Building an MCP Server in Rails

How we built an MCP integration, and what we learned along the way.

Behavioral DNA as Agent Configuration

Why static system prompts aren't enough. How measurable behavioral dimensions create consistent agent identity across sessions and providers.

Your AI Has the Memory of a Goldfish — So We Fixed It

What happens when you give an AI agent real memory — with confidence scoring, time decay, contradiction detection, and a knowledge graph.

The Sleeve Pattern: Why Your AI Agent Needs a Wardrobe

One user, multiple agent identities. How the sleeve abstraction gives AI agents context-appropriate personality, memory, and skills.

The Economics of Thinking: How We Keep AI Costs Under a Penny

Not every AI call deserves a frontier model. How deliberate model-tier strategy keeps per-conversation costs under a penny without sacrificing quality.

Teaching Agents to Use Your Tools: The Psychology of MCP Adoption

We built MCP tools and agents refused to use them. The fix had nothing to do with the protocol.