What two hackathons taught me about agent architecture — and how it's reshaping Atlarix

I recently competed in two hackathons back to back: the Amazon Nova AI Hackathon (virtual, won the Bonus Blog Post Prize) and the Lua x Antler "Building Agent-First Businesses" event in Nairobi (physical). Both cracked open how I was thinking about agents in ways I didn't expect. The Amazon Nova lesson: a model is only as powerful as its capabilities The hackathon required building with Amazon Nova. My instinct going in was that model choice was the primary variable — pick the best model, get the best results. Wrong. What actually moved the needle was what I wrapped around the model: the tools it could call, the context it had access to, how I structured the agent loop. Nova performed at a high level not because of raw benchmark numbers but because I gave it enough surface area to work with. This directly influenced how I think about Atlarix's Compass tier system. Compass routes users to Fast / Balanced / Thinking model tiers via OpenRouter — but the tier is almost secondary to the too