CRMs Don’t Have to Suck: Rebuilding Business Software with AI and Ruby with Thomas Witt

15 snips

Mar 10, 2026

Thomas Witt, founder of Vendis.ai and operator at Expedite Ventures, builds AI-native CRMs and AI-heavy production systems. He explains why conversation-first CRMs replace rigid forms. He discusses using Ruby on Rails with Hotwire, DynamoDB, async Ruby, vector search, and multi-model LLM workflows. He also covers telemetry for prompt chains and how small teams can be amplified by AI.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Treat Prompts Like Composable View Components

Prompt composition needed new patterns: prompt components like view components and explicit orchestration replace deep inheritance.
Thomas built composable prompt components and uses telemetry to trace long chains and changes to system prompts.

ADVICE

Trace Prompts And Compare Model Versions

Instrument prompt chains and model calls with tracing so you can debug and compare models.
Thomas uses Langfuse to log spans and evaluate what would change if a different model version ran.

ANECDOTE

Background Workers Push LLM Results To Hotwire

Vendors.ai uses SQS and background workers to process LLM calls and push updates to Hotwire frontends.
Thomas says this keeps the web frontend lean while workers handle heavy model orchestration and scaling.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

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