One agent, many skills: structuring a production AI assistant

A developer at an enterprise SaaS platform restructured a conversational AI agent from a monolithic design into a modular 'skills' architecture. Each skill handles a single responsibility, such as changing a user or creating a survey, with a classifier routing user prompts to the appropriate skill. The new structure made adding features predictable and testing reliable, solving the fragility that emerged as the system grew.

We didn't give our AI agent one big brain. We gave it skills. We built a conversational AI inside an enterprise SaaS platform, where users get work done just by chatting — change a customer's user, create a survey, add questions, reopen customers. The first version handled everything in one place. It worked fine — while we had 3 or 4 features. Then the pain started. 😅 Every new feature made that one place heavier. Change one thing, break another. Re-testing the old flows became a nightmare. Here's what I learned: don't give an AI one giant brain — give it separate "skills." So we restructured: → A user's prompt goes to a classifier that decides which skill is relevant → Each skill is self-contained, with its own tools and one responsibility the "change user" skill only knows how to reassign a user → Common work — like resolving which customer or user the request means — lives in one shared layer, not copy-pasted into every skill → Each skill stays in its lane. Not its job? It hands off to another skill. The payoff: a new feature means adding a new skill, not touching the old ones. Testing became predictable, and changes stopped being scary. The lesson: if your AI system feels fragile every time you add a feature, the problem usually isn't the AI — it's the structure. Break it into skills.