Merge pull request OthersideAI#105 from michaelhhogue/evaluation-documentation

Add instructions for testing changes

Author: joshbickett

CONTRIBUTING.md

@@ -11,7 +11,20 @@ We appreciate your contributions!
 ## Modifying and Running Code
 1. Make changes in `operate/main.py`
 2. Run `pip install .` again
-3. Run `operate` to test your changes
+3. Run `operate` to see your changes
+
+## Testing Changes
+**After making significant changes, it's important to verify that SOC can still successfully perform a set of common test cases.**
+In the root directory of the project, run:
+```
+python3 evaluate.py
+``` 
+This will automatically prompt `operate` to perform several simple objectives. 
+Upon completion of each objective, GPT-4v will give an evaluation and determine if the objective was successfully reached. 
+
+`evaluate.py` will print out if each test case `[PASSED]` or `[FAILED]`. In addition, a justification will be given on why the pass/fail was given. 
+
+It is **strongly** recommended that a screenshot of the `evaluate.py` output is included in any PR which could impact the performance of SOC.
 
 ## Contribution Ideas
 - **Improve performance by finding optimal screenshot grid**: A primary element of the framework is that it overlays a percentage grid on the screenshot which GPT-4v uses to estimate click locations. If someone is able to find the optimal grid and some evaluation metrics to confirm it is an improvement on the current method then we will merge that PR.