microsoft · leestott · Feb 27, 2026 · Feb 27, 2026 · Feb 27, 2026 · Copilot
diff --git a/.env.example b/.env.example
@@ -1,5 +1,5 @@
-# Azure AI Foundry Project (Required)
-# Your Azure AI Foundry project endpoint — used by AzureOpenAIResponsesClient
+# Azure AI Foundry Project (Required for most lessons)
+# Your Azure AI Foundry project endpoint
 AZURE_AI_PROJECT_ENDPOINT="https://..."
 
 # Model deployment name in your Foundry project (e.g., gpt-4o)
@@ -8,3 +8,11 @@ AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4o"
 # Azure AI Search (Required for Lesson 05 - Agentic RAG)
 AZURE_SEARCH_SERVICE_ENDPOINT="https://..."
 AZURE_SEARCH_API_KEY="..."
+
+# GitHub Models (Required for Lesson 06 and Lesson 08 GitHub Models workflows)
+GITHUB_TOKEN="..."
+GITHUB_ENDPOINT="https://models.inference.ai.azure.com"
+GITHUB_MODEL_ID="gpt-4o-mini"
+
+# Azure AI Bing Connection (Required for Lesson 08 - Bing grounding workflow)
+BING_CONNECTION_ID="..."
diff --git a/00-course-setup/README.md b/00-course-setup/README.md
@@ -236,6 +236,24 @@ Lesson 5 uses **Azure AI Search** for retrieval-augmented generation. If you pla
 | `AZURE_SEARCH_SERVICE_ENDPOINT` | Azure portal → your **Azure AI Search** resource → **Overview** → URL |
 | `AZURE_SEARCH_API_KEY` | Azure portal → your **Azure AI Search** resource → **Settings** → **Keys** → primary admin key |
 
+## Additional Setup for Lesson 6 and Lesson 8 (GitHub Models)
+
+Some notebooks in lessons 6 and 8 use **GitHub Models** instead of Azure AI Foundry. If you plan to run those samples, add these variables to your `.env` file:
+
+| Variable | Where to find it |
+|----------|-----------------|
+| `GITHUB_TOKEN` | GitHub → **Settings** → **Developer settings** → **Personal access tokens** |
+| `GITHUB_ENDPOINT` | Use `https://models.inference.ai.azure.com` (default value) |
+| `GITHUB_MODEL_ID` | Model name to use (e.g. `gpt-4o-mini`) |
+
+## Additional Setup for Lesson 8 (Bing Grounding Workflow)
+
+The conditional workflow notebook in lesson 8 uses **Bing grounding** via Azure AI Foundry. If you plan to run that sample, add this variable to your `.env` file:
+
+| Variable | Where to find it |
+|----------|-----------------|
+| `BING_CONNECTION_ID` | Azure AI Foundry portal → your project → **Management** → **Connected resources** → your Bing connection → copy the connection ID |
+
 ## Stuck Somewhere?
 
 If you have any issues running this setup, hop into our <a href="https://discord.gg/kzRShWzttr" target="_blank">Azure AI Community Discord</a> or <a href="https://github.com/microsoft/ai-agents-for-beginners/issues?WT.mc_id=academic-105485-koreyst" target="_blank">create an issue</a>.

diff --git a/02-explore-agentic-frameworks/README.md b/02-explore-agentic-frameworks/README.md
@@ -84,8 +84,7 @@ def book_flight(date: str, location: str) -> str:
 
 
 async def main():
-    provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),
-    )
+    provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())
     agent = await provider.create_agent(
         name="travel_agent",
         instructions="Help the user book travel. Use the book_flight tool when ready.",
@@ -120,8 +119,7 @@ import os
 from agent_framework.azure import AzureAIProjectAgentProvider
 from azure.identity import AzureCliCredential
 
-provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),
-)
+provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())
 
 # Data Retrieval Agent
 agent_retrieve = await provider.create_agent(
@@ -177,8 +175,7 @@ Here are some important core concepts of the Microsoft Agent Framework:
     from agent_framework.azure import AzureAIProjectAgentProvider
     from azure.identity import AzureCliCredential
 
-    provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),
-    )
+    provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())
     agent = await provider.create_agent(
         name="my_agent",
         instructions="You are a helpful assistant.",

diff --git a/04-tool-use/README.md b/04-tool-use/README.md
@@ -75,7 +75,7 @@ Let's use the example of getting the current time in a city to illustrate:
     ```python
     # Initialize the Azure OpenAI client
     client = AzureOpenAI(
-        azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
+        azure_endpoint = os.getenv("AZURE_AI_PROJECT_ENDPOINT"), 
-        azure_endpoint = os.getenv("AZURE_AI_PROJECT_ENDPOINT"), 
+        azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"),
-        azure_endpoint = os.getenv("AZURE_AI_PROJECT_ENDPOINT"), 
+        azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"),
         api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
         api_version="2024-05-01-preview"
     )
@@ -225,10 +225,7 @@ def get_current_time(location: str) -> str:
     ...
 
 # Create the client
-provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),
-    project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
-    deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
-)
+provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())
 
 # Create an agent and run with the tool
 agent = await provider.create_agent(name="TimeAgent", instructions="Use available tools to answer questions.", tools=get_current_time)

diff --git a/06-building-trustworthy-agents/README.md b/06-building-trustworthy-agents/README.md
@@ -169,8 +169,6 @@ from azure.identity import AzureCliCredential
 # Create the provider with human-in-the-loop approval
 provider = AzureAIProjectAgentProvider(
     credential=AzureCliCredential(),
-    endpoint=os.getenv("AZURE_AI_PROJECT_ENDPOINT"),
-    model="gpt-4o-mini",
 )
 
 # Create the agent with a human approval step

diff --git a/07-planning-design/README.md b/07-planning-design/README.md
@@ -81,10 +81,7 @@ class TravelPlan(BaseModel):
     subtasks: List[TravelSubTask]
     is_greeting: bool
 
-provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),
-    endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
-    model="gpt-4o-mini",
-)
+provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())
 
 # Define the user message
 system_prompt = """You are a planner agent.
@@ -157,10 +154,7 @@ from azure.identity import AzureCliCredential
 
 # Create the client
 
-provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),
-    endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
-    model=os.getenv("AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"),
-)
+provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())
 
 from pprint import pprint
 

diff --git a/10-ai-agents-production/code_samples/10-python-agent-framework.ipynb b/10-ai-agents-production/code_samples/10-python-agent-framework.ipynb
@@ -61,10 +61,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Create the Azure OpenAI Responses client using Azure CLI credentials\n",
-    "provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),\n",
-    "    project_endpoint=os.environ[\"AZURE_AI_PROJECT_ENDPOINT\"],\n",
-    ")"
+    "# Create the Azure AI Foundry provider\n",
+    "provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())\n"
    ]
   },
   {
@@ -238,4 +236,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}
diff --git a/12-context-engineering/code_samples/12-chat_summarization.ipynb b/12-context-engineering/code_samples/12-chat_summarization.ipynb
@@ -59,14 +59,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Load environment variables and create Azure OpenAI client\n",
+    "# Load environment variables and create Azure AI Foundry provider\n",
     "load_dotenv()\n",
     "\n",
-    "provider = AzureAIProjectAgentProvider(credential=AzureCliCredential()),\n",
-    "    deployment_name=os.environ[\"AZURE_AI_MODEL_DEPLOYMENT_NAME\"],\n",
-    ")\n",
+    "provider = AzureAIProjectAgentProvider(credential=AzureCliCredential())\n",
     "\n",
-    "print(\"✅ Azure OpenAI client configured\")"
+    "print(\"✅ Azure AI Foundry provider configured\")\n"
    ]
   },
   {
@@ -303,4 +301,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}