Latest
A second domain experiment showing why workflow behavior, retrieval shape, and reusable evaluation architecture matter more than simply adding more context.
Research desk
A second domain experiment showing why workflow behavior, retrieval shape, and reusable evaluation architecture matter more than simply adding more context.
A practical experiment comparing baseline, RAG, fine-tuning, and combined approaches for automotive warranty and service diagnostics.
No posts match that filter yet.
About the work
These notes focus on evaluation design, retrieval shape, fine-tuning behavior, and the architecture choices that decide whether a model behaves like a workflow or just a helpful assistant.
