Building Approval Gates AI Agents Can't Route Around
Tell an agent “always ask before sending” in the system prompt and the model treats it as a suggestion, not a constraint. Framework-level enforcement is the version that actually holds.
I walk through adding requireApproval: true to a Mastra meeting-assistant agent, then demo the full pause-and-approve flow in Mastra Studio. You’ll see exactly where the enforcement lives and why prompt-based “always ask first” breaks in practice.
Building an AI agent?
I help teams design and ship agentic systems — from architecture to production.
See how I can help
Stop Letting AI Agents Run the Whole Workflow
One inbox agent should not classify, research, score, route, and draft replies in one loose loop.
Harness Engineering: 4 Levers to Diagnose Any AI Agent
Most agent failures aren't model failures. They're harness failures. Here's the 4-lever framework I use to diagnose what broke.
Your AI Assistant Doesn't Need a Bigger Model. It Needs Colleagues
The multi-agent supervisor pattern in Mastra: eight specialist agents on one local LLM, one supervisor, structural trust boundaries — using TypeScript.
The Quality Loop Your AI Agent Is Missing (Evals + Tracing)
Add an LLM-as-judge scorer to a Mastra agent, catch a fabricated action item your tests would never flag, and fix the prompt — no custom infra.
Get new videos and posts by email
Weekly videos on AI engineering, plus deeper dives in the newsletter.
Occasional emails, no fluff.