Streaming Agents on Confluent Cloud Quickstart

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

Lab	Description
Lab1 - Price Matching Orders With MCP Tool Calling	*NEW!* Now using new Agent Definition (CREATE AGENT) syntax. Price matching agent that scrapes competitor websites and adjusts prices in real-time
Lab2 - Vector Search & RAG	Vector search pipeline template with retrieval augmented generation (RAG). Use the included Flink documentation chunks, or bring your own documents for intelligent document retrieval.
Lab3 - Agentic Fleet Management Using Confluent Intelligence	End-to-end boat fleet management demo showing use of Agent Definition, MCP tool calling, vector search, and anomaly detection.

Prerequisites

Required accounts & credentials:

• 
• Lab1: Zapier remote MCP server (Setup guide)
• Lab2: MongoDB Atlas vector database (Setup guide)
• Lab3: Zapier (Setup guide) + MongoDB (Setup guide)

Required tools:

• AWS CLI or Azure CLI - must be logged in
• Confluent CLI - must be logged in
• Docker - for Lab1 & Lab3 data generation only
• Git
• Terraform
• uv

Installation commands (Mac/Windows/Linux)

**Mac:**

brew install uv git python && 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 Python.Python Amazon.AWSCLI # or Microsoft.AzureCLI

Linux:

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

🚀 Quick Start

Clone the repository and navigate to the Quickstart directory:

git clone https://github.com/confluentinc/quickstart-streaming-agents.git
cd quickstart-streaming-agents

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).

Note

For instructor-led workshops, add the --workshop flag: uv run deploy --workshop.

Directory Structure

quickstart-streaming-agents/
├── aws|azure/                          # Choose a cloud
│   ├── core/                           # Shared Confluent Cloud infra for all labs
│   ├── lab1-tool-calling/              # Lab-specific infra
│   ├── lab2-vector-search/             # Lab-specific infra
│   └── lab3-agentic-fleet-management/  # Lab-specific infra
├── deploy.py                           # 🚀 Start here
└── scripts/                            # Python utilities

🔄 Alternative deployment methods

Traditional Python:

pip install -e . && python deploy.py

🔧 Manual terraform deployment

Prerequisites

• All tools installed and authenticated
• Confluent Cloud API keys (Cloud Resource Management keys with EnvironmentAdmin role)

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

cloud_provider = "aws"  # or "azure"
cloud_region = "your-region"  # must be a region supported by MongoDB free tier, otherwise Lab2 deployment will not succeed
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 & Lab3
mongodb_connection_string = "mongodb+srv://cluster0.abc.mongodb.net"  # Lab2 & Lab3
mongodb_username = "your-db-user"  # Lab2 & Lab3
mongodb_password = "your-db-pass"  # Lab2 & Lab3

Tear down

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

Cleanup

# Automated
uv run destroy

Sign up for early access to Flink AI features

For early access to exciting new Flink AI features, fill out this form and we'll add you to our early access previews.