diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..707a9ee
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,16 @@
+.git
+.gitignore
+.venv
+venv
+env/
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+test/
+README.md
+docker-compose.yml
+Dockerfile
+.dockerignore
+.files/
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index f967714..1b5c3a2 100644
Binary files a/.gitignore and b/.gitignore differ
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..5af32eb
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,18 @@
+FROM python:3.11-slim
+WORKDIR /main
+
+RUN apt-get update && apt-get install -y \
+    gcc \
+    g++ \
+    make \
+    pkg-config \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+ENTRYPOINT ["chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "8000"]
\ No newline at end of file
diff --git a/core/__init__.py b/README.md
similarity index 100%
rename from core/__init__.py
rename to README.md
diff --git a/api/tools/admin_proceedings.py b/api/tools/admin_proceedings.py
index 2b5ef81..8bde97a 100644
--- a/api/tools/admin_proceedings.py
+++ b/api/tools/admin_proceedings.py
@@ -1,4 +1,5 @@
 from api.fetch_api_data import fetch_api_data, docstring_from_model
+
 from api.schemas import (AdministrativeProceedings,
                          AdministrativeProceedingsID,
                          AdministrativeProceedingsAutocomplete)
diff --git a/app.py b/app.py
index de748f1..cd0671d 100644
--- a/app.py
+++ b/app.py
@@ -1,8 +1,12 @@
+import os
 import chainlit as cl
 
 from core.initialize_agent import assistant_agent
 from core.stream_response import stream_response
 
+def clear_screen():
+    os.system('cls' if os.name == 'nt' else 'clear')
+
 @cl.set_starters
 async def set_starters():
     return [
@@ -47,6 +51,8 @@ async def chat_profile():
 
 @cl.on_chat_start
 async def start():
+    clear_screen()
+
     cl.user_session.set("message_history", [])
 
     profile = cl.user_session.get("chat_profile")
diff --git a/core/__init__ b/core/__init__
new file mode 100644
index 0000000..e69de29
diff --git a/core/initialize_agent.py b/core/initialize_agent.py
index 16d2167..ee29c04 100644
--- a/core/initialize_agent.py
+++ b/core/initialize_agent.py
@@ -1,4 +1,4 @@
-from agents import Agent
+from agents import Agent, AgentHooks
 from agents import OpenAIChatCompletionsModel, AsyncOpenAI, ModelSettings
 from agents import set_tracing_disabled, enable_verbose_stdout_logging
 
@@ -16,6 +16,10 @@ enable_verbose_stdout_logging()
 
 class BaseAgent(Agent[None]): pass
 
+class MyAgentHooks(AgentHooks):
+  async def on_start(self, context, agent): print(f"\n🏃‍♂️‍➡️[AgentHooks] {agent.name} started.")
+  async def on_end(self, context, agent, output): print(f"\n🏁[AgentHooks] {agent.name} ended.")
+
 def assistant_agent(model_name: str = "qwen3-next:80b-cloud") -> BaseAgent:
 
     judge_api = JudgesAPI()
@@ -50,6 +54,7 @@ def assistant_agent(model_name: str = "qwen3-next:80b-cloud") -> BaseAgent:
         ],
         tool_use_behavior="run_llm_again",
         reset_tool_choice=True,
+        hooks=MyAgentHooks(),
     )
 
     return agent
\ No newline at end of file
diff --git a/core/stream_response.py b/core/stream_response.py
index f08bfd3..1ceeda9 100644
--- a/core/stream_response.py
+++ b/core/stream_response.py
@@ -1,26 +1,23 @@
-from typing import Any
+from typing import Any, AsyncGenerator
 from agents import Agent, Runner
-from agents import RunHooks, RunContextWrapper
+from agents import RunHooks, ModelResponse
 from openai.types.responses import ResponseTextDeltaEvent
 
-class MyHooks(RunHooks):
-    """Custom hooks to track usage after each model request."""
-    async def on_model_response(self, context: RunContextWrapper, agent: Agent, output: Any) -> None:
-        ctx_usage = context.usage
-        if ctx_usage:
-            print(f"\n🪙{agent.name} → {ctx_usage.requests} requests")
-            print(f"\n🪙Input tokens: {ctx_usage.input_tokens}")
-            print(f"\n🪙Output tokens: {ctx_usage.output_tokens}")
-            print(f"\n🪙Total tokens: {ctx_usage.total_tokens}")
+class MyRunHooks(RunHooks):
+    """RunHooks for logging the lifecycle of an agent."""
+    async def on_agent_start(self, context, agent) -> None:
+        print(f"\n 🐾[RunHooks] {agent.name} started.\n")
 
+    async def on_agent_end(self, context, agent, output: Any) -> None:
+        print(f"\n 🚪[RunHooks] {agent.name} ended.\n")
 
-async def stream_response(agent: Agent, prompt: str):
+async def stream_response(agent: Agent, prompt: str) -> AsyncGenerator[str, None]:
     """Stream agent response and update the UI."""
-    hooks = MyHooks()
     try:
-        result = Runner.run_streamed(agent, input=prompt, hooks=hooks)
+        result = Runner.run_streamed(agent, input=prompt, hooks=MyRunHooks())
         async for event in result.stream_events():
             if event.type == "raw_response_event" and isinstance(event.data, ResponseTextDeltaEvent):
                 yield event.data.delta # <-- sends the next piece of response text
+
     except Exception as e:
         yield f"⚠️🖨️ Error: {e}"
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..bd7ca55
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,13 @@
+version: "3.8"
+
+services:
+  legal-ai-assistant:
+    build: .
+    ports:
+      - "8000:8000"
+    volumes:
+      - .:/main
+    environment:
+      - PYTHONPATH=/main
+      - PYTHONUNBUFFERED=1
+    restart: unless-stopped
\ No newline at end of file