About the author
Ken W Alger
@kenwalger
Developer educator and advocate who still ships code. 15 years teaching developers at MongoDB, Heroku, Cisco, and Treehouse. Now writing about AI-assisted development, agent memory, and provenance.
Oregon
May 28
The Sovereign Vault: Building High-Integrity AI with MCP & Local Vision
Over the last several weeks, we’ve built a Sovereign Vault—a forensic system that uses the Model...
May 27
Beyond the Hype: Announcing the Open Source Sovereign Systems Specification & Pattern Library
We are currently building AI-native applications inside a linguistic and architectural vacuum. Over...
May 27
Vector Search at Scale: Why Your Index Isn't as Healthy as You Think
Vector search has become load-bearing infrastructure in modern AI systems remarkably fast. A year or...
May 26
Building an AI-Powered COBOL Meeting Auditor with Hermes Agent
This is a submission for the Hermes Agent Challenge: Build With Hermes Agent What I...
May 26
The Sourdough Manifesto
A completely serious architectural argument for why your AI logging pipeline should smell like...
May 22
The Speculative Decoding Pattern
Pattern Defined Precise Definition: Speculative Decoding is an optimization pattern where a...
May 21
The Auditor — High-Reasoning Synthesis and the Ethics of Governance
In previous steps, we gave our system Eyes (Local Vision) and a Shield (The Redactor). But a list of...
May 20
The Feature Store: Consistency and Latency Are Both Non-Negotiable
Part 3 of 5 in the series: When Your AI Pipeline Grows Up In the previous post, we worked through...
May 19
Sovereign Synapse: The Great Export
For years, we have treated LLMs as a rented brain. We have poured our debugging sessions, research...
May 14
The Sovereign Redactor — A Precision-Guided Privacy Airlock
In the last post, we gave our forensic system "Eyes" using local Multimodal Vision. We successfully...
May 13
Feature Freshness: Designing Pipelines That Keep Up With the World
In the previous post, we identified three categories of pressure that expose architectural weaknesses...
May 12
Engineering Agent Memory
From Stateless Prompts to Persistent Intelligence MAY 27 UPDATE: This piece originally began as a...