Hi everyone, I’m currently testing Google’s ADK and building my first multi-agent system (a customer service agent). My idea is to have a root agent that communicates directly with the customer, while the sub-agents only interact with or assist the root agent (not the customer directly). The problem I’m facing is that all agents are responding to the customer, which breaks some intended features. For example: - The root agent can open a ticket using a tool when it cannot solve the customer’s problem. - If the customer’s prompt is about an order and the root agent delegates it to the “orders” sub-agent, the sub-agent should send its answer back to the root agent. - However, what happens now is that the sub-agent replies directly to the customer saying it can’t do anything, instead of sending this information to the root agent, which should then decide whether to answer or propose opening a ticket. Has anyone faced this issue before or knows how to make only the root agent respond to the customer?

Hi everyone 👋 I’m currently working on building a OneDrive connector using ADK. Has anyone here worked on something similar or has experience with it? Any guidance or references would be really helpful!

Hello, Can someone please help with this issue: Getting an error when creating a basic agent with GOOGLE_GENAI_USE_VERTEXAI=TRUE Followed all gcloud cli steps to authenticate and configure project, enable Vertex AI APIs etc., HTTP/1.1 401 Unauthorized" 2025-09-17 21:41:46,793 - ERROR - adk_web_server.py:1076 - Error in event_generator: 401 UNAUTHENTICATED. {'error': {'code': 401, 'message': 'API keys are not supported by this API. Expected OAuth2 access token or other authentication credentials that assert a principal.

Hi all... I built RAG application using Langchain framework where I used BQ vectorstore. Now due to organisation shift, I need to move to google adk. I am new to this adk, have couple of questions, 1. Can I implement this using Google ADK ( I want to use BQ as vectorstore) 2. If yes, what kind of library and function I need to use for recursivecharactertextsplitter(), documentloaders(), retriever(). I am using BQ as vectorstore... 3. If I want to retain my existing langchain code in adk, how is that possible ?Any docs to support/refer ...

I am new to the development of agents, so i am following the materclass on ADK. But i can't make the adk web function. I am frustrated. I already read other tutorials but I cannot resolve the error that the adk web shows me when i ask something. The error is the next: {"error": "[WIP] _load_from_yaml_config: _load_from_yaml_config is not ready for use."} Does anybody have the same issue?