Nov 20
Agentic Data Quality: Why Your Data Needs It Twice
Agentic data quality means two things: quality for the data agents use, and agents that fix data issues. Here's why you need both, and how to start.
Monte Carlo · Company blog · 8.1 a month · 86 posts since Feb 9, 2021
Nov 20
Agentic data quality means two things: quality for the data agents use, and agents that fix data issues. Here's why you need both, and how to start.
Nov 20
A step-by-step agent observability example: how one bad answer was traced across context, performance, behavior, and output to its root cause, and fixed.
Nov 19
A large language model (LLM) is a neural network trained on large amounts of text to understand and generate human language.
Nov 19
An AI model is a system trained on data to recognize patterns and make predictions or generate content. A model takes an input, like a transaction, an image, or a question, and produces an output, like a fraud score, a label, or a written...
Nov 19
Tool calling, also called function calling, is how a large language model asks an application to run a function, such as querying a database, calling an API, or searching documents, and then uses the result in its answer.
Nov 19
A vector database is a database built to store embeddings, which are numeric representations of the meaning of text, images, or other data, and to quickly find the embeddings most similar to a query.
Nov 19
A schema change is any change to the structure of a dataset, such as a column being added, removed, renamed, or given a new data type.
Nov 18
An agent tells a customer their order shipped. It didn’t. Every service returned 200 OK, latency was normal, and the logs show a request in and a response out.
Nov 18
Your LLM app has been live for a month. Latency is under a second, the error rate is zero, and uptime is perfect. Meanwhile, a product manager forwards a screenshot: the bot told a customer about a discount that ended in March.
Nov 18
A customer asks whether they can still return a jacket. A chatbot would answer from what it was trained on. An AI agent looks up the order, checks the return policy table, sees the purchase was 34 days ago, notices the customer is a...
Nov 18
Two teams build the same support agent on the same model with nearly identical prompts. One answers correctly nine times out of ten. The other confidently quotes a shipping policy that changed in the spring.
Nov 18
A customer types “can I send this back?” Your help center never uses that phrase. It talks about the “return window” and the “refund policy.” Keyword search finds nothing.
Nov 18
A support agent is about to paste a customer’s full account number into a chat reply. An output check catches the pattern, redacts it, and logs the event. The customer never sees it. That’s a guardrail doing its job. Now a different run.
Nov 18
An agent tells a customer that refunds are available for 60 days. The answer is well written, confident, and even links to the refund policy. The policy says 30 days. Nobody hacked anything and nothing crashed.
Nov 16
An LLM firewall has a simple job. It sits between the people using your AI agent and the large language model (LLM) behind it, checking every message going in and every reply coming out so that it can block anything that looks like an...
Nov 16
Imagine you hire a bank teller. You check their references, confirm they have the right keys, and make sure they can’t touch the safe-deposit boxes. Then you turn off the cameras and never count the cash.
Nov 16
A support agent tells a customer they qualify for a refund they don’t. The trace exists. The source table exists. In the post-incident review, three teams point at each other: the AI engineers who built the agent, the data team that owns...
Nov 14
Every developer working with large language models has learned to fear context degradation. This manifests when an agent, which started off sharp, gradually loses the thread as a conversation lengthens, forgetting instructions, fixating on...
Nov 13
Across the enterprise, organizations are standing up some form of an AI platform team, whether under the banner of “AI enablement” or an “AI Center of Excellence.” As we’ve explored in previous posts on industry structures and team...
Nov 13
Most teams learn their agent is broken the same way: a customer tells them. In Monte Carlo’s 2026 survey of 260 agent builders and leaders, 52% of builders said they find out about production issues through customer or user complaints.
Nov 12
AWS re:Invent is right around the corner! If you’re planning to attend, you’re in exactly the right place. Our team has pulled together everything you need to know to make the most of the event: from key sessions and our booth, to...
Nov 9
What Is Agentic Observability? How It Works and Where It Stops A support agent tells a customer their refund is $40. The real number is $140. Every dashboard is green: the request returned 200, latency was normal, no tool threw an error.
Nov 5
Most enterprises envision their human-agent teams will be made up of two layers. On top, there is a small group of people planning, orchestrating, and managing. Underneath, there is a growing workforce of agents executing the work.
Nov 5
The tech industry is having a bit of a deja vu moment right now. As AI transformation spreads rapidly, large organizations are increasingly leaning on human expertise to drive it forward.
Nov 5
Tokenmaxxing had a big year. Dictionary.com named “maxxing” its 2026 Word of the Year, and the token utilization trend wave was part of the reason.
Monte Carlo's own blog on montecarlodata.com, found by the daily check.
AI and agents (43), Databases (2), Product and company (1) in the last six months.
Across Glyph:awards·calendar·marketplaces·Paydays·problems·quadrant·Changefeed·socials·standards