diff --git a/README.md b/README.md
index 002ecbb..618e5d7 100644
--- a/README.md
+++ b/README.md
@@ -68,6 +68,7 @@ Key Python libraries used:
 *   `mlx` / `mlx-lm`: Likely used for efficient model inference, especially on Apple Silicon.
 *   `mcp`: For integrating external tools via the Multi-Agent Collaboration Protocol.
 *   `python-dotenv`: For managing environment variables (e.g., API keys).
+*   `rich`: For beautiful terminal formatting and progress indicators.
 
 See `pyproject.toml` for the full list of dependencies.
 
@@ -77,4 +78,4 @@ This an architectural spike, I welcome your feedback through `qwan.eu/contact`.
 
 ## License
 
-Apache 2.0
\ No newline at end of file
+Apache 2.0
diff --git a/agentic_search.py b/agentic_search.py
index 89ea505..5bf8c8f 100644
--- a/agentic_search.py
+++ b/agentic_search.py
@@ -1,5 +1,6 @@
-import json  # Import the json module
-
+import json
+from rich.console import Console
+from rich.spinner import Spinner
 from qwen_agent.agents import Assistant
 
 # Define LLM
@@ -41,6 +42,7 @@ tools = [
 
 # Define Agent
 bot = Assistant(llm=llm_cfg, function_list=tools)
+console = Console()
 
 # Streaming generation
 messages = [{'role': 'user',
@@ -53,17 +55,17 @@ messages = [{'role': 'user',
 final_responses = None
 # Consider adding error handling around bot.run
 try:
-    for responses in bot.run(messages=messages, enable_thinking=True, max_tokens=30000):
-        print(".", end="", flush=True)
-        final_responses = responses.pop()
+    with console.status("[bold blue]Thinking...", spinner="dots") as status:
+        for responses in bot.run(messages=messages, enable_thinking=True, max_tokens=30000):
+            final_responses = responses.pop()
 except Exception as e:
-    print(f"An error occurred during agent execution: {e}")
+    console.print(f"[bold red]An error occurred during agent execution:[/] {e}")
 
 # Pretty-print the final response object
 if final_responses:
-    print("--- Full Response Object ---")
-    print(json.dumps(final_responses, indent=2))  # Use indent=2 (or 4) for pretty printing
-    print("\n--- Extracted Content ---")
-    print(final_responses.get('content', 'No content found in response.'))  # Use .get for safer access
+    console.print("\n[bold green]--- Full Response Object ---[/]")
+    console.print(json.dumps(final_responses, indent=2))
+    console.print("\n[bold green]--- Extracted Content ---[/]")
+    console.print(final_responses.get('content', 'No content found in response.'))
 else:
-    print("No final response received from the agent.")
\ No newline at end of file
+    console.print("[bold red]No final response received from the agent.[/]")
diff --git a/pyproject.toml b/pyproject.toml
index 9ad7ecd..1f2abfa 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -11,4 +11,5 @@ dependencies = [
     "python-dateutil>=2.9.0.post0",
     "python-dotenv>=1.1.0",
     "qwen-agent[code-interpreter]>=0.0.20",
+    "rich>=13.7.0",
 ]