diff --git a/README.md b/README.md
index adfef3a..d122da5 100644
--- a/README.md
+++ b/README.md
@@ -269,6 +269,7 @@ For each uploaded invoice image:
 - OCI Vision supports Portuguese OCR (`language="POR"` can be used instead of `"ENG"`).
 - LLM prompt can be adjusted to extract other fields like `CNPJ`, `quantidade`, `data de emissão`, etc.
 - Consider persisting `processed_files` with a database or file to make the process fault-tolerant.
+- This is part of the Use Case: [Build an AI Agent with Multi-Agent Communication Protocol Server for Invoice Resolution](https://docs.oracle.com/en/learn/oci-aiagent-mcp-server/) as a pre-processed Invoice Image. The invoice is a Devolution invoice came from the Company Customer. The fields customer and location are captured from the Invoice creator.
 
 ---
 
diff --git a/files/Invoice Multi-items.png b/files/Invoice Multi-items.png
deleted file mode 100644
index c4851e6..0000000
Binary files a/files/Invoice Multi-items.png and /dev/null differ
diff --git a/images/Invoice Multi-items.png b/images/Invoice Multi-items.png
new file mode 100644
index 0000000..8f55cef
Binary files /dev/null and b/images/Invoice Multi-items.png differ
diff --git a/images/img.png b/images/img.png
index 415067d..7bf61d3 100644
Binary files a/images/img.png and b/images/img.png differ