diff --git a/demos/hr_agent/Dockerfile b/demos/hr_agent/Dockerfile
new file mode 100644
index 00000000..503ffeff
--- /dev/null
+++ b/demos/hr_agent/Dockerfile
@@ -0,0 +1,19 @@
+FROM python:3.10 AS base
+
+FROM base AS builder
+
+WORKDIR /src
+
+COPY requirements.txt /src/
+RUN pip install --prefix=/runtime --force-reinstall -r requirements.txt
+
+COPY . /src
+
+FROM python:3.10-slim AS output
+
+COPY --from=builder /runtime /usr/local
+
+COPY . /app
+WORKDIR /app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--log-level", "info"]
diff --git a/demos/hr_agent/arch_config.yaml b/demos/hr_agent/arch_config.yaml
new file mode 100644
index 00000000..4294278a
--- /dev/null
+++ b/demos/hr_agent/arch_config.yaml
@@ -0,0 +1,58 @@
+version: v0.1
+listener:
+  address: 127.0.0.1
+  port: 8080 #If you configure port 443, you'll need to update the listener with tls_certificates
+  message_format: huggingface
+
+# Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
+llm_providers:
+  - name: OpenAI
+    provider: openai
+    access_key: OPENAI_API_KEY
+    model: gpt-4o
+    default: true
+
+# default system prompt used by all prompt targets
+system_prompt: |
+  You are a HR agent assistant that helps HR decision makers with reporting and workfoce planning. Nothing else. Please stay on topic of HR.
+
+prompt_targets:
+    - name: headcount
+      description: Get headcount data for a region by staffing type
+      endpoint:
+        name: app_server
+        path: /agent/headcount
+      parameters:
+        - name: staffing_type
+          type: str
+          description: The staffing type like contract, fte or agency 
+          required: true
+        - name: region
+          type: str
+          required: true
+          description: the geographical region for which you want head count data. 
+    - name: hr_qa
+      endpoint:
+        name: app_server
+        path: /agent/hr_qa
+      description: Handle general Q/A related to HR.
+      default: true
+
+# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
+endpoints:
+  app_server:
+    # value could be ip address or a hostname with port
+    # this could also be a list of endpoints for load balancing
+    # for example endpoint: [ ip1:port, ip2:port ]
+    endpoint: host.docker.internal:18083
+    # max time to wait for a connection to be established
+    connect_timeout: 0.005s
+
+ratelimits:
+  - model: gpt-4
+    selector:
+      key: selector-key
+      value: selector-value
+    limit:
+      tokens: 1
+      unit: minute
diff --git a/demos/hr_agent/docker-compose.yaml b/demos/hr_agent/docker-compose.yaml
new file mode 100644
index 00000000..7ea41173
--- /dev/null
+++ b/demos/hr_agent/docker-compose.yaml
@@ -0,0 +1,23 @@
+services:
+  api_server:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "18083:80"
+    healthcheck:
+        test: ["CMD", "curl" ,"http://localhost:80/healthz"]
+        interval: 5s
+        retries: 20
+
+  chatbot_ui:
+    build:
+      context: ../../chatbot_ui
+      dockerfile: Dockerfile
+    ports:
+      - "18080:8080"
+    environment:
+      - OPENAI_API_KEY=${OPENAI_API_KEY:?error}
+      - CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
diff --git a/demos/hr_agent/main.py b/demos/hr_agent/main.py
new file mode 100644
index 00000000..5bd65b62
--- /dev/null
+++ b/demos/hr_agent/main.py
@@ -0,0 +1,73 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel, Field
+from typing import List, Optional
+from enum import Enum
+import re
+
+app = FastAPI()
+
+class StaffingType(Enum):
+    CONTRACT = "contract"
+    FTE = "fte"
+    AGENCY = "agency"
+
+# Define the request model
+class HeadcountRequest(BaseModel):
+    region: str
+    staffing_type: str
+
+class HeadcountResponseSummary(BaseModel):
+    region: str
+    headcount: int
+    staffing_type: str
+
+# Post method for device summary
+@app.post("/agent/headcount")
+def get_headcount(request: HeadcountRequest):
+    """
+    Endpoint to headcount data by region, staffing type over time range
+    """
+    staffing_type_value = request.staffing_type
+
+    if re.match(r"(?i)contract", staffing_type_value):  # Case-insensitive regex match
+        headcount = 500
+    elif re.match(r"(?i)fte", staffing_type_value):
+        headcount = 1000
+    elif re.match(r"(?i)agency", staffing_type_value):
+        headcount = 4000
+    else:
+        raise HTTPException(
+            status_code=400, detail="staffing_type parameter is invalid."
+        )
+
+    response = {
+            "region": request.region,
+            "staffing_type": f"Staffing agency: {staffing_type_value}",
+            "headcount" : f"Headcount: {headcount}"
+        }
+
+    return response
+
+@app.post("/agent/hr_qa")
+async def general_hr_qa():
+    """
+    This method handles Q/A related to general issues in HR.
+    It forwards the conversation to the OpenAI client via a local proxy and returns the response.
+    """
+    return {
+        "choices": [
+            {
+                "message": {
+                    "role": "assistant",
+                    "content": "I am a helpful HR agent, and I can help you plan for workforce related questions",
+                },
+                "finish_reason": "completed",
+                "index": 0,
+            }
+        ],
+        "model": "hr_agent",
+        "usage": {"completion_tokens": 0},
+    }
+
+if __name__ == "__main__":
+    app.run(debug=True)
diff --git a/demos/hr_agent/requirements.txt b/demos/hr_agent/requirements.txt
new file mode 100644
index 00000000..77e7584c
--- /dev/null
+++ b/demos/hr_agent/requirements.txt
@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+pydantic
+typing
diff --git a/demos/hr_agent/run_demo.sh b/demos/hr_agent/run_demo.sh
new file mode 100644
index 00000000..f6097b09
--- /dev/null
+++ b/demos/hr_agent/run_demo.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+
+# Function to start the demo
+start_demo() {
+  # Step 1: Check if .env file exists
+  if [ -f ".env" ]; then
+    echo ".env file already exists. Skipping creation."
+  else
+    # Step 2: Create `.env` file and set OpenAI key
+    if [ -z "$OPENAI_API_KEY" ]; then
+      echo "Error: OPENAI_API_KEY environment variable is not set for the demo."
+      exit 1
+    fi
+
+    echo "Creating .env file..."
+    echo "OPENAI_API_KEY=$OPENAI_API_KEY" > .env
+    echo ".env file created with OPENAI_API_KEY."
+  fi
+
+  # Step 3: Start Arch
+  echo "Starting Arch with arch_config.yaml..."
+  archgw up arch_config.yaml
+
+  # Step 4: Start Network Agent
+  echo "Starting Network Agent using Docker Compose..."
+  docker compose up -d  # Run in detached mode
+}
+
+# Function to stop the demo
+stop_demo() {
+  # Step 1: Stop Docker Compose services
+  echo "Stopping Network Agent using Docker Compose..."
+  docker compose down
+
+  # Step 2: Stop Arch
+  echo "Stopping Arch..."
+  archgw down
+}
+
+# Main script logic
+if [ "$1" == "down" ]; then
+  stop_demo
+else
+  # Default action is to bring the demo up
+  start_demo
+fi