Learn
What we've learned
Research notes, frameworks, and explanations from building AI products. No jargon, no hype — just what we've found to be true.
AI Councils: Why One Model Isn't Enough
Karpathy, Perplexity, and a wave of startups all shipped the same idea within months. When AI models check each other's work, the results improve — but the details matter more than the headline.
Read articleFrontier Models and Open Source
Closed-source models still lead the frontier, but open-source is closing the gap fast. What this means for organizations building AI products and the future of model access.
Read articleThe Agentic Frontier
From Claude Code to OpenClaw — the most powerful AI agents aren't the ones that think the hardest. They're the ones that use tools. What primate evolution teaches us about where agentic AI is heading.
Read articleAgentic Workflow Management
How to design, implement, and manage workflows where AI agents handle real operational processes — from task decomposition to monitoring and human oversight.
Read articleMulti-Agent Orchestration
How to coordinate multiple AI agents into systems that are greater than the sum of their parts — patterns, architectures, and lessons from building Kapwa.
Read articleThe Agentic AI Framework
A structured approach to identifying where AI agents create real value — from mapping processes to prioritizing opportunities and planning implementation.
Read articleWhat are AI Agents
From chatbots to autonomous agents — what makes an agent different, how they work, and why they represent the next major shift in business technology.
Read articleWhat is AI (Without the Jargon)
A plain-English explanation of AI, machine learning, and large language models for business leaders who want to understand the technology before investing in it.
Read article