Recent Blog Posts
View All PostsOrder Sensitivity in LLM Decision Models: The Flashlight That Became a Solar Calculator
A practical retrofit for choice-order sensitivity in LLM decision models, using isolated scoring, relational comparison, and tested serving evidence.
aimachine learninggemma
Laya on AWS Lambda - A Curiosity-Driven Experiment with a Decision Model
Running the 421M-parameter Laya decision model on AWS Lambda with CPU-only PyTorch. What broke on ARM64, where the cold start really goes, warm latency, Banking77 accuracy, and how it compares with BitNet and EmbeddingGemma on Lambda.
aws lambdaserverlessmachine learning
Expectation Constructs: The Missing Primitive in Agentic AI
Expectation Constructs are a focused unit of agent work that defines what to produce, how it is judged, how retries are bounded, and what context moves forward—a unifying primitive for reliable agentic AI.
aiagentic-aiai-agents
Tech Stack
☁️AWS
☁️Azure
💻C#
💻JavaScript
💻TypeScript
💻.NET
🔄Angular
🚢Kubernetes
📦Containers
🧩Microservices
🗄️SQL Server
🗄️Cosmos DB