In my app I built an agent to extract my positioning and offer ladder. I upload my knowledge documents, they are stored safely on cloud storage. A cloud task picks them up to send to vertex who extract the vectors an put it in a postgress datastore on cloud run. Then I aks the agent to create my positioning and offer ladder. It uses researcher, writer, evaluator to create my ideal positioning and offer ladder. Pretty impressed with the quality of results it gives.I probably could have used Notebook LLM for this as well, but I don’t Want to push all my IP and client notes (confidentiality) to public LLM. Now it is in private storage.