I build the production systems your operations are still held together without.
Embedded two to three days a week inside companies with real operational complexity. Automations, internal tools, reporting infrastructure, and AI-enabled workflows — built on your stack, handed to your team. Systems that run, instead of decks.
Workflow automation & internal tools
The system layer between your people and your tools. Internal apps and automations that replace the manual glue holding the operation together.
Reporting & data infrastructure
The reporting you keep promising to fix. Pipelines the team trusts and dashboards they open, instead of another monthly Excel rebuild.
AI-enabled operating layers
Agents, extraction, classification, and copilots, added where they carry real operational weight instead of sitting in a demo.
Embedded build capacity
Scoping, code, and rollout, inside your team. AI is the reason one person can ship all of the above with a fraction of the usual project weight.
We Didn't Build a Machine That Thinks. We Built One That Reads
Classic AI tried to program intelligence top-down. LLMs learned it bottom-up — by reading an enormous portion of what humans have written. That's not a technical detail. It might be the most important philosophical observation of our era.
I Stopped Managing My Notes—and They Started Managing Themselves
I've killed three note-taking systems. Each time, the same pattern: enthusiasm, elaborate architecture, slow decay, abandoned graveyard. What changed was adding AI agents to the loop. Not as a novelty, but because agents solve the core problem.