Kief Studio

AI agents

Notes

AI agents

Every Kief Studio note filed under AI agents, newest first. Read one before you decide to write to us.

32 notesshowing 25–32, page 2 of 2

  1. Build

    WordPress AI Agents Can Now Publish to Your Site. Who Controls It?

    WordPress AI agents can draft and publish via MCP on WordPress.com, and WordPress 7.0 added an AI Client. What changed, the risks, how to limit agent access.

    Amelia Gagne

  2. Protect

    Identity and Access Management for AI Browser Agents

    Identity and access management for AI browser agents: give each agent its own identity, scope it to one task, require approvals and log who acted for whom.

    Brian Gagne

  3. Protect

    Network Security Monitoring: Detecting AI Browser Anomalies

    Network security monitoring for AI browser agents: baseline each agent, alert on new destinations and odd outbound data, and watch app logs for hosted agents.

    Brian Gagne

  4. Protect

    Browser Extensions vs. Agentic AI: What Massachusetts Users Need to Know

    How browser extensions and AI agents in the browser differ, what can go wrong with each, and the controls a Worcester area business should set up first.

    Amelia Gagne

  5. Protect

    2026 Predictions for AI Agents and Web Safety: What Held Up

    We made 2026 predictions about AI agents and web safety. What the record shows in October 2026, what we got wrong, and how a small business should prepare.

    Amelia Gagne

  6. Protect

    Safe Browsing Habits for AI Agents: A Practical Guide for Everyday Users

    Safe browsing habits for AI browser agents: MFA, updates, least privilege, approvals and what to do if an agent is compromised, with a one week plan.

    Brian Gagne

  7. Automate

    Why Trust Still Matters in Agentic Browsing: The Human Element

    Agentic browsing lets AI act on web pages for you. How to calibrate trust, keep a person approving what matters, and widen an agent's scope only on evidence.

    Amelia Gagne

  8. 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