Subscribe

Stage 2 · Core

LLM Apps: Caching & RAG

Put retrieval and caching in front of a model without leaking data or serving the wrong answer.

You'll be able to: Design a semantic cache and a RAG pipeline that respect tenants and permissions.

0 of 2 done
  1. 1 Deep dive 6 min Failure mode + fix Semantic Caching for LLMs A semantic cache is only as safe as its key: key on meaning alone and it serves wrong answers and leaks data across tenants.
  2. 2 60-sec Short 45 sec Failure mode + fix Post-Filter RAG Leaks If you check permissions *after* retrieval, the LLM has already read the secret — pre-filter by ACL inside the search.
  3. Coming soonPrompt Injection Through ToolsAnnounced at the end of an episode in this track. Subscribe to catch it.
  4. Coming soonPre-Filter RAGAnnounced at the end of an episode in this track. Subscribe to catch it.
Next stage Decision Models