diff --git a/Confido/src/GenAICore.ts b/Confido/src/GenAICore.ts
new file mode 100644
index 00000000..a1cf3894
--- /dev/null
+++ b/Confido/src/GenAICore.ts
@@ -0,0 +1,120 @@
+import {
+  fetchAllPatientAppointmentsFromFb,
+  fetchClinicDetailsFromFb,
+  fetchPatientAssignedWorkflowFromFb,
+  fetchPatientFromFb,
+} from '../Utilities/FirestoreServices';
+import {
+  Variable,
+  WorkflowTask,
+  defaultClinicDetails,
+  defaultPatient,
+  defaultWorkflow,
+} from '../shared/FirestoreInterfaces';
+import { ChatOpenAI } from 'langchain/chat_models/openai';
+import { OpenAIEmbeddings } from 'langchain/embeddings/openai';
+import { Document } from 'langchain/document';
+import { HNSWLib } from 'langchain/vectorstores/hnswlib';
+import { RetrievalQAChain, loadQAStuffChain } from 'langchain/chains';
+import { defineString } from 'firebase-functions/v2/params';
+
+export const replyToPatientWithContext = async (
+  patientUid: string,
+  incomingMessage: string
+) => {
+  const openAiApiKey = defineString('OPENAI_API', { default: '' });
+
+  if (!openAiApiKey.value()) {
+    return '';
+  }
+
+  // Fetch all relevant data
+  let clinicDetails = await fetchClinicDetailsFromFb();
+  if (!clinicDetails) {
+    clinicDetails = { ...defaultClinicDetails };
+  }
+
+  let patient = await fetchPatientFromFb(patientUid);
+  if (!patient) {
+    patient = { ...defaultPatient };
+  }
+
+  let appointments = await fetchAllPatientAppointmentsFromFb(patientUid);
+  if (!appointments) {
+    appointments = [];
+  }
+
+  let currentAssignedWorkflows = null;
+  const surgeryTasks: any[] = [];
+  const surgeryDetails = new Map();
+  if (patient.currentAssignedWorkflowUid) {
+    currentAssignedWorkflows = await fetchPatientAssignedWorkflowFromFb(
+      patientUid,
+      patient.currentAssignedWorkflowUid
+    );
+  }
+  if (!currentAssignedWorkflows) {
+    currentAssignedWorkflows = { ...defaultWorkflow };
+  }
+
+  currentAssignedWorkflows.surgeryDetails.variables.forEach(
+    (variable: Variable) => surgeryDetails.set(variable.name, variable.value)
+  );
+
+  currentAssignedWorkflows.workflowTasks.forEach((task: WorkflowTask) => {
+    surgeryTasks.push({
+      name: task.name,
+      timeline: task.timeline,
+      message: task.patientMessageContent,
+    });
+  });
+
+  // Build document array
+  const docs = [
+    new Document({ pageContent: JSON.stringify(clinicDetails) }),
+    new Document({ pageContent: JSON.stringify(patient) }),
+    ...currentAssignedWorkflows.surgeryDetails.variables.map(
+      (variable: Variable) => {
+        return new Document({ pageContent: JSON.stringify(variable) });
+      }
+    ),
+    ...appointments.map((appointment) => {
+      return new Document({ pageContent: JSON.stringify(appointment) });
+    }),
+    ...surgeryTasks.map((task: any) => {
+      return new Document({ pageContent: JSON.stringify(task) });
+    }),
+  ];
+
+  // Convert to Vector store
+  const embeddingsModel = new OpenAIEmbeddings({
+    openAIApiKey: openAiApiKey.value(),
+  });
+  const vectorStore = await HNSWLib.fromDocuments(docs, embeddingsModel);
+  console.log(vectorStore);
+
+  const retreiver = vectorStore.asRetriever(40);
+  console.log(retreiver);
+
+  // Initialize LLM
+  const llm = new ChatOpenAI({
+    openAIApiKey: openAiApiKey.value(),
+    temperature: 0,
+    modelName: 'gpt-3.5-turbo',
+  });
+  console.log(llm);
+
+  // Setup retreival chain
+  const retreivalChain = new RetrievalQAChain({
+    retriever: retreiver,
+    combineDocumentsChain: loadQAStuffChain(llm),
+    verbose: true,
+  });
+  console.log(retreivalChain);
+
+  // Run the input message through the chain
+  const reply = await retreivalChain.run(incomingMessage);
+  console.log(reply);
+
+  return reply;
+};
diff --git a/README.md b/README.md
index 9d3f4a24..f2b38b62 100644
--- a/README.md
+++ b/README.md
@@ -1,26 +1,26 @@
-# Gen-Ai-Rush-Buildathon
+Team Name - Confido Health
+Problem Statement - Virtual Nurse AI to automate patient communication in complex treatments like surgeries
+Team Leader Email - vichar@confido.health
 
-## Submission Instruction:
-  1. Fork this repository
-  2. Create a folder with your Team Name
-  3. Upload all the code and necessary files in the created folder
-  4. Upload a **README.md** file in your folder with the below mentioned informations.
-  5. Generate a Pull Request with your Team Name. (Example: submission-XYZ_team)
+A Brief of the Prototype:
+Live prototype: https://clinical-workflow-demo.web.app/ [vichar@confido.health/VIchar1995]
+Link: 
+https://www.loom.com/share/d915cf751d56409ebd4516965c0b6243?sid=27c7322e-ae0a-44c9-b4e8-35d7813ccd36
 
-## README.md must consist of the following information:
+OpenAI LLM -> Retraining on Patient Context, Medical Record Data and Surgical Data -> Clinic Dashboard built on ReactJS -> Patient SMS via Twilio
 
-#### Team Name -
-#### Problem Statement - 
-#### Team Leader Email -
+Tech Stack:
+
+GenAI Stack:
+OpenAI
+Langchain
+
+Prototype Stack:
+Firebase, Firestore
+ReactJS
+NodeJS
+Twilio API for SMS
+
+What I Learned:
+- How to retrain an LLM on unstructured datasets like medical record data, patient context
 
-## A Brief of the Prototype:
-  This section must include UML Diagrams and prototype description
-  
-## Tech Stack: 
-   List Down all technologies used to Build the prototype
-   
-## Step-by-Step Code Execution Instructions:
-  This Section must contain a set of instructions required to clone and run the prototype so that it can be tested and deeply analyzed
-  
-## What I Learned:
-   Write about the biggest learning you had while developing the prototype