Streaming Agents on Confluent Cloud Quickstart

Build real-time AI agents with Confluent Cloud Streaming Agents. This quickstart includes two hands-on labs:

Lab	Description	Requirements
Lab1 - MCP Tool Calling	Price matching agent that scrapes competitor websites and adjusts prices in real-time	Zapier MCP server
Lab2 - Vector Search - RAG	Vector search pipeline with optional retrieval augmented generation (RAG) for intelligent document retrieval	MongoDB Atlas (free M0 tier)

Demo Video

🚀 Quick Start

One command deployment:

uv run deploy

That's it! The script will guide you through setup, automatically create API keys, and deploy your chosen lab(s).

Prerequisites

Required accounts & credentials:

• 
• Lab1: Zapier account + SSE endpoint URL → Setup guide
• Lab2: MongoDB Atlas + connection string, database-specific user credentials → Setup guide

Required tools:

• uv - brew install uv (Mac) or winget install astral-sh.uv (Windows)
• Docker - for data generation
• Terraform - infrastructure deployment
• Confluent CLI - cloud resource management
• AWS CLI or Azure CLI - choose your cloud provider
  • *⚠️ AWS users:* Enable Claude Sonnet 3.7 in Bedrock in your specific region before deploying.

📦 Platform-specific installation commands

Mac:

brew install uv git && brew tap hashicorp/tap && brew install hashicorp/tap/terraform && brew install --cask confluent-cli docker-desktop  && brew install awscli  # or azure-cli

Windows:

winget install astral-sh.uv Git.Git Docker.DockerDesktop Hashicorp.Terraform ConfluentInc.Confluent-CLI Amazon.AWSCLI  # or Microsoft.AzureCLI

Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh
# Install other tools via your package manager

Directory Structure

quickstart-streaming-agents/
├── aws|azure/               # Choose a cloud
│   ├── core/                # Shared infrastructure
│   ├── lab1-tool-calling/  
│   └── lab2-vector-search/ 
├── deploy.py                # 🚀 Start here
└── scripts/                 # Python utilities

🔄 Alternative deployment methods

Traditional Python:

pip install -r requirements.txt
python deploy.py

🔧 Manual terraform deployment

Prerequisites

• All tools installed and authenticated
• Confluent Cloud account with API keys

Deploy

cd aws/  # or azure/
cd core/
terraform init && terraform apply --auto-approve
cd ../lab1-tool-calling/  # or lab2-vector-search
terraform init && terraform apply --auto-approve

Required terraform.tfvars

prefix = "streaming-agents"
cloud_provider = "aws"  # or "azure"
cloud_region = "your-region"
confluent_cloud_api_key = "your-key"
confluent_cloud_api_secret = "your-secret"
ZAPIER_SSE_ENDPOINT = "https://mcp.zapier.com/api/mcp/s/your-key/sse"  # Lab1
MONGODB_CONNECTION_STRING = "mongodb+srv://cluster0.abc.mongodb.net"  # Lab2
mongodb_username = "your-db-user"  # Lab2
mongodb_password = "your-db-pass"  # Lab2  # pragma: allowlist secret

Cleanup

# Automated
uv run deploy  # Choose cleanup option

# Manual
cd aws/lab1-tool-calling && terraform destroy --auto-approve
cd ../core && terraform destroy --auto-approve