Thanks for reading!
I’m curious about how other developers are approaching LLM systems.
A few questions for discussion:
• Are you using RAG in your projects yet? • How do you manage context window limits when dealing with long documents? • Do you think prompt engineering will evolve into a more structured “prompt architecture” discipline?
I’d love to hear how others are building with LLMs and retrieval systems.
If you have examples, tools, or experiments, share them below.