JN

Jerry Nixon

Things Jerry Says on Podcasts

Works as a Principal Program Manager on Microsoft's SQL Server team, focused on the Data API builder, and holds Microsoft MVP recognition. He also teaches as a professor at Colorado Christian University and writes for Microsoft's Azure SQL developer blog. He describes the risk of handing database queries to AI models as confident, wrong answers that get acted on, with no intent behind them at all. Guests on developer podcasts covering .NET and data tooling, including The Modern .NET Show.

Where to Find Them

Jerry Nixon has been a guest on The Modern .NET Show (2 times) .

Recently: “Giving AI Agents Safe Access to Your Data: SQL MCP Server with Jerry Nixon” on The Modern .NET Show (July 2026); “Designing APIs Like a Pro: Lessons from Jerry Nixon on Data API Builder and Beyond” on The Modern .NET Show (October 2025).

What They Said

“…It's not really a question or a category of maliciousness. You know, it's not like the model is trying to ruin your business. The model just got it wrong and now it is ruining your business.” — Jerry Nixon, The Modern .NET Show

Nixon had spent several minutes on why handing database queries to a non-deterministic model is dangerous — not because it might delete your data, but because it can hand back a confident, wrong answer you then act on. His closing line reframes the risk: the model isn't malicious, it just gets it wrong while you make decisions on the result.

The Modern .NET Show · 2026-07-24 Permalink → Listen →
The Modern .NET Show Around 21:43 into the episode
Jerry Nixon

So let's dive into it because this is a deep subject. It really is.

Jamie Taylor

…of grepping and sending HTTP requests and trying to connect to the database yourself or anything like that. Use this tool. The tool knows how to do it. It will help you to achieve that solution. Just to sort of level set, is that kind of, am I on the right, the right tracks as to what an MCP is?

Jerry Nixon

…talking about is a query that gets executed against my data, returned back as a response that looks correct and is presented to me by a model that is disproportionately confident in that data when it's wrong. And now I look at that data and I make decisions in my business thinking that this data that I am using is revealing information inside of my data set when actually it is misleading me. It's not really a question or a category of maliciousness. You know, it's not like the model is trying to ruin your business. The model just got it wrong and now it is ruining your business.

Jamie Taylor

If I can just pause there then and talk about what I'm hearing then. So the SQL MCP Server allows me to have my agent via the LLM interact with the data plane of my data. And say, for instance, if I have an internal tool that I release out to the data people or maybe the people in my business who…

Jerry Nixon

That's right.

Jamie Taylor

That can talk to the database. And I could say in natural language, get me, for instance, the sales by category for the last quarter and create a just get me those, right? Put it into a JSON table so I can display it on screen. So then maybe I can export that to, say, Excel or something like that…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

Collections They Appear In