Building a Software Factory: How Much Should You Delegate to the Agent?
A software factory is not all-or-nothing autonomy. The useful question is how much scope an agent has earned, and where you should stop at read-only recommendations instead of full execution.
In this first episode, I build a read-only Dependabot triage agent in TypeScript with Mastra. It pulls the PR, reads the release notes you would normally skip, and posts a merge-or-hold recommendation to Slack so the factory starts with judgment before it earns action.
Building an AI agent?
I help teams design and ship agentic systems — from architecture to production.
See how I can help
I Added ACP to My Mastra Agent So It Can Work in Repos
ACP is the layer that lets my Mastra agent hand real repo work to Claude Code instead of stopping at advice.
Stop Giving Your Agent Every Tool
Large tool catalogs break agent context. Tool search fixes that by letting agents discover and load only what they need.
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.
Get new videos and posts by email
Weekly videos on AI engineering, plus deeper dives in the newsletter.
Occasional emails, no fluff.