diff --git a/README.md b/README.md
index 538fb00..7a56758 100644
--- a/README.md
+++ b/README.md
@@ -45,6 +45,12 @@ Open http://localhost:5173 to use the app.
If you prefer to run the backend on a different port, update VITE_WS_BACKEND_URL in `frontend/.env.local`
+For debugging purposes, if you don't want to waste GPT4-Vision credits, you can run the backend in mock mode (which streams a pre-recorded response):
+
+```bash
+MOCK=true poetry run uvicorn main:app --reload --port 7001
+```
+
## Docker
If you have Docker installed on your system, in the root directory, run:
@@ -66,12 +72,10 @@ The app will be up and running at http://localhost:5173. Note that you can't dev
**NYTimes**
-| Original | Replica |
-| -------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
+| Original | Replica |
+| --------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 
| 
|
-
-
**Instagram page (with not Taylor Swift pics)**
https://github.com/abi/screenshot-to-code/assets/23818/503eb86a-356e-4dfc-926a-dabdb1ac7ba1
diff --git a/backend/main.py b/backend/main.py
index c97067d..93d2e9a 100644
--- a/backend/main.py
+++ b/backend/main.py
@@ -33,7 +33,8 @@ app.add_middleware(
# Useful for debugging purposes when you don't want to waste GPT4-Vision credits
# Setting to True will stream a mock response instead of calling the OpenAI API
-SHOULD_MOCK_AI_RESPONSE = False
+# TODO: Should only be set to true when value is 'True', not any abitrary truthy value
+SHOULD_MOCK_AI_RESPONSE = bool(os.environ.get("MOCK", False))
app.include_router(screenshot.router)