What happens when you treat an AI agent like a co-founder instead of a tool?

In this episode, Valentino and Joe go deep into a real-world experiment: spinning up an autonomous agent using OpenClaw, giving it domains, goals, and just enough guidance to build an actual business. From creating accounts and managing projects to writing code, deploying with Kamal, and even designing its own training curriculum, the agent evolves from confused assistant to something resembling a junior engineer with initiative.

Along the way, they explore the messy reality of agent workflows: memory systems, self-training loops, PR reviews, hallucinated confidence, and the constant tension between autonomy and control. The result? A working product, 15 early users, and a pile of hard-earned lessons about what AI can and definitely cannot do today.

If you’re building with agents, thinking about autonomous systems, or just curious what happens when you let AI run a startup… this one’s for you.

🔗 Show Notes

- Valentino's Minerva Experiment
- Minerva's First Product

Core Tools & Frameworks
- RubyLLM (Carmine Paolino)
- Kamal (Deploy Rails anywhere)
- Tailscale (Secure networking)

Libraries & Infra Mentioned
- ExtraLite (SQLite performance layer)

Learning & Community
- Ruby AI Newsletter (Matt Solt)

Other Mentions
- OpenClaw
- Claude Code
- Action MCP
- Fizzy (37signals)
- Magic Beans (graph-based project management for agents)
- ups.dev (agent status pages project)
- DailyVibe.ai

Books & Resources Referenced
- Practical Object-Oriented Design in Ruby by Sandi Metz
- Programming Ruby (Pickaxe Book)
- The Well-Grounded Rubyist
- Layered Design for Ruby on Rails Applications — Vladimir Dementyev

Cultural Reference
- Wired article on AI-generated band marketing (“Geese”)

00:00 Podcast kickoff
00:40 Geese AI marketing psyop
02:03 Starting an AI band
04:18 Daily Vibe artist generator
06:24 Open Claw origin story
08:52 Domains to business ideas
10:44 Onboarding an AI coworker
13:22 Handholding and action loops
14:10 Shark Tank idea filter
15:32 Training and memory system
20:20 UPS dev agent status pages
22:54 Rails build struggles
24:04 Bootcamp with Ruby books
26:20 Rebuild MVP and open source
27:55 Deploying with EC2
28:38 Locking Down Access
30:06 AI PR Reviews
32:50 Self QA Automation
36:11 Fixing Agent Memory
38:15 Email and Token Costs
40:11 Heartbeats and Delegation
43:01 Customer Discovery Lessons
44:49 Selling Workflow Friction
48:19 Knowledge Base Frameworks
51:37 Open Source Model Future
53:57 Security Agents and Wrap

Valentino Stoll and co-host Joe Leo open the Ruby Podcast noting OpenAI is winding down its SOA video app and discuss the broader difficulty of building AI businesses. Guest Bekki Freeman, staff software engineer at Caribou Financial and organizer of Rocky Mountain Ruby, shares conference details (Boulder, Colorado at eTown, September 28–29; CFP opening soon; tickets after the schedule). The conversation focuses on safely scaling AI use in an 8-year Rails monolith: preparing messy codebases with dead code and metaprogramming, strengthening test harnesses and coverage, improving documentation, and being explicit about desired patterns rather than copying existing bad ones. They discuss PR review bottlenecks from increased AI-generated PRs, ideas like specialized AI review agents, stronger RuboCop rules, pairing/mobbing, and remote knowledge-sharing practices, plus security cautions and what AI may and may not replace (tech-debt work vs “taste”).

00:00 Sora Shutdown News
00:57 AI Hype Reality Check
01:43 Meet Bekki Freeman
02:00 Rocky Mountain Ruby Update
04:32 AI Meets Legacy Rails
07:22 Prep Codebase for AI
10:06 Patterns Versus Best Practices
12:37 Testing Strategy and TDD
16:45 PR Review Bottlenecks
19:27 Specialized Review Agents
21:31 Defining Quality Context
24:29 Humans and Team Adoption
25:20 Remote Change Adoption
27:00 Creating Sharing Rituals
29:19 Release Calls As Watercooler
30:12 Mob Sessions With Agents
33:55 Security And YOLO Risks
35:45 Too Much Code Problem
37:16 Vibe Coding Vs SaaS
42:10 AI Engineering In Two Years
45:33 Codex Versus Claude
47:39 Wrap Up And Farewell

On the Ruby AI Podcast, hosts Valentino and Joe Leo welcome Scholarly CTO/co-founder Kelly Sutton to discuss building a vertical SaaS “faculty information system” for universities. Sutton explains why competitors can’t easily replicate Scholarly: higher ed is moving off decades-old homegrown software, and the product must meet trust, security, compliance, and regulatory demands such as SOC 2 Type II. He describes how Scholarly expanded from replacing Excel/Access tracking to sophisticated workflow automation and how universities recently shifted from AI skepticism to AI FOMO. Scholarly uses AI in product surfaces, heavily in engineering, and via an admin MCP server that helps ops/customer success rapidly configure workflows from faculty handbooks with human-in-the-loop review. The conversation debates MCP’s likely temporariness versus traditional APIs, emphasizes smaller reviewable “PR-sized” outputs, and frames AI as an implementation detail focused on customer value. Valentino also shares an experiment training Claude to build products, including ups.dev and an open-source Ruby uptime-monitoring gem.

Many “AI startups” today are little more than thin wrappers around large language model APIs. But what happens when those APIs improve and the platforms absorb those features?

In this episode of The Ruby AI Podcast, Valentino Stoll and Joe talk with builder and investor Thomas Witt, founder of Vendis.ai and operator of the pre-seed firm Expedite Ventures. Thomas shares why he believes the next generation of durable companies must deliver real value deep in the product stack rather than bolting chat onto existing software.

The conversation explores why traditional CRMs are widely disliked and how an AI-native CRM might look completely different. Instead of rigid forms and required fields, Thomas describes a system where conversations themselves become the primary data source. Emails, meetings, and messages are embedded, searched semantically, and transformed into structured knowledge automatically.

They also dive into the architecture required to support this shift. From Ruby on Rails and Hotwire to DynamoDB, vector search, async Ruby, and multi-model LLM workflows, Thomas shares practical lessons from building AI-heavy production systems.

Along the way the discussion touches on agentic coding workflows, LLM-as-a-judge evaluation patterns, telemetry for prompt chains, and why small teams may soon replace the massive engineering orgs we’ve grown used to.

If you’re curious where Ruby, Rails, and AI systems are heading next, this conversation offers a fascinating glimpse.

Show Notes

Guest: Thomas Witt
Founder of Vendis.ai
Investor at Expedite Ventures

Topics we explore

• Why many AI startups are just “wrappers” around LLM APIs
• What an AI-native CRM looks like when conversations become the database
• Why Thomas chose Ruby on Rails with minimal JavaScript using Hotwire and Stimulus
• Using Amazon DynamoDB instead of relational databases for AI workloads
• Hybrid keyword + vector search with OpenSearch and Elasticsearch
• Async Ruby patterns using fibers, the Async ecosystem, and the Falcon web server
• Orchestrating many concurrent LLM calls within a single user interaction
• Background job systems and queues such as Amazon SQS
• Code quality workflows with StandardRB and RuboCop
• Using models like Claude, OpenAI Codex, and Gemini together in multi-model workflows
• Observability and prompt tracing with Langfuse
• Why AI tooling may enable much smaller engineering teams

Mentioned in the Show

• Vendis.ai – Thomas’s AI-native CRM platform
• Hotwire – HTML-over-the-wire approach for modern Rails apps
• Falcon – Fiber-based Ruby web server
• Ruby AI Builders Discord – Community of Ruby developers building AI tools
• Chaos to the Rescue @ Artificial Ruby

In this episode of the Ruby AI Podcast, hosts Joe and Valentino welcome special guest, Kinsey Durham Grace, a prominent figure in the Ruby community and member of the GitHub team. The discussion covers a range of topics including the use of AI for generating episode artwork, the application of AI agents in coding tasks, and the recent developments at GitHub like the Agent HQ. Kinsey shares insights into her day-to-day work on the coding agent core team at GitHub, including the use of custom agents to enhance coding efficiency. They also delve into the impact of AI on software development, the importance of well-rounded developer skills, and Kinsey’s perspective on the future of Ruby in the AI landscape.

00:00 Introduction and Guest Welcome
00:30 AI-Generated Images and Their Drawbacks
03:07 Kinsey's Role at GitHub
06:33 Using AI Tools in Development
11:26 Challenges in Large Monolith Apps
18:23 Modular and Maintainable Agents
24:47 AI's Role in Software Development
25:29 Challenges with Current AI Tools
26:50 Observational Memory in AI
27:42 Open Claw and Heartbeat Concepts
28:22 Collaborative AI and Future Prospects
29:22 In-House vs. Third-Party Observability Tools
29:54 New AI Products and Intent Capture
31:08 Persisting Context in Software Development
37:42 Custom Agents and Knowledge Management
46:13 The Human Element in AI Collaboration
47:20 Skills for the Future of AI in Engineering
48:54 Ruby and AI: Staying Relevant
50:50 Conclusion and Final Thoughts

🔗 Resources Mentioned in This Episode

Kinsey’s talk at RailsWorld 2025: The Rise of the Agents In Rails

GitHub & Agent Workflows

• https://github.com
• https://github.com/features/copilot
• https://github.blog
• https://cli.github.com
• https://code.visualstudio.com
• https://github.com/features/codespaces

Models & AI Tools Mentioned

• https://claude.ai
• https://www.anthropic.com
• https://openai.com
• https://platform.openai.com
• https://gemini.google.com
• https://cursor.sh
• https://ampcode.com

Observability & Infrastructure

• https://www.datadoghq.com
• https://learn.microsoft.com/en-us/azure/data-explorer/kusto/query/

OpenClaw

• https://openclaw.ai
• https://github.com/OpenClaw

Mastra AI

• https://mastra.ai

QMD (Referenced by Valentino)

• https://github.com/tobi/qmd

Stephen Margheim – SQLite / Ruby Work

• https://fractaledmind.github.io
• https://github.com/digital-fabric/extralite

GitHub-Related Announcements (Former CEO Mention)

• https://entire.io/

In this episode of the Ruby AI Podcast, hosts Valentino Stoll and Joe Leo are joined by Ben Schofield, an accomplished author, open source contributor, and Ruby enthusiast. The discussion starts with thoughts on the upcoming RubyConf and the unique experience of conferences hosted in Las Vegas. Ben shares his recent experiences with Bento and the impact of layoffs. The conversation delves deep into the nature of expertise, exploring questions around achieving world-class performance and domain-specific skills. The hosts explore the goals of software development, the role of AI in coding, and the importance of intentionality in using agents. They also touch on the concept of default settings in development, the nuances of staff engineering, and strategies for training future staff engineers. The discussion concludes with ideas for improving the onboarding and training of engineers in the evolving landscape of AI tools.

Mentioned in this episode:

• RubyConf 2026 (Las Vegas)
• RailsConf (context/history)
• O’Reilly (RailsConf partner mentioned historically)
• Bento (Ben’s recent company)
• Gusto (host context)
• Artificial Ruby / Ruby x AI NYC meetups
• Agentic coding & tooling
  • Claude Code docs
  • Claude Code + MCP
• Books, papers, and ideas
  • C. Thi Nguyen (background)
  • Games: Agency as Art (Oxford)
  • Ezra Klein Show episode (Nguyen)
  • Malcolm Gladwell, Outliers
  • Andy Hunt, Pragmatic Thinking and Learning (Refactor Your Wetware)
  • Ericsson et al. (1993) deliberate practice (DOI)
  • Macnamara & Maitra replication (2019) (DOI)
  • David Epstein, Range
  • Will Larson, Staff Engineer
  • Robert Cialdini, Influence resources
  • DHH on conceptual compression
  • Chad Fowler, The Phoenix Architecture (Leaflet)
  • Quote referenced (“How can I know what I think till I see what I say?”)
• Ruby/Rails primitives referenced in Valentino's experiments
  • Ruby method_missing
  • Ruby define_method
  • Rails rescue_from
  • Valentino's experimental Ruby project (“Chaos to the Rescue”) that uses LLMs + runtime method definition

Ruby turns 30, Ruby 4 quietly ships, and the AI tooling arms race shows signs of maturity. Valentino and Joe unpack what stability really means for a language in its third decade, debate agent-driven development, AI “slop,” binary distribution, and whether open source incentives are breaking down—or simply evolving.

Mentioned In The Show

A grab-bag of tools, projects, and references Valentino & Joe brought up.

Ruby & Core Ecosystem

• Ruby Gets A Fresh Look — Official Ruby programming language site (news, downloads, docs) now with a great new look.
• Ruby Kaigi — Ruby’s flagship conference (talks, schedules, archives).
• Bundler — Ruby dependency manager used across the ecosystem.

AI Coding Tools

• Claude Code — Anthropic’s CLI coding assistant workflow discussed heavily in the episode.
• OpenAI Codex — OpenAI’s coding agent/tooling referenced as an alternative workflow.

Ruby Web Frameworks & Architecture

• Rails Framework — Ruby on Rails, referenced as the default baseline for many apps.
• Jumpstart Rails — Rails starter kits/templates mentioned as a “pick a Rails” approach.
• Roda Framework — Jeremy Evans’ web toolkit (lighter than Rails, bigger than Sinatra).
• dry-rb Suite — Ruby gems for functional-ish architecture and explicit business logic.
• Trailblazer — High-level architecture for operations, workflows, and domain logic.

Quality, Testing, and Practice

• Better Specs — Community-curated RSpec guidelines mentioned as a spec style target.
• Datadog — Error monitoring referenced in the “well-defined bug + stack trace” workflow.

Open Source Sustainability

• GitHub Sponsors — Sponsorship mechanism discussed as one (partial) monetization path.

People Mentioned

• Sandi Metz — Referenced as the “code whisperer” ideal for idiomatic Ruby guidance.

In this episode of the Ruby AI podcast, hosts Valentino Stoll and Joe Leo engage with Evan Phoenix, a seasoned Ruby programmer and CEO of Mirren. The conversation explores Evan's unique name origin, his career trajectory, and the integration of AI in development workflows. They discuss the distinction between real and fake AI in products, the impact of AI on engineering practices, and the future of AI in development tools. Evan shares insights on performance optimization, human-centric AI interactions, and the role of AI in deployment and architecture detection. In this conversation, Joe, Evan Phoenix, and Valentino Stoll discuss the evolving landscape of software development, particularly focusing on the role of AI, automation, and the Ruby programming language. They explore how AI can assist in analyzing code bases, the future of development with ambient agents, and the potential resurgence of monolithic architectures. The discussion also touches on the importance of human-centric design in software, the significance of experimentation, and the unique strengths of Ruby in the current tech environment. The conversation concludes with predictions about the future of small teams in software development and the impact of AI on coding practices.