What if getting frontier-level AI capabilities did not mean sending every problem to the biggest proprietary model you can find?

Open models are getting remarkably capable. But the model is only part of the system. Tool use, context management, retrieval, routing, memory, verification, and agent harnesses can matter just as much as the name printed on the model card.

In this demo-heavy session, we will see how far we can get using open models and open source tools to build a system that tackles the kind of complex, multi-step work normally associated with frontier models. We will experiment with different models, give them tools, route work between them, and add mechanisms for checking and improving their own output.

The goal is not to claim that every open model magically matches Fable. It is to find out how much intelligence we can assemble from the pieces we can actually inspect, run, change, and own.