diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..1ea5834
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,2 @@
+GROQ_API_KEY=your_groq_api_key_here
+LLM_PROVIDER=groq
diff --git a/README.MD b/README.MD
index 158ecf0..cf37a48 100644
--- a/README.MD
+++ b/README.MD
@@ -14,13 +14,26 @@ BonziAssist revives the classic BonziBuddy assistant in a modern, voice-activate
 
 ### Installation
 1. Clone this repository.
-2. Ensure you have [Python](https://www.python.org/downloads/) and [Visual CPP Build Tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/). installed, and then run `pip install -r requirements.txt` to install the necessary packages.
-4. Set up your environment variables. Edit the `.env.example` file in `helpers\` and follow the instructions there. `[INSTRUCTIONS='Remove this line of instructions. Fill out the info below. Rename this file, and remove the .example. It should just be ".env" now.']`
+2. Ensure you have [Python](https://www.python.org/downloads/) and [Visual CPP Build Tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/) installed.
+3. Install the required packages:
+```bash
+python -m pip install -r requirements.txt
+```
+4. Set up your environment variables:
+```bash
+copy .env.example .env
+```
+Then open `.env` and set `GROQ_API_KEY` and `LLM_PROVIDER`.
 
 ### Usage
-To start BonziAssist:
+Before starting BonziAssist, run the setup check:
+```bash
+python start.py --check
+```
+
+If the check passes, start BonziAssist:
 ```bash
-python main.py
+python start.py
 ```
 
 You will be prompted to configure your microphone settings upon the first run or if you choose to be prompted every time by the configuration settings.
@@ -60,4 +73,4 @@ First of all, I appreciate anyone being excited about this project. That being s
 - **SimpleAudio**: Used for playing back audio responses generated by the system.
 - **PyAudio**: Handles microphone input and audio stream management.
 - **Python-dotenv**: For managing environment variables in a .env file, which helps secure API keys and other sensitive settings.
-- **GitHub Community**: For all the open-source contributors who have developed libraries and tools that made this project feasible.
\ No newline at end of file
+- **GitHub Community**: For all the open-source contributors who have developed libraries and tools that made this project feasible.
diff --git a/helpers/llm.py b/helpers/llm.py
index 3aba156..3854606 100644
--- a/helpers/llm.py
+++ b/helpers/llm.py
@@ -1,17 +1,20 @@
 import os
+from pathlib import Path
+
 from dotenv import load_dotenv
 import litellm
 
-load_dotenv()
+PROJECT_ROOT = Path(__file__).resolve().parents[1]
+load_dotenv(PROJECT_ROOT / ".env")
 
 groq_api_key = os.getenv("GROQ_API_KEY")
 llm_provider = os.getenv("LLM_PROVIDER")
 
 if groq_api_key is None:
-    raise ValueError("GROQ_API_KEY environment variable not found. Please set it in your .env file.")
+    raise ValueError("GROQ_API_KEY environment variable not found. Copy .env.example to .env and set your key.")
 
 if llm_provider is None:
-    raise ValueError("LLM_PROVIDER environment variable not found. Please set it in your .env file.")
+    raise ValueError("LLM_PROVIDER environment variable not found. Copy .env.example to .env and set your provider.")
 
 os.environ["GROQ_API_KEY"] = groq_api_key
 
@@ -34,4 +37,4 @@ def request(user_query, model="llama3-8b-8192", temperature=0.7, max_tokens=150)
         max_tokens=max_tokens
     )
     
-    return response.choices[0].message.content
\ No newline at end of file
+    return response.choices[0].message.content
diff --git a/helpers/mic.py b/helpers/mic.py
index 5101544..04a0f70 100644
--- a/helpers/mic.py
+++ b/helpers/mic.py
@@ -1,8 +1,11 @@
-import pyaudio
-import os
 import json
+from pathlib import Path
+
+import pyaudio
 
-CONFIG_FILE = "config\mic_config.json"
+PROJECT_ROOT = Path(__file__).resolve().parents[1]
+CONFIG_FILE = PROJECT_ROOT / "config" / "mic_config.json"
+LEGACY_CONFIG_FILE = PROJECT_ROOT / "mic_config.json"
 
 def list_microphones():
     p = pyaudio.PyAudio()
@@ -34,13 +37,17 @@ def get_device_index(num_devices, default_device_index, default_device_name):
         print("Invalid input. Please enter a valid number.")
 
 def load_config():
-    if os.path.exists(CONFIG_FILE):
-        with open(CONFIG_FILE, "r") as f:
+    if CONFIG_FILE.exists():
+        with CONFIG_FILE.open("r") as f:
+            return json.load(f)
+    if LEGACY_CONFIG_FILE.exists():
+        with LEGACY_CONFIG_FILE.open("r") as f:
             return json.load(f)
     return None
 
 def save_config(config):
-    with open(CONFIG_FILE, "w") as f:
+    CONFIG_FILE.parent.mkdir(parents=True, exist_ok=True)
+    with CONFIG_FILE.open("w") as f:
         json.dump(config, f, indent=4)
 
 def configure_microphone():
@@ -57,4 +64,4 @@ def configure_microphone():
         "prompt_every_time": prompt_every_time == 'y'
     }
     save_config(config)
-    return config
\ No newline at end of file
+    return config
diff --git a/main.py b/main.py
index c312325..0a4b82f 100644
--- a/main.py
+++ b/main.py
@@ -71,9 +71,12 @@ def listen_for_bonzi(device_index=None):
                 time.sleep(.45)
                 command_active = True  # Enable command capture
 
-if __name__ == "__main__":
+def main():
     config = mic.load_config()
     if config is None or config.get("prompt_every_time", False):
         config = mic.configure_microphone()
     device_index = config['device_index']
     listen_for_bonzi(device_index)
+
+if __name__ == "__main__":
+    main()
diff --git a/requirements.txt b/requirements.txt
index 0564ce1..6de2b72 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,6 @@
 pyaudio
 python-dotenv
 litellm
+requests
 simpleaudio
 vosk
diff --git a/start.py b/start.py
new file mode 100644
index 0000000..bbc83cf
--- /dev/null
+++ b/start.py
@@ -0,0 +1,103 @@
+import argparse
+import importlib.util
+import os
+import sys
+from pathlib import Path
+
+
+PROJECT_ROOT = Path(__file__).resolve().parent
+REQUIRED_PACKAGES = {
+    "dotenv": "python-dotenv",
+    "litellm": "litellm",
+    "pyaudio": "pyaudio",
+    "requests": "requests",
+    "simpleaudio": "simpleaudio",
+    "vosk": "vosk",
+}
+
+
+def missing_packages():
+    missing = []
+    for import_name, package_name in REQUIRED_PACKAGES.items():
+        if importlib.util.find_spec(import_name) is None:
+            missing.append(package_name)
+    return missing
+
+
+def load_env_file():
+    env_path = PROJECT_ROOT / ".env"
+    values = {}
+    if not env_path.exists():
+        return values
+
+    for line in env_path.read_text().splitlines():
+        line = line.strip()
+        if not line or line.startswith("#") or "=" not in line:
+            continue
+        key, value = line.split("=", 1)
+        values[key.strip()] = value.strip()
+    return values
+
+
+def check_setup():
+    errors = []
+    warnings = []
+
+    missing = missing_packages()
+    if missing:
+        errors.append(
+            "Install missing packages with: "
+            + f"{sys.executable} -m pip install -r requirements.txt"
+            + f" (missing: {', '.join(missing)})"
+        )
+
+    env_path = PROJECT_ROOT / ".env"
+    env_values = load_env_file()
+    if not env_path.exists():
+        errors.append("Create .env by copying .env.example, then set GROQ_API_KEY and LLM_PROVIDER.")
+    else:
+        for key in ("GROQ_API_KEY", "LLM_PROVIDER"):
+            if not env_values.get(key) or env_values[key].startswith("your_"):
+                errors.append(f"Set {key} in .env.")
+
+    model_path = PROJECT_ROOT / "vosk" / "vosk-model-small-en-us-0.15"
+    if not model_path.exists():
+        errors.append("The Vosk model is missing. Expected: vosk/vosk-model-small-en-us-0.15")
+
+    if not (PROJECT_ROOT / "canned_responses").exists():
+        errors.append("The canned_responses folder is missing.")
+
+    if not (PROJECT_ROOT / "config").exists():
+        warnings.append("The config folder will be created on first microphone setup.")
+
+    return errors, warnings
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Check and start BonziAssist.")
+    parser.add_argument("--check", action="store_true", help="Only check setup and exit.")
+    args = parser.parse_args()
+
+    os.chdir(PROJECT_ROOT)
+    errors, warnings = check_setup()
+
+    for warning in warnings:
+        print(f"Warning: {warning}")
+
+    if errors:
+        print("BonziAssist is not ready to start:")
+        for error in errors:
+            print(f"- {error}")
+        raise SystemExit(1)
+
+    print("BonziAssist setup looks ready.")
+    if args.check:
+        return
+
+    from main import main as run_bonzi
+
+    run_bonzi()
+
+
+if __name__ == "__main__":
+    main()