Nupur Sharma describes challenges with long contexts and compares retrieval, summaries, knowledge graphs and critic stepsRetrieval is the process of selecting relevant stored information and returning it to an AI system for the current task.. She presents these as approaches with different setup, cost and latency tradeoffs.
Nupur Sharma outlines specialist agents and a judging step in code reviewAn agent handoff transfers an AI task, relevant context, authority, and responsibility between agents, people, sessions, or environments., then discusses audience questions about coordination, calibration and the risks of relying on past review behavior.
Watch on YouTube
