We've all done RAG, now what?
2.70T1.5 sourcePractical AI (podcast)
Practical AI (podcast)original source ↗
Source record
Published by Practical AI (podcast) (T1.5 source). The original is at https://share.transistor.fm/s/e13d399b.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryPodcast episode where Rajiv Shah discusses a year of lessons building RAG pipelines and reasoning model integrations, covering why AI pilots fail, why evaluation and error analysis matter, and when LLMs are not the right tool.
Why it mattersA practitioner's synthesis on evaluation-driven RAG, with the useful counterpoint that not every problem warrants an LLM. General but grounded.
Cited by
No citations on record.