Olivier Leplus

This session shows how to build an eval-driven LLM routing system: harvest a production eval dataset, define accuracy KPIs using LLM-as-judge, set a non-negotiable accuracy floor as the practitioner's decision, benchmark candidate models, and generate a routing policy optimized for cost within that floor.

The game master (GM) plays a central role in tabletop role-playing games, weaving together player stories, controlling NPCs, and managing rules. AI can wonderfully support GMs with rule checking, scenario improvisation, and on-the-fly content creation.

Navigating through complex cloud solutions can be a daunting task. In this session, see how generative AI can help solve this problem by building an AWS solutions architect agent.

It is exciting to ship code to users, but a release can also carry risk. To control this risk, many choose to decouple the deployment from when the feature is live.