diff --git a/examples/multimodal/multimodal_report_generation_agent.ipynb b/examples/multimodal/multimodal_report_generation_agent.ipynb
index bd89b78..1225815 100644
--- a/examples/multimodal/multimodal_report_generation_agent.ipynb
+++ b/examples/multimodal/multimodal_report_generation_agent.ipynb
@@ -11,6 +11,8 @@
     "\n",
     "In this cookbook we show you how to build a multimodal report generation agent from a bank of research reports. We use the a set of ICLR papers (which were also used as the dataset in our [DeepLearning.ai course](https://www.deeplearning.ai/short-courses/building-agentic-rag-with-llamaindex/?utm_campaign=llamaindexC2-launch&utm_medium=headband&utm_source=dlai-homepage).\n",
     "\n",
+    "![](multimodal_report_generation_agent_img.png)\n",
+    "\n",
     "We use our workflow abstraction to define an agentic system that contains two main phases: a research phase that pulls in relevant files through chunk-level or file-level retrieval, and then a blog generation phase that synthesizes the final report."
    ]
   },
diff --git a/examples/multimodal/multimodal_report_generation_agent_img.png b/examples/multimodal/multimodal_report_generation_agent_img.png
new file mode 100644
index 0000000..7b98423
Binary files /dev/null and b/examples/multimodal/multimodal_report_generation_agent_img.png differ