// PROOF OF WORK
Receipts, not slides.
Most AI-for-L&D content is prompts and promises. This page is the opposite: the decision records, failure logs, and working demos behind the tools I build — updated as the models change.
The 10× update pipeline
When a model changes, the toolkit is re-verified in hours, not weeks. Maintenance — the hidden tax of every AI toolkit — is the product.
Unfakeable proof-of-work
Two years of timestamped decision records, failure logs, and a live working system (Jarvis). Not slides — receipts.
Practitioner-manager, not a guru
17 years leading L&D and managing instructional designers at a major bank, lecturing at HIT. I ship with these tools; I don’t just talk about them.
Freshness log
Every time a model update breaks a workflow, it gets fixed or flagged within 14 days — and logged here. The public SLA record lands with the LearnOps launch. Until then, the living evidence is the writing itself:
Recent build-in-public
- I Used the Insights Command and Got a Performance Review From Claude CodeI ran /insights in Claude Code and received a personal report on 34 sessions: what worked, where I lost time, and the rules I changed.
- What Is Storybook? The UI/UX Catalog for Your WebsiteWhat Storybook is, why you should use it when building websites and applications with AI agents, how to install it, and what you can do with it.
- What Is Agentic Engineering and How Do You Build Autonomous AI Agents?The difference between a chatbot and an autonomous AI agent, what an agent harness is, which components a real agent must have, and how Claude Code Agents, OpenClaw, and Hermes differ from one another.
- What Are Skills in Working with AI AgentsIf an AI agent is a new employee, a skill is their instruction sheet: what the goal is, what information matters, how to work, where to stop, and how to verify the result is good.
- Managing the Context Window in Claude CodeThe Claude Code context window is a precious resource. Before you've typed a single word, you've already burned thousands of tokens. This guide explains why that happens and how to deal with it.
- Knowledge Gap Analysis: The Shift to Personalized Learning — A Case Study (Part 1)From generic macro analysis to personalized learning: a bank knowledge-gap project with 1,250 employees and 31,771 answers, showing how AI turns mountains of data into action.