@jerryjliu0: I'm glad people still understand the importance of building high-quality retrieval systems in 2026, especially as the o…

X AI KOLs Following News

Summary

Jerry Liu highlights the engineering challenges of productionizing agentic retrieval systems, emphasizing that success depends on careful tuning of chunking, synchronization, reranking, and tool API design rather than novel techniques.

I'm glad people still understand the importance of building high-quality retrieval systems in 2026, especially as the outer models/harnesses are getting better every day. Making agentic retrieval work in production doesn't necessarily require groundbreaking new techniques around retrieval or planning. This article shows that you do need to spend engineering time tuning chunking, synchronization, reranking, tool API design, permissioning, and more. Some interesting tidbits: * Concatenating onto existing Slack threads as one contiguous chunk with heuristics for determining additional relevant context * Real-time updates for Slack * Separate chunking/updates for codebases * The discovery that hybrid search works well (not like this was a super new realization, but always good to validate and understand the specific parameters they tweaked) * Having natural guardrails on which data sources are relevant for which projects Building simple retrieval is easy, building production retrieval is hard. We had to deal with a lot of these challenges when productionizing our own Index feature within LlamaParse.
Original Article
View Cached Full Text

Cached at: 07/20/26, 09:36 PM

I’m glad people still understand the importance of building high-quality retrieval systems in 2026, especially as the outer models/harnesses are getting better every day.

Making agentic retrieval work in production doesn’t necessarily require groundbreaking new techniques around retrieval or planning. This article shows that you do need to spend engineering time tuning chunking, synchronization, reranking, tool API design, permissioning, and more. Some interesting tidbits:

  • Concatenating onto existing Slack threads as one contiguous chunk with heuristics for determining additional relevant context
  • Real-time updates for Slack
  • Separate chunking/updates for codebases
  • The discovery that hybrid search works well (not like this was a super new realization, but always good to validate and understand the specific parameters they tweaked)
  • Having natural guardrails on which data sources are relevant for which projects

Building simple retrieval is easy, building production retrieval is hard. We had to deal with a lot of these challenges when productionizing our own Index feature within LlamaParse.

Similar Articles