Skip to content
SJ

Sensible AI, Coding, and Everything In-Between

My mission is to empower every developer and data scientist to be successful with Artificial Intelligence, Machine Learning, and Generative AI. Also Coding. And Software. And whatever else I am thinking about.

Read the Blog About Me

Latest Posts

View all →
Fixing Mixed-Content and CORS issues at ML Model inference time with Azure Functions

Fixing Mixed-Content and CORS issues at ML Model inference time with Azure Functions

This is a follow-up from the previous post on deploying an ONNX model using Azure Functions. Suppose you've got the API working great and youwant to include this amazing functionality on a brand new website. What follows is the harrowing path…

Machine Learning Azure Functions
Troubleshooting an ONNX Model deployment to Azure Functions

Troubleshooting an ONNX Model deployment to Azure Functions

Building awesome machine learning models can be an onerous task. Once all the blood, sweat and tears have been expended creating this magical (and ethical) model sometimes it feels like getting the thing deployed will require severing another limb…

Machine Learning Azure Functions
Making Use of Unstructured Data with Form Recognizer

Making Use of Unstructured Data with Form Recognizer

Every business has their "junk" drawer (or the "share" as Bill/Karen likes to call it). Often hidden in this data wasteland are nuggets of informational gold that could revolutionize the way you do business (we hope). Turns out that the most…

Machine Learning Azure
3 Tips for Debugging Cloud Scale Machine Learning Workloads

3 Tips for Debugging Cloud Scale Machine Learning Workloads

Let's say you built an amazingly wonderful hand-crafted artisanal convolutional neural network that works beautifully on your hard-drive based dataset. You are now ready to take this masterpiece to the cloud to work on a much larger dataset on…

Machine Learning Azure
Talking about Technology

Talking about Technology

Making software is hard. Every once in a while we find some code that really helps the process. It makes our own code intelligible: almost fun! Sometimes the magical code is of our own making but often we are using someone else's code. In…

dotnet OSS

A New Position

It is appallingly wrong of me to not have written anything in over a year. One of my resolutions is to ameliorate the situation by trying to write at least one thing every month (sorry January). In this post I would like to announce that I have…

General

Up Next?

Vote →
0
Blog Post

Why Your AI Agent Forgets Everything

Agents don't just need more context. They need memory that survives the prompt. I want to explore what useful memory actually looks like in agentic systems, why most implementations are glorified note-taking, and how to build something that helps an agent get meaningfully better over time.
0
Blog Post

In AI Years, Prompty Is Ancient - And That's the Interesting Part

In a field that reinvents itself every six months, Prompty v2 does something almost suspiciously sane: it keeps the prompt format and upgrades the runtime. The result is a two-year-old .prompty file format that now speaks tools, tracing, structured output, streaming, and Python, TypeScript, C#, and Rust.
0
Blog Post

The Agentic Loop, Explained

Everyone talks about "agents," but the core pattern is much simpler than the hype: observe, reason, act, and repeat. This idea breaks down the agentic loop into its essential parts, why it matters, and where most implementations go wrong.
0
Blog Post

Guardrails, Steering, and Control in Agentic Loops

We keep asking prompts to do the job of an operating system. This idea is about the real control surfaces in agentic software - schemas, tool permissions, approvals, workflow boundaries, and runtime policies - and why the best guardrails usually live outside the model.
0
Blog Post

Why Predicting the Next Token Turns Into Intelligence

The core training objective behind LLMs sounds almost embarrassingly simple. So why does it produce systems that can reason, translate, code, and chat? I want to build the intuition from the ground up without turning it into a graduate seminar.