diff --git a/.github/workflows/document_deploy.yml b/.github/workflows/document_deploy.yml
index 8444c6e4..1a9bb9cd 100644
--- a/.github/workflows/document_deploy.yml
+++ b/.github/workflows/document_deploy.yml
@@ -11,6 +11,8 @@ on:
 jobs:
   deploy:
     runs-on: ubuntu-latest
+    permissions:
+      contents: write
 
     steps:
       - name: Checkout repository
diff --git a/documents/docs/getting_started/quick_start.md b/documents/docs/getting_started/quick_start.md
index 7fab390c..1bb85467 100644
--- a/documents/docs/getting_started/quick_start.md
+++ b/documents/docs/getting_started/quick_start.md
@@ -42,6 +42,7 @@ API_DEPLOYMENT_ID: "YOUR_AOAI_DEPLOYMENT", # The deployment id for the AOAI API
 You can also non-visial model (e.g., GPT-4) for each agent, by setting `VISUAL_MODE: False` and proper `API_MODEL` (openai) and `API_DEPLOYMENT_ID` (aoai). You can also optionally set an backup LLM engine in the field of `BACKUP_AGENT` if the above engines failed during the inference. The `API_MODEL` can be any GPT models that can accept images as input.
 
 
+
 ####  Non-Visual Model Configuration
 You can utilize non-visual models (e.g., GPT-4) for each agent by configuring the following settings in the `config.yaml` file: