← GitHub Certified: Agentic AI Developer
AZURE · objective · 23% of the exam
Implement Tool Use and Environment Interaction — GitHub Certified: Agentic AI Developer
The official AZURE documentation our Implement Tool Use and Environment Interaction practice questions are cited to. Review the primary sources, then practise.
Official references for this objective
-
Microsoft — Using function tools with an agent | Microsoft Learn
If a tool is implemented outside the framework (for example, client-side in a UI), you can declare it without an implementation using FunctionTool(..., func=None)
-
Microsoft — Azure AI Search | Microsoft Learn
Agentic mode requires exactly ONE of: knowledge_base_name OR index_name # Option 1: Use existing Knowledge Base (recommended)
-
Microsoft — semantic_kernel.core_plugins.sessions_python_tool.SessionsPythonTool class | Microsoft Learn
download_file Download a file from the session pool.
-
Microsoft — Code Interpreter | Microsoft Learn
Code interpreter is a hosted tool — code execution happens on the AI service side, not locally.
-
Microsoft — File Search | Microsoft Learn
async def create_vector_store(client: OpenAIChatClient) -> tuple[str, str]: """Create a vector store with sample documents."""
-
Microsoft — semantic_kernel.core_plugins.text_memory_plugin.TextMemoryPlugin class | Microsoft Learn
relevance The relevance score, from 0.0 to 1.0; 1.0 means perfect match Default value: 0.75