Insights
How we think about AI in business.
Our vision, our positioning, and the real economics — written for founders, owners, and technical leaders. No hype, no jargon walls.
AI that survives an audit When an intelligent system makes a decision, sooner or later someone asks: 'why?' A system that can't answer fails an audit. We believe auditability has to be in the design from day one, not a later add-on. Insights 3 min read Attentive AI: why focused beats big The biggest model is not the best answer. When every job has a defined boundary, focused intelligence beats jack-of-all-trades intelligence every time. Insights 3 min read Authority is a trajectory, not a key You don't hand an intern the keys to everything on day one. AI agents should earn their authority along a path too — just like a career. Insights 3 min read CRM is a special case of a larger pattern What we've built to manage customer relationships looks, at first glance, like a CRM. But underneath it lies a more general pattern that reaches beyond relationships. Insights 2 min read You're not buying software — you're buying an ecosystem that compounds A tool solves one problem once, and stays there. What we build is an ecosystem whose intelligence compounds with every addition. Insights 2 min read Fine-tune, RAG, or prompt: which one, and what each costs There are three ways to adapt a model to your need, and the wrong choice can get expensive. The difference is in what problem each one actually solves. Insights 3 min read From prompt engineering to context engineering There was a time when the art of working with a model came down to writing a good prompt. But we believe the centre of gravity is shifting: from crafting one instruction to designing the whole context the model works in. Insights 3 min read From a vague message to the right structured action Humans speak vaguely, incompletely, messily. The hard job of an intelligent system is to pull the right action out of that mess — without asking the user to speak like a form. Insights 3 min read Layered intelligence: when conversational AI meets background AI A good agent has to do two things well at once: fluent conversation with a human, and deep cognitive work behind the scenes. These are two different layers of intelligence — and we believe separating them is the key. Insights 3 min read Why we run our own models on home infrastructure Running models on our own infrastructure isn't just a technical choice; it's a conviction about independence, keeping data at home, and durability. This is our decision and its reasoning. Insights 2 min read Hire, coach, and learn to trust your AI employees You install software; you hire an employee. That small difference changes everything about how you build a digital organization. Insights 5 min read Making AI reliable on real, messy documents On a clean document, any model looks good. The difference is in the messy tail — where real documents live. Insights 4 min read Smaller, faster, cheaper: the case against one big model for everything It's tempting to hand every job to the most capable model. But most jobs need only one focused capability — and the right smaller model does it faster and cheaper. Insights 2 min read The self-learning colleague: a roadmap, not a release Today, an agent begins each conversation anew and learns nothing from yesterday's work. What follows is a vision, not a current capability: an agent that learns from its own work. Insights 3 min read Where LLM serving costs actually go If you open up the bill for serving a model, most of the cost is concentrated in one place. Understanding that concentration also clarifies the eternal 'build or buy' question. Insights 3 min read Why we don't build chatbots: the two multi-agent paradigms we rejected Most AI systems are built in one of two shapes — and both break at scale. This is the story of what we chose instead. Insights 4 min read