Update README.md

README.md

@@ -22,7 +22,8 @@ license: mit
   <p align="center" style="width:50%">
     Final hands-on assignment for the Hugging Face Agents course. In this project I built a multi-agent solution, evaluated it against questions from the General AI Assistants (GAIA) benchmark (level one only), and got creative with some agent and tool improvements. 
 </div>
-## About The Project
+
+##About The Project
 
 ![[HF Space Screen Shot][images/submit_answers.jpg]](https://huggingface.co/spaces/civerson916/Final_Assignment_Template)
 
@@ -34,7 +35,7 @@ Achieving 30 points for the certification was relatively easy with the template
 
 Beyond what looks like a smolagents guided tour, you can find the following in this repo... 
 
-* Research agent armed with Google search via [Serper](https://serper.dev/) and both Audo and Video Understanding via [Gemini] (https://ai.google.dev/gemini-api/docs/)video-understanding#python)
+* Research agent armed with Google search via [Serper](https://serper.dev/) and both Audo and Video Understanding via [Gemini](https://ai.google.dev/gemini-api/docs/)video-understanding)
 * Chess agent leveraging my [board_to_fen](https://github.com/civerson/board_to_fen) fork and a Stockfish API.
 * [Langfuse](https://langfuse.com/) setup boilerplate, a working example. This is an absolute must.
 * [Pydantic](https://docs.pydantic.dev/latest/) settings for type safety, centralized, and encapsulated config.