Introducing Skein and Beaker Stack: Using AI Agent Engineers to Ship SaaS Faster

In this special episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss Brad's experiment proving that AI can dramatically boost output for teams with strong engineering practices. Brad shares an MIT-licensed open-source SaaS template called Beaker Stack, which includes web and mobile scaffolding, CI/CD for preview/staging/production, automated setup, observability, email tooling, and Stripe-based tiered billing with feature gating. He then uses it to build Skein, a cloud-hosted shared "memory backplane" served via an MCP endpoint that lets multiple AI tools and agents read/write memories with strong security controls and auditing. Brad describes hiring four AI agent "engineers" (Diego, Mei, Rahul, Sarah) with persona "soul files," running them in Nanocloud/Nanoclaw containers for security, coordinating work via Telegram and GitHub, and applying spec-driven, test-heavy guardrails to ship Skein in about 10 days of part-time work. Scott asks questions about Brad's process, and the two hosts debate how different perspectives effect an engineer's process, be they AI agent or human coworker. A video version of this episode can be found on the How Many CTOs YouTube channel!

00:00 Cold Open 01:05 AI Velocity Thesis 02:16 Shipping SaaS Every Six Weeks 04:37 Beaker Stack Tour 08:11 Meet The AI Engineers 09:52 Agent Workflow And Reviews 12:11 Building Skein Shared Memory 14:45 10 Day Build And Metrics 18:51 How Skein Uses Beaker Stack 24:20 Under The Hood Supabase Vectors 25:50 Admin UI Walkthrough 26:27 Managing Agent Workforce 26:49 Nanoclaw Security Containers 28:59 Telegram Agent Ops 30:32 Agent Personas Backstories 33:31 Thinking Hats Perspectives 37:25 Human Loop Guardrails 41:47 Marketing Distribution Channels 47:18 Factory Vision Rapid Launch 48:46 Wrap Up Credits

Resources

How Many CTOs Pod: https://howmanyctospod.com
Scott Porad: https://www.linkedin.com/in/scottporad/
Brad Hefta-Gaub: https://www.linkedin.com/in/bradheftagaub/
Skein: https://getskein.ai/
Beaker Stack website: https://beakerstack.com/
Beaker Stack GitHub: https://github.com/Artificer-Innovations/BeakerStack

#techpodcast #EngineeringPodcast #DevTalks #PodcastForDevs #HowManyCTOs #Podcast #CTOs #CTOPodcast #ChiefTechnologyOfficer #Technology #Engineering #SoftwareDevelopment #SoftwareEngineering #TechLeadership #EngineeringLeadership #EngineeringCulture #TechDebates #AI #SaaS #Engineering #Development #BeakerStack #Skein #TechInnovation #AIRevolution #AIEngineering #AIAssistedCoding #AICoding #AIProgramming #AIAssistedProgramming

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(84)

Fast, On Time, or Fully Utilized? Choosing What to Optimize in Engineering Delivery

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss a leadership conversation where three senior stakeholders wanted different outcomes from enginee...

25 Aug 16min

The Pace of Innovation: Systems Thinking for Faster Engineering

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub open with travel and sports talk, including World Cup rules, then pivot to Scott's change-management tra...

18 Aug 56min

Method to the Madness: A CTO Framework for Systemic AI Adoption

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss how CTOs must frame narratives that help teams organize around ideas, inspired by how Scott expl...

11 Aug 45min

There's A Pattern To Follow: An Interview with Robert "Uncle Bob" Martin

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub are honored to interview Robert "Uncle Bob" Martin, who recounts his 60+ year programming journey from a...

4 Aug 1h 1min

Is Uncle Bob Right? Reading Code vs. Architecting the Future

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss how Robert "Uncle Bob" Martin—author of Clean Code and Agile Manifesto signer—sparked online con...

28 Juli 43min

Token Maxxing and Local Inference: Navigating the Shift in AI Usage for Developers

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss token spending and the "token maxing" backlash, sparked by a GitHub Copilot budget issue and bro...

21 Juli 1h

This Has Always Been A Problem: Slot Machine Devs and Growing Junior Engineers in the Age of AI

In this episode of "How Many CTOs Does It Take?" podcast, hosts Scott Porad and Brad Hefta-Gaub discuss how managing armies of coding agents can be physically draining, likening it to context switchin...

14 Juli 56min

From Chaos to Control: Bringing Specification Driven Design to Vibe Coding with David Bauer

In this episode of "How Many CTOs Does It Take?" podcast, host Brad Hefta-Gaub is joined by Dr. David Bauer of Axonis AI, who shares how his background in distributed computing, startups, and the U.S....

7 Juli 51min