A detailed benchmark analysis comparing raw Claude Code's performance with windowed grep and Turbopuffer's semantic search for code retrieval in LLM agents. The study reveals significant improvements in file precision (65% to 87%) and reduced wasted reads (1 in 3 to 1 in 8) with semantic search, while highlighting the importance of the agent's understanding of when to use retrieval tools.
Martin Keen compares Retrieval Augmented Generation (RAG) with the emerging long context window approach in LLMs. He analyzes the pros and cons of each, from infrastructure simplicity and retrieval accuracy to computational costs and the 'needle in the haystack' problem, providing guidance on when to use each solution.
Nishikant Dhanuka from Prosus Group shares practical lessons on building effective AI agents for e-commerce and productivity. He covers why context engineering is more crucial than prompt tweaking, how to build a modern search pipeline, the failures of pure-chat interfaces, and why a robust evaluation framework is the real competitive advantage.
OpenEvidence founder Daniel Nadler explains how his company solved the semantic search problem in medicine, achieving 40% adoption among US doctors in 18 months. He discusses the strategy of treating physicians as consumers, the future of medical education in the age of AI, and his unique philosophy on motivation and recruiting.
Daniel Nadler, founder of OpenEvidence, discusses the platform's rapid adoption by 40% of US physicians. He explains how OpenEvidence solves the semantic search problem in high-stakes clinical decision-making, its growth strategy of treating doctors as consumers, and how AI will reshape medical education and the role of the physician.
Arvind Jain, CEO of Glean, details the company's journey from a pre-LLM enterprise search innovator to a leading AI agent platform. He covers their hybrid model strategy, the critical role of permission-aware RAG for security, and how AI agents are creating 'evergreen' documentation and reshaping enterprise workflows.