-
What I Got Wrong Before I Started: Five Posts, One App, Four Rebuilds
When I started this series, I had three assumptions I was fairly confident about. All three were wrong — in ways that turned out to be the actual point of the series. — read more
-
Enterprise AI Cloud Adoption: The Patterns Survive. The SDKs Don’t.
I spent four posts building enterprise AI by hand. Then I looked at AWS AgentCore and found I’d reinvented about half of it. AI correctness held at 72% across every configuration. No managed service improved that number. The value landed in compliance, operations, and procurement — not better answers. Post 5 of Enterprise AI from… — read more
-
A Skills Roadmap for Engineers Going AI-Native
You don’t need a new job title to work in AI. The skills that make an engineer “AI-native” are learnable from wherever you’re starting — here’s the roadmap, and what actually changes. — read more
-
I Expected AWS to Win on Retrieval. It Went 0 for 5.
I migrated Policy Pal to AWS Bedrock and ran 50 queries to measure exactly what transfers cleanly, what transfers with caveats, and what doesn’t transfer at all. The most marketed feature caused the most friction. Here’s the honest breakdown. — read more
-
LOW Confidence Isn’t a Bug. It’s Your Policy Telling You Something. Path to entry level enterprise AI policy management.
Post 3 of 5 in “Enterprise AI from the Inside Out” TLDR: When Policy Pal returned LOW confidence on a simple expense question, the problem wasn’t the AI — the judgment had never been encoded. Enterprise AI policy management requires three separate systems: one to generate policy (Council), one to serve it (Policy Pal), and… — read more
-
Git to 42: a vision for self-evolving AI agents
I asked Claude a question about version control. It went somewhere neither of us planned. Here’s the conversation, lightly edited. Act One: The craftsman’s question Why git can’t track what AI agents learn Will: You are an expert in frontier AI and technology development. Give me perspective on the gap between git-based tracking versus skill… — read more
-
Eight Enterprise AI Patterns. AWS Covers Five.
Post 2 of 5 — Enterprise AI from the Inside Out TLDR: I built a local Python demo of eight enterprise AI patterns — no AWS account needed. Five map to Bedrock equivalents. Three expose gaps Bedrock doesn’t cover yet. The most interesting finding had nothing to do with the code. Jump to the Policy… — read more
-
Why Internal Tools Are the Enterprise AI Entry Point
Post 1 of 5 in “Enterprise AI from the Inside Out” TLDR: 76% of enterprises now buy AI off the shelf — up from 53% two years ago. Enterprise AI internal tools are still the fastest entry point — but only if you treat them as a platform, not a demo. Engineering leaders who skip… — read more
-
I Broke My NanoClaw Fork So I Had to Actually Learn How It Works
TLDR: I added voice to my NanoClaw fork the wrong way first — patched directly into core, it worked, upstream shipped an update, everything broke. Getting unstuck forced me to actually understand agentic AI plugin isolation: three-way merging, runtime isolation, idempotent reapplication. Here’s that journey, including the TLS wall, a one-character VAD bug that took… — read more
-
Standup Buddy: What 10 Hours of Voice AI Taught Me About Engineer Communication
TLDR: Built a voice AI engineer communication tool that detects when engineers are stuck through tone and conversational signals — not just words. 8th place at AI Agents Waterloo. GitHub here. Skip to Demo Results if you want to see the personas in action. The Voice AI Engineer Communication Problem Nobody Talks About Until It’s… — read more
