Update README with Agentic vs Chatbot comparison and new feature highlights

README.md

@@ -25,26 +25,24 @@ Imagine a patient arriving in severe respiratory distress. The physician orders
 
 This happens every day. Medical errors are the 3rd leading cause of death. Our system is built to ensure it never happens again by employing **Five Specialized AI Agents** that act as the ultimate safety net for emergency physicians.
 
-## 🧠 The 5-Agent Architecture
+## 🧠 Agentic Orchestration vs. Standard Chatbots
 
-This system uses a sequential orchestration of 5 Gemini-powered AI agents (using `gemini-2.0-flash`):
+A typical medical chatbot is a single model answering a single prompt. CodeBlue Context is **fundamentally different**:
 
-1. **Triage Agent**: Determines ESI severity level and identifies time-critical flags (e.g., "Sepsis Alert").
-2. **Contraindication Guardian**: Cross-references every medication and allergy against proposed emergency treatments.
-3. **Lab Interpreter**: Instantly highlights critical abnormalities and their immediate clinical significance (e.g., "Potassium 6.8 - High risk of cardiac arrest").
-4. **Differential Diagnosis Agent**: Formulates the top 3 emergency differentials based strictly on evidence, not guesswork.
-5. **Action Protocol Agent**: Suggests the immediate next steps, required monitoring, and patient disposition.
-
-*(Crucially: A deterministic rules engine acts as a permanent fallback for safety, ensuring an emergency brief is always generated—even if the AI API is rate-limited or unavailable).*
+*   **Multi-Agent Pipeline**: Instead of one "black box" answer, we use a **sequential team of 5 specialists**. Each agent (Triage, Guardian, Pathologist, Physician, Attending) performs a specific task and "hands off" its findings to the next, just like a real ER team.
+*   **Inter-Agent Communication**: Our agents don't just work in isolation; they **cross-reference** each other. If the Pathologist finds a high INR, the Guardian agent automatically blocks anticoagulants in the Action Protocol.
+*   **Deterministic Guardrails**: We combine LLM intelligence with a **deterministic core**. If the AI is unavailable, our hardcoded medical rules engine still extracts and highlights critical vitals and labs, ensuring the system never fails in an emergency.
+*   **Explainability**: Every decision includes a "Collaboration Thread" showing the reasoning of each agent, making it a "Glass Box" system that doctors can trust.
 
 ## 🌟 Hackathon-Winning Features
 
-- **Upload Anything (PDF, DOC, JSON, Image)**: Doctors don't always have structured JSON. Drop a raw clinical PDF chart into our system, and our Gemini Vision extractor instantly structures the raw text into a parsable medical context.
-- **Live "Run Demo" Feature**: One click in the navbar instantly simulates a critical patient crashing, allowing judges to watch the 5-agent orchestration happen in real-time.
-- **MCP Integration**: Fully exposes an MCP Tool Manifest (`/mcp/tools`), making it 100% compliant with PromptOpinion and modern Agent-to-Agent architectures.
-- **Explainability First**: Every AI reasoning step is exposed. It doesn't just give an answer; it shows *why* it arrived at that conclusion.
-- **Live Treatment Checker**: Instantly type in a proposed drug (e.g., "morphine") and cross-check it against the patient's entire profile.
-- **Medical-Grade UI**: A highly polished, dark-themed, glass-morphic React dashboard with pulse animations, strictly color-coded for critical (Red), moderate (Amber), and stable (Green) alerts.
+- **Advanced Clinical Consultation**: Beyond the initial brief, doctors can enter "Consult Mode" to ask the 5-agent team specific follow-up questions (e.g., *"Why did you exclude pulmonary embolism?"*).
+- **Primary Clinical Directive**: A high-impact banner that identifies the single most important stabilization task in milliseconds.
+- **"Hospital Clinical" UI**: A professional, high-contrast "Blue-Green" dashboard with pulse animations, designed for readability in high-stress hospital environments.
+- **Real-Time Thinking Logs**: Watch the agents "deliberate" in real-time with terminal-style logs showing their cross-checks and hand-offs.
+- **BYOK (Bring Your Own Key)**: Securely inject your own Gemini API key via the UI to bypass server-side rate limits during live demonstrations.
+- **Upload Anything (PDF, DOC, JSON, Image)**: Gemini Vision structures raw clinical charts into parsable medical contexts instantly.
+- **MCP Compliance**: Fully exposes an MCP Tool Manifest (`/mcp/tools`) for seamless integration with modern agent ecosystems.
 
 ## 🚀 Run Locally