, the issue of hallucinations is perennially in the …
AI Observability
In the AI Kingdom, Experience is King
Just in case you’ve been living under a rock, the emergence of AI as a technological super-serum is upending the enterprise economy. The announcement of OpenAI’s AgentKit provided a poignant example of the volatility that AI is creating in the development world. Almost as soon as the announcement came down about OpenAI’s latest and greatest, …
Agent Trust
Read more on Agent Trust
AI Observability
Token prices are falling, so why is your AI bill going up?
There’s a clear narrative sweeping the software world these days: AI is getting dramatically cheaper. Or, to be more specific, inference is getting cheaper. Various researchers have been quantifying this: Stanford’s AI Index, for example, tracked the cost of querying a GPT-3.5-equivalent model falling from $20.00 per million tokens in late 2022 to $0.07 by …
Agent Trust
How Monte Carlo’s Reinforcement Loop Caught a Silent Issue in Our Own Troubleshooting Agent
Inside the Monte Carlo platform, our Troubleshooting Agent (TSA) works behind the scenes to analyze data and AI incidents, pinpointing root causes and suggesting fixes in real time. To keep TSA—and our other production agents—running efficiently, we rely on the Reinforcement Loop, an automated monitoring system designed to continuously evaluate agent performance, catch subtle inefficiencies, …
AI Observability
The Open vs. Closed AI Debate Misses the Point: Most Orgs Cannot Measure Either
The discussion around enterprise AI often focuses on the choice between open-weight models, like Meta’s Llama and models from Mistral, vs. closed frontier models, such as Anthropic’s Claude and OpenAI’s GPT models. While closed frontier models promise state-of-the-art reasoning without managing infrastructure, open-weight models promise sovereignty, portability, and freedom from vendor lock-in. Public commentary has …
Agent Trust
How We Measure What AI Says About Us: An LLM Visibility Audit
We built a category once and could see ourselves winning. Building the next one, we couldn’t see the scoreboard. The first category we built, we could see ourselves winning. Data observability didn’t exist as a market until we helped make it one, and the signs it was working were out in the open where we …
AI Observability
Production is Not a Bigger Dev: How Evals Leave Your Agents Unwatched
Every AI team that has shipped an agent has likely utilized a golden dataset evaluation; essentially a curated set of prompts with expected completions, a scoring harness, a threshold to clear before merge. Evals are very useful, as they let us take a highly unpredictable system and produce a scalar to gate a release on. …
AI Observability
Root Cause is Half the Job; Remediation Agent Ensures Every Analysis Ends in a Plan
When a monitor fires on a data table or agent, Monte Carlo streamlines the investigation process for you via our Troubleshooting Agent. It gives you a root cause, the evidence behind it, and a verification checklist. The last step in the resolution process still relies heavily on human input: an engineer still has to decide …
Data Observability
Read more on Data Observability17 Valuable Use Cases for Automated Data Lineage
Learn how today's data teams apply automated lineage to boost productivity, reduce time to incident resolution, and more.
Download
Data Observability
What Is an AI Trace? A Practical Guide to Tracing LLMs and Agents
Your AI agent just answered a customer’s question. The request came in, the system processed it, and a response went out. All of your signals are green, indicating that latency was normal, no errors were thrown, and your HTTP response codes are clean 200s. The answer it gave, however, was also completely wrong. This is …
AI Observability
Saying bye-bye to BI
One of the casualties of the race to agentify everything has been BI. At Monte Carlo we’ve seen usage drop to a third of what it was at the start of the year. This is down to end users now asking their questions of their favourite LLM (Claude in our case) either directly or through …
Data Observability
Stop Cleaning Up Your Clickstream Data. Let Claude Ship It Clean.
Every product team has the same recurring nightmare. A PM opens Mixpanel to answer a simple question — how many users completed onboarding last week — and finds three events that could plausibly mean “completed onboarding”: Onboarding Complete, onboarding_finished, and Completed Setup. None of them is documented. Two of them stopped firing in March. The …
Data Observability
Agent Health in practice: How we caught a stale model in our own Troubleshooting Agent
One of the things I believe most strongly about building AI agents: the best way to understand what your agents actually need is to run them on your own products. That’s the spirit behind our internal testing and iteration program where we use our own products to make our platform better; think of it as …
Data Observability
Monte Carlo brings native Agent Bricks observability to Databricks — zero instrumentation required
Ahead of Databricks Data + AI Summit, Monte Carlo is thrilled to launch native observability support for agents built on Agent Bricks. Agent Bricks already writes MLflow trace data to Unity Catalog Delta tables as part of its standard operation. Monte Carlo now reads those traces directly through your existing Databricks connection — no SDK …
Data Observability
Data trust used to come after the fact. With Claude, it ships with your code.
Data teams have always wanted quality and reliability to be a built-in property of how data gets produced and consumed — not a separate chore bolted on after the fact. The whole point of data observability has been to shrink data downtime — the periods when data is wrong, missing, or otherwise inaccurate — by …
AI Observability
Read more on AI Observability
AI Observability
The 18 Best AI Observability Tools in Sep 2026
Whether you're monitoring a handful of models or managing AI at enterprise scale, you need AI observability tools. Let's dive into it.
AI Observability
Token prices are falling, so why is your AI bill going up?
There’s a clear narrative sweeping the software world these days: AI is getting dramatically cheaper. Or, to be more specific, inference is getting cheaper. Various researchers have been quantifying this: Stanford’s AI Index, for example, tracked the cost of querying a GPT-3.5-equivalent model falling from $20.00 per million tokens in late 2022 to $0.07 by …
Agent Trust
How Monte Carlo’s Reinforcement Loop Caught a Silent Issue in Our Own Troubleshooting Agent
Inside the Monte Carlo platform, our Troubleshooting Agent (TSA) works behind the scenes to analyze data and AI incidents, pinpointing root causes and suggesting fixes in real time. To keep TSA—and our other production agents—running efficiently, we rely on the Reinforcement Loop, an automated monitoring system designed to continuously evaluate agent performance, catch subtle inefficiencies, …
AI Observability
The Open vs. Closed AI Debate Misses the Point: Most Orgs Cannot Measure Either
The discussion around enterprise AI often focuses on the choice between open-weight models, like Meta’s Llama and models from Mistral, vs. closed frontier models, such as Anthropic’s Claude and OpenAI’s GPT models. While closed frontier models promise state-of-the-art reasoning without managing infrastructure, open-weight models promise sovereignty, portability, and freedom from vendor lock-in. Public commentary has …
AI Observability
LLM Evals: What They Are and How to Get Started
TL;DR: Imagine hiring someone for a critical role, letting them start the job, and never once checking their work. Most companies would never operate this way with a human employee, yet that’s effectively how a lot of teams have shipped their first LLM-powered features. They build, deploy, and hope for the best. As enterprises have …
AI Observability
Prompt Versioning: Why Your AI Prompts Need the Same Rigor as Your Code
If your team is building anything powered by LLMs, there’s a good chance your prompts have already changed a dozen times since launch. Maybe someone tweaked a system message to fix a tone problem, or maybe an engineer added a new instruction to stop the model from hallucinating a feature that doesn’t exist. Perhaps even …
Data Platforms
Read more on Data Platforms
Data Observability
Stop Cleaning Up Your Clickstream Data. Let Claude Ship It Clean.
Every product team has the same recurring nightmare. A PM opens Mixpanel to answer a simple question — how many users completed onboarding last week — and finds three events that could plausibly mean “completed onboarding”: Onboarding Complete, onboarding_finished, and Completed Setup. None of them is documented. Two of them stopped firing in March. The …
Data Platforms
Built for the enterprise, ready for AI: Under the hood of Monte Carlo’s platform updates
The enterprise data and AI stack is heterogeneous by design Enterprise data stacks don’t fit into one cloud, one network, or one security review template — and they’re not going to start. Monte Carlo has 400+ enterprise customers — Nasdaq, Salesforce, and American Airlines among them — and few share the same architecture: multiple public …
Cheat Sheet: A Data Leader's Guide to Data Metrics
Access the must-have metrics today's data leaders use to measure data quality, platform ROI, team productivity, and more.
Download Your Copy
Data Observability
How to make Claude a trusted analyst for your whole company
Every data leader is being asked the same question right now: “Can’t we just point Claude at our warehouse and let everyone ask their own questions?” The naive version works for about a week. Then two execs ask the same question and get two different numbers, Claude joins the wrong tables and answers confidently anyway, …
Data Platforms
What is a Data Platform and How Do You Build One?
A data platform is a central repository and processing house for all of an organization's data. Here's how to build an awesome data platform.
Data Platforms
Open Source Business Intelligence Tools
Typically, an open-source BI tool is a limited version of another commercial product, or there may be additional, complementary tools to purchase.
AI Observability
What Is Model Context Protocol (MCP)? A Quick Start Guide.
You might not consider scalability a critical limitation of enterprise AI—but development velocity is undoubtedly at the top of executive agendas this year. Nearly every SaaS tool today comes with some sort of AI feature to expedite something or other—and that’s mostly a good thing. AI is unlocking new capabilities for teams of all sizes, …
AI Culture
Read more on AI Culture
AI Observability
Token prices are falling, so why is your AI bill going up?
There’s a clear narrative sweeping the software world these days: AI is getting dramatically cheaper. Or, to be more specific, inference is getting cheaper. Various researchers have been quantifying this: Stanford’s AI Index, for example, tracked the cost of querying a GPT-3.5-equivalent model falling from $20.00 per million tokens in late 2022 to $0.07 by …
The Ultimate Guide to Data Product Management
Learn how to build, manage, and scale reliable data products in our latest how-to guide, written by and for data product managers.
Download
Agent Trust
The EU AI Act: Are You Prepared for What’s Next?
Given the plethora of LinkedIn posts on the subject, if you deploy a general purpose agent or other AI system to the EU market, you are likely aware that the majority of EU AI Act Article 50 transparency rules went into effect on 2 August 2026. At a high level, Article 50 requires providers and …
AI Culture
Inside Monte Carlo’s GTM Hub: How We Run our Revenue Team on AI Agents
With the proliferation of AI across businesses for internal use cases, teams are quickly spinning up agents to take on many of the tasks that humans used to do. With that inevitably comes some operational chaos. Walk into almost any go-to-market org today, for example, and you will find the same thing we found when …
AI Culture
What Is an AI Observability Engineer? 5 Key Skills, Responsibilities, & Tools
Quick Answer An AI observability engineer monitors, troubleshoots, and improves the reliability of AI systems in production including the data pipelines, models, and agents involved in the stack. Where a data engineer builds pipelines and an AI/ML engineer builds models, the AI observability engineer makes sure both keep working as intended once they ship. As …
Agent Trust
Building autonomous agent trust: RL, an agent fleet, and comprehensive observability
For many organizations, getting agents to successfully run in production, particularly to the extent that they can be trusted to be completely autonomous, seems like an insurmountable challenge. Agents look great in pilots, but once they are deployed live, issues inevitably emerge. Production is unpredictable; agents have to operate in conditions that cannot be anticipated …
AI Culture
Monte Carlo’s Enterprise Platform Updates: Coverage and Control Below the Agent Layer
Our enterprise customers are shipping agents in production at scale, and that raises the bar on everything underneath them. An agent is only as reliable as the data it reads and the guardrails on what it’s allowed to do with it. That’s why we continue to strengthen and expand the capabilities of our platform. Read …
Data Reliability
Read more on Data Reliability
Data Observability
The Ultimate Guide To Data Lineage
Data lineage is a must-have feature of the modern data stack, yet we're struggling to derive value from it. Here's why and how we can fix this.
Data Reliability
Data Contracts 101: What They Are, Why They Matter, and How to Implement Them
Data contracts aren't in-depth legal documents, rather they codify data needs and schemas upfront to ensure transparency and build trust between teams.
2023 Modern Data Leader's Playbook
Stay up-to-date with the latest technologies, trends, and processes shaping modern data management.
Access Today
Data Observability
The New Dictionary of AI Reliability
As the modern data + AI stack grows more complex, so does the language. We put together this field guide to the terms defining this new era of end-to-end observability.
Data Reliability
Monitoring Through Disaster: Why Multi-Region Hosting Matters
Monte Carlo's multi-instance architecture, multi-region failover support, and EU hosting capabilities give customers essential flexibility and resilience.
Data Reliability
Data Remediation: Ensuring Data Quality and Reliability in Modern Data Pipelines
Ensure data quality and reliability in modern pipelines with effective data remediation. Learn the key steps you should follow in the data remediation process.
Data Reliability
Data Munging That Actually Works
Data never shows up ready for analysis. This guide walks you through data munging to clean messy datasets with practical Python examples.
Data Discovery
Read more on Data Discovery
AI Observability
Saying bye-bye to BI
One of the casualties of the race to agentify everything has been BI. At Monte Carlo we’ve seen usage drop to a third of what it was at the start of the year. This is down to end users now asking their questions of their favourite LLM (Claude in our case) either directly or through …
Data Discovery
6 Tips For Better SQL Query Optimization
Check out these 6 tips for better SQL query optimization and increased database performance.
Data Discovery
Star Schema vs. Snowflake Schema: Which One Should You Use?
When should you use a star schema vs. snowflake schema? Learn the pros and cons of both.
Data Discovery
The Best Snowflake Orchestration Tools
Most Snowflake orchestration tools just send SQL to Snowflake and call it done. Here's which tools actually use warehouse scaling, native tasks, and cloning—and why it matters for cost.
Data Discovery
Data Catalog vs. Data Dictionary: 5 Essential Differences
Both are tools, but use the wrong one and things get messy. Learn the essential differences between data catalog vs. data dictionary and each tool's purpose, contents, and usage.
Data Discovery
Tired of Broken Pipelines? Here’s How ETL Orchestration Can Help
Learn how ETL orchestration works, compare top tools like Airflow, Prefect & Dagster, and discover best practices to fix broken data pipelines once and for all.
Case Studies
Read more on Case Studies
Case Studies
How the New York Jets Are Advancing the Ball for an AI Forward Future with Monte Carlo
Background The New York Jets’ ownership, led by Chairman Woody Johnson, set a mandate to build “the best AI decision-support infrastructure in all of sports.” To lead it, the Jets created an innovative and entirely new role: Iwao Fusillo, hired in 2026 as Chief Data and Analytics Officer, with a remit spanning both football analytics …
How Much Does Bad Data Cost You?
Do you know the cost of data downtime? This guide will help you calculate the cost of bad data for your company.
Download
Case Studies
Morningstar Accelerates Validations and Resolutions for Key IP With Monte Carlo
How Morningstar is using Monte Carlo to maintain its high data validation and reliability standards with more efficiency, clearing the way for ever-more sophisticated models and new analytics and innovations.
Case Studies
How Axios Is Delivering Reliable AI with Agent Observability
How Axios controlled cost and improved alerting while monitoring agent inputs and outputs.
AI Observability
How Pilot Flying J Scales Production AI with Monte Carlo
Learn how the team at Pilot Flying J reliably scales AI in production with data + AI observability.
Case Studies
How T. Rowe Price Reduced Time To Resolution 83% with Monte Carlo
Read how Monte Carlo helped T. Rowe Price, "materially improve data reliability, reduce data issues, and strengthen business confidence in provided data."
Case Studies
How M&T Bank Scales Trusted Data With Monte Carlo
Best practices and lessons from a top U.S. super-regional bank serving millions of customers.
Announcements
Read more on Announcements
Announcements
Enterprise AI Confidence with Atlan + Monte Carlo
The problem with your AI Agent’s confidence There’s a failure mode quietly spreading through enterprise AI deployments. You’ve built an agent. The data pipeline runs, the model responds, and the agent – answering a customer, triggering a workflow, or maybe drafting a recommendation. Everything appears to be working, up until someone notices the outputs are …
Announcements
Data Observability, ML Model, and Agent Observability In A Single Pane Of Glass
Monte Carlo launches Machine Learning Metric Monitors, becoming the first platform to monitor data, ML models, and agents.
Announcements
Discover All Cortex Agents In A Single Click: Agent Observability for Snowflake Intelligence
Monitor the reliability of all your Cortex Agents with Agent Observability.
Announcements
From Insight to Action: Operations Agent is now Generally Available
Smarter monitoring, faster investigations, and effective resolution - all in one place.
Announcements
Monte Carlo Named to G2’s Best Software Products of 2026
We're thrilled to be a 2026 G2 Best Software Awards winner!
AI Observability
Debug Problematic Agent Behavior 4x Faster with Agent Observability
Trace Explorer makes it easy to filter and navigate each step of an agent run to identify the root cause of issues.