012026
demo
Latency budget
An interactive model for the network, compute, and rendering time hiding inside one response.
Builder · Operator · Writer
I build things for people.
I’m CTO at Caylent. This is where I keep demos, writing, talks, and the projects that deserve a URL.
Selected work
All work →022023
project
Where Next
A small application that suggests where to travel based on the countries you have already visited.
Latest writing
Full archive →POC to PROD: Hard Lessons from 200+ Enterprise GenAI Deployments, Part 1
Six lessons from moving more than 200 generative AI applications past the demo.
Agentic AI: Why Prompt Engineering Delivers Better ROI Than Orchestration
What two years of production agent work taught us about prompts, evals, and unnecessary orchestration.
Amazon Bedrock: Everything You Need To Know
A hands-on guide to model access, inference parameters, pricing, governance, security, and benchmarks.
AWS X-Ray Now Supports Amazon API Gateway and New Sampling Rules API
Today, we’re adding two new features to AWS X-Ray: support for Amazon API Gateway, making it easier to trace and analyze requests as they travel through your APIs to the underlying services, and support for centralized sampling rules in the AWS X-Ray console, SDKs, and API.
Extending AWS CloudFormation with AWS Lambda Powered Macros
Today I’m really excited to show you a powerful new feature of AWS CloudFormation, we’re calling Macros. Macros allow developers to extend the native syntax of CloudFormation templates by allowing AWS Lambda powered transformations on templates.