When you want to use services from Agent Platform with other runtimes (like GKE, and Cloud Run), you need to first create a resource identifier. At the time of writing, the way to do this is actually to deploy a “dummy” or backend agent. This is an agent that basically does nothing, except provide us… Continue reading Creating an Agent Platform resource identifier for other runtimes
Category: Agents
Deploying to Agent Platform with ADK
In my previous post, we created an agent with ADK and ran it locally. The next step is to deploy it to Agent Platform runtime. ADK deployments are typically deployed using a small Python script to configure the required properties. Create the following script in the root project folder (the one containing trading_agent from the… Continue reading Deploying to Agent Platform with ADK
Building a stock-trading agent with ADK
The Agent Development Kit (ADK) is an open-source framework from Google designed to simplify building, evaluating, and deploying AI agents. It allows developers to define agent logic, connect external tools, and orchestrate workflows directly in Python. I wanted a slightly more interesting app than Hello World to exercise more parts of the platform, so figured… Continue reading Building a stock-trading agent with ADK