Mechanisms that let an AI agent interact with the outside world to accomplish tasks: extensions (connect the agent to an external API), functions (the model decides which function to call, the app executes it), data stores (proprietary data sources for grounding/RAG), and plugins (prebuilt integrations with third-party services).
In GENAI-L (Domain 2, section 2.5) the exam asks you to recognize these 4 types of tools and which Google Cloud services (Cloud Storage, Cloud Functions, Cloud Run, AI APIs) are used to implement them.
Agent tooling (extensions, functions, data stores, plugins) is a concept that can show up on the exam. Check the full guide to see it in context.