Chapter 01
Enabled AI across an enterprise
When Shopify's CEO mandated an AI-first operating model, I didn't wait for a playbook. I started small, proved value, and let adoption pull the work across the org. Each tool built on the last.
Click to expand
Shopify / Proof of Concept
"While You Were Away" Agent
Catch-up time cut from a full day to 30-60 minutes. Proactive risk follow-ups from day one back.
+
Shopify / Team Adoption
Six-Week Executive Reviews
~80% reduction in manual reporting prep across all teams.
+
Shopify / Cross-Org Adoption
Program Briefs Agent
Timeline cut from 6-8 weeks to 3-4 weeks.
+
Shopify / Self-Serve Data
MCP-Powered Dashboards
Delivery time cut from 3-4 months to 1-2 weeks. Early data influenced roadmap decisions before priorities locked in.
+
Shopify / Multi-Agent System
Performance Review Agent
30 hours per cycle down to 5-6 hours. Other leads adopted and customized it.
+
The through-line: Start small, prove value, let adoption spread. Treat AI agents as internal products with teams as customers. Measure quality, feed corrections back, improve over time.
~80%
Manual reporting reduced
~50%
Review processes streamlined
5-6 hrs
Down from 30 per cycle
Chapter 02
Built AI for clients
After Shopify, I went independent. First real engagement: a skincare brand drowning in repetitive customer questions and manual clinic management.
Click to expand
Client engagement / B2B skincare
Multi-Agent Customer Service System
~5 hours saved weekly at 98% lower cost. Non-technical staff run both agents themselves.
+
Consulting — Construction Client
AI-Powered Bid Review Agent
15+ hours/week saved. Team shifted from doing analysis to validating it.
+
Chapter 03
Built my own products
Client work proved I could ship production AI for someone else. Next: building products I own, where I'm the user, the designer, and the operator.
Click to expand
Solo product / Music discovery SaaS
reDiscover
Live. Paying users.
+
Solo product / AI-powered job search
Signal
Live. In beta with early users.
+
Chapter 04
Went deeper
I'd shipped production AI across enterprise, client, and personal contexts. But I knew there were gaps. At Shopify, I'd consumed MCP servers (Looker, Salesforce, GitHub, Figma) but never built one. I'd built individual agents but never orchestrated multiple agents with genuinely different jobs working as a pipeline.
So I mapped the skills I wanted to develop and applied each one to real work. Not tutorials. Not demos. Real systems running in production right now.
Click to expand
Skill: MCP Server as Producer
Foundation Server
Every session makes the next one better.
+
Skill: Multi-Agent Orchestration
KB Quality Agent
Fully automated weekly scans. Staff review through the admin dashboard they already use.
+
Skill: Adversarial Multi-Agent Code Review
Ralph-Lisa Loop
All 91 findings remediated across reDiscover and Signal. Both codebases production-hardened.
+
Now it compounds
The Foundation Server isn't just another project. It's the layer underneath everything else. Lessons from one project surface when they're relevant in another. The KB Quality Agent proved the architecture is portable. One system. Every session makes it smarter. Every project feeds the next.
Teaching it: Delivered a session on context engineering for my Sidebar AI circle — walking through the evolution from ad-hoc copy-paste to structured context systems. The entire session prep was built in a single sitting from loaded foundation context. The system demonstrating itself.
Principles
What I've learned
Start small, prove value, let adoption spread.
Don't mandate AI adoption. Build one tool, show the results, let demand pull it across the org.
Bring the tool to the user.
If people have to learn your platform, you've already lost. Build around how they already work.
Human-in-the-loop by design.
The propose/review/approve pattern isn't a safety net. It's an architecture choice that builds trust and catches things AI misses.
Model selection by task.
Strongest model where reasoning quality matters. Cheapest model where the task is mechanical. Know which is which.
Not all AI is expensive.
Cheap models can produce high-quality output. Test and try before defaulting to the most powerful option. The right model for the task is often smaller and faster than you'd expect.
Agents that improve over time.
Track edit rates. Feed corrections back. If output quality isn't trending up, the system isn't learning.
The system should compound.
If every session starts from scratch, you're leaving value on the table. Capture what you learn. Make it accessible. Let it build.
Build the second opinion into the system.
Don't trust single-pass output at scale. The adversarial audit runs two AI reviewers against each codebase and surfaces findings neither catches alone. The conversation evaluator checks every chatbot response for grounding and flags issues before customers notice. The KB agent monitors the website and proposes updates when content drifts. The pattern is the same: automate the review, make it structural, don't rely on someone hopefully noticing.