Hey guys, I’m building an AI agent / SaaS . This is an actual product that I want to deploy, monetize not just a toy project. I’m using ADK for the agent creation. The issue: - The first message I send to the agent takes about 20 seconds to get a response. - Every subsequent message takes another 10 seconds. - At this speed, it’s simply not usable, no real user will ever wait that long. Right now I’m stuck. I honestly can’t believe this is ADK’s fault, because if it is, then it’s basically unusable in production. So I assume it’s something I’m doing wrong, but I have no idea what. All the Google Cloud setup/config stuff is so complicated, and I feel lost. For more details, I posted here on the Google ADK GitHub: 👉 https://github.com/google/adk-python/issues/2704

I’m building an app using Google ADK with a custom front end, an AI agent, and a FastAPI backend to connect everything. I want my agent to have persistent user memory, so I’m planning to use Vertex Memory Bank, the new feature in Vertex AI. For deployment, I’m unsure about the best approach: - Should I deploy the AI agent directly in Vertex AI Engine and host FastAPI separately (e.g., on Cloud Run)? - Or should I package and deploy both the AI agent and FastAPI together in a single service (like Cloud Run)? What would be the best practice or most efficient setup for this kind of use case?