Thanks for reading. I’m especially interested in hearing from people who have worked on real RAG or GenAI workflows.

Which one has been the biggest challenge for your team?

1. Choosing the right source data
2. Access control and governance
3. Improving retrieval quality
4. Evaluating groundedness
5. Monitoring cost and latency
6. Getting business users to trust the answers

For me, retrieval quality and evaluation are usually where demo systems start to become real production systems.