Permissions Are Part of Agent Architecture
Secure agent systems constrain blast radius with scoped identities, narrow tools, data boundaries, meaningful approvals, and a tested way to revoke access.
Tag
enterprise ai
Essays
The First Enterprise Agent Deployment Should Be Boring
Choose a frequent, bounded, reviewable workflow, integrate only the systems it needs, and build a harness for that deployment.
Measuring Whether Coding Agents Are Actually Working
Measure accepted outcomes, cycle time, quality, review burden, and total cost together instead of mistaking usage or code volume for value.
Projects
EconaAI
A decision-intelligence product for measuring AI value, modeling agent economics, prioritizing use cases, and connecting AI investments to business outcomes.
Founder, product strategy, research, prototyping
GCPFlow
Enterprise AI consulting for Google Cloud — helping teams take Gemini, BigQuery, and Vertex AI from prototype to production-ready systems.
Founder, product strategy, AI architecture, GTM
AI-Enabled Enterprise Prototypes
Rapid AI prototypes that help enterprise teams see, test, and evaluate new workflow ideas before making a larger platform investment.
Discovery, product design, architecture, implementation