July 3, 2026
David Guttman - Delegating Outcomes to AI with OpenClaw
Principal at Superstruct and author David Guttman joined me on Ditching Hourly to talk about using OpenClaw and AI agents to delegate outcomes instead of micromanaging code.
Chapters
- From Superstruct Teams to AI Employees
- Testing Devin Against a Human Engineer
- What OpenClaw Adds to AI Agents
- Vibe Coding from Anywhere
- Pretending You Do Not Know How to Code
- Software Quality, Risk, and Real Requirements
- How OpenClaw Has Changed
- Qualifying Tasks for an AI Employee
- The Secure OpenClaw Setup Process
- Local Machines vs Cloud Servers
- Tailscale and Remote Access Security
- Teaching Clients to Train Their Agent
- Ask the Agent Before Asking the Expert
- Life-Changing Client Use Cases
- Disposable Software and the Future of Developers
- Productivity, Pricing, and Value
Guest’s Bio
David Guttman is the Principal at Superstruct, where he helps solopreneurs and founders set up AI employees. He is the author of The Superstruct Manifesto, a survival guide for founders who depend on developers to get things done. David has also written Fullstack Node.js and Fullstack React and has held engineering leadership roles at Outlier.org and Interlincx after earlier work with Disney and AT&T Interactive. You can find more of his work at davidguttman.com and david.app.
Sharing is caring!
If you enjoyed this episode, please consider sharing it with a few friends who might find it useful. Thanks!
Yours,
—J