Notes
NotesFrom the studio notes
The notes are the long version. Read one before you decide to write to us.
Protect
AI Agent Least Privilege for a Small Business: A One-Week Playbook
AI agent least privilege for a small business: what it means, why agents need tighter limits than staff, and a one-week playbook to scope tools, keys and approvals.
Brian Gagne
Protect
Voice-Activated Browsing: The Real Risks of Talking to an AI Browser
Voice-activated browsing risks backed by research and regulators: inaudible commands, cloned voices, prompt injection and stored recordings, plus a one-hour fix list.
Brian Gagne
Protect
Prompt Injection Attacks Explained: How Massachusetts Users Can Stay Protected
How prompt injection tricks AI browsers and assistants, why it can't simply be patched, and the steps Massachusetts users and businesses can take today.
Brian Gagne
Protect
The Rise of Agentic Malware: Protecting Your Data Before It Thinks for You
Agentic malware asks an AI model what to do mid attack. The documented cases from 2025, what is still hype, and six practical defenses for a small business.
Brian Gagne
Automate
Beyond the Hype: How We Build Multi-Model AI Agents That Hold Up
Multi-model AI agents swap models without a rewrite. Vendor retirement policies, OWASP's excessive agency risk, and the 7-step build order we follow.
Brian Gagne