The Knowledge Layer
Subscribe
Sign in
Home
Notes
Archive
About
Vector vs graph vs episodic: a tour of agent memory systems
RAG retrieves from a fixed corpus. Memory is the part that remembers what happened, and the vendors building it have each bet on a different…
15 hrs ago
•
Ratko Nikolić
Serbian Legal AI: a RAG architecture comparison
Five knowledge-layer architectures, one Serbian-law corpus, 300 graded answers.
Aug 11
•
Ratko Nikolić
July 2026
Agentic RAG: when retrieval becomes a decision, not a pipeline
Naive and advanced RAG retrieve the same way every time. Agentic RAG lets the model decide what to look up, whether the results are good enough, and…
Jul 28
•
Ratko Nikolić
GraphRAG and friends: when entities and relationships beat similarity
Some questions aren't about what a document says — they're about how things are connected. Vector search can't answer those. A typed knowledge graph…
Jul 14
•
Ratko Nikolić
June 2026
Advanced RAG: what you actually run in production
Four moves turn the naive baseline into something that survives real traffic — hybrid search, reranking, query rewriting, and metadata filtering. Each…
Jun 30
•
Ratko Nikolić
Naive RAG: the baseline you'll always benchmark against
The simplest retrieval pipeline there is — chunk, embed, match, stuff into the prompt. It's also the thing every fancier technique has to prove it…
Jun 16
•
Ratko Nikolić
Your agent's problem isn't the model. It's the knowledge layer.
Most agent failures aren't model failures or prompt failures — they're failures in the layer underneath. This series is about that layer.
Jun 2
•
Ratko Nikolić
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
