// THE TEAM
We're not a 20-person firm pretending to be enterprise. We're a founder, an AI research system, and a stack of purpose-built agents. Every engagement gets the full stack.
Embedded AI leader across three industries — energy, insurance, and distribution. Every system built is in production. Every engagement either continued or expanded.
The work starts with joining the team: learning every name, attending every standup, understanding the business before touching the data. This isn't a philosophy — it's the only approach that consistently ships production systems.
Based in Portland, OR. Available for embedded engagements nationwide.
41,000 lines of Python. 1,900+ passing tests. Edwin is our internal AI research system — a living memory architecture that verifies what it stores, challenges what it believes, and catches 95% of false information before it enters memory.
Edwin uses multi-model adversarial verification, where AI models argue with each other to surface the truth. It runs agentic pipelines, maintains cryptographic proof of knowledge state, and continuously consolidates its understanding through counterfactual challenges.
Everything we learn building Edwin flows directly into client work. The same verification discipline that powers our R&D powers your data warehouse.
41,000
lines of Python
1,900+
passing tests
95%
false info caught
9
packages
Purpose-built agents deployed for every client engagement.
ETL, enrichment, and deduplication. Every pipeline caches before spending, monitors yield per batch, and stops automatically when something breaks.
Fact-checking and quality gates. Multi-model adversarial verification catches false information before it enters any system — yours or ours.
Pattern recognition and anomaly detection. These surface what humans miss in large datasets — cross-domain connections, emerging trends, and contradictions.
Multi-platform connectors that unify data from five tools into one operational picture. Built to handle the messy reality of enterprise data.