Web Development Then, LLMs Now: Forecasting LLM Best Practices by Looking Back – and Ahead

A talk on best practices for building RAG pipelines at the 7CTOs Colloquium in Austin.

Published Jun 18, 2025 in LLM, AI, Video
Scroll

I gave a talk at the 7CTOs Colloquium in Austin on best practices for building Retrieval-Augmented Generation (RAG) pipelines—and how we’re starting to see a clear architecture emerge for serious LLM-based applications.

Web Development Then, LLMs Now: Forecasting LLM Best Practices by Looking Back – and Ahead

In this talk, I cover:

  • Chunking strategies (simple, structural, semantic)
  • Search and retrieval (BM25, vector search, RRF)
  • Query rewriting, decomposition, and HyDE
  • Reranking, repacking, and summarization
  • Tool calling and query classification

I also share prompts, techniques, and design tradeoffs we’ve discovered while building real-world LLM applications at Scientist.com.

Thanks to 7CTOs for putting on the event and thank you to Howdy.com for hosting!

AI's Quiet Revolution in the Pharma Supply Chain

I joined the Mendelspod podcast to discuss how AI is transforming the research services marketplace.

Published Apr 17, 2025 in AI, LLM, Scientist.com