The prototype is the argument.
Production is the proof.
I'm the one on the team who takes a vague "it'd be cool if" into the technical deep dive, builds the proof of concept, and turns it into the real thing. For 25 years I've led teams through that process, putting computer vision in Adobe Creative Cloud, wiring a concept car to Salesforce, teaching robots to take orders from AI agents, and building agentic tools people use every day.
Checking the agent
years building production software. patents in computer vision, adaptive AI interfaces, and accessibility. people used Adobe Shape. assets generated with the Agentic Brand System.
I built this. Try it out.
One quick check. Each run spends real money on real models, so this keeps bots out.
| Step | Model | Start | Time | Result |
|---|
Visitor gallery
Whether it's a request or a glimmer of an idea, I dig into and evaluate new technology.
Hardware, software, or both, built fast enough that the team can react to something real.
Walk people through how it works and train them up, so the project doesn't depend on me.
On a keynote stage, in a customer meeting, or in a tool people use every day. What doesn't hold up becomes a lab note.
Demos start as requests and others are ideas we can't let go. All of them ended up in front of real audiences, and some went on to become products. The last two are internal tools, so they show what they do and what they're built on instead of screenshots.
Agentforce Robotics · Dreamforce · 2025
Automotive · CES · 2022 to 2023
Gene therapy · HLTH · 2022
Einstein smart speaker · Dreamforce · 2019
(phando) Blades · Burning Man · 2025
A multi-model AI pipeline (LLMs, diffusion, and vision models, plus fine-tuned LoRAs) that creative teams across Brand, Studio, Keynote, and Demo use to generate assets. Long-running jobs, sharing, access control, and retries are all handled.
Built for Salesforce's User Insights team in support of Global Marketing Messaging. It turns research on what keynotes tell customers and the public into synthesized analysis and recommendations, surfaced through dashboards and reports.
Some of my biggest successes were catastrophes, at first.
Writing about what the demos taught me, mostly about where things actually break.
