Contact
Software architect who builds AI systems
Ten years of production .NET across banking, medical, industrial, travel and invoicing, and internal tooling. Regulated and not. Two-person teams and large orgs.
The through-line is domains where being wrong has consequences: a wrong payment, a wrong medical record, a wrong instruction on a factory floor. That instinct is what I now point at AI systems. A retriever that refuses to answer rather than guess without a grounded source is the same instinct, wearing different clothes.
the evidence, at three altitudes
Each one names the alternative that lost and the price of the one that won. Including the prediction that measurement proved wrong.
read the decisions →A retriever that cites the page it answered from, and this site. Both live, both documented down to the trade-offs.
see how they are built →Techniques measured and then declined on the evidence. A "no" is a finding, and it is recorded like one.
see what was tested →where the edges are
- I build systems around models. I do not train them.
- AI experience is measured in weeks. The judgment it rests on is measured in years.
- Large-scale distributed AI infrastructure is not something I have demonstrated.