How to Build a Real-Time AI Assistant for Your DigitalOcean Account

Want an AI helper that knows your DigitalOcean infrastructure inside and out? Learn how to build your own AI agent that uses live data to answer your questions, manage your servers, and more.

Why Build an AI Agent for Your Cloud Infrastructure?

In today's fast-paced tech world, using real-time data is vital for AI-powered tools. Industries like finance, healthcare, and e-commerce need immediate insights to make smart decisions and improve customer experiences. By integrating AI with live APIs, you create systems that react instantly to change, offering benefits such as:

• Instant Information: Access up-to-the-minute data about your resources.
• Hands-Free Automation: Automate routine tasks.
• Scalable Solutions: Manage numerous requests at once.
• Better User Experiences: Get fast, smart answers to your questions.

Who Should Build an AI Agent?

AI agents integrated with real-time data are incredibly versatile, benefiting several key roles:

• Developers: Get quick insights into your cloud setup, making resource management much easier.
• Support Teams: Automate answers to common questions, leading to faster and better customer service.
• System Administrators: Keep a real-time watch on your DigitalOcean resources for valuable updates and alerts.

What You'll Need to Build Your Own AI Helper

Before you dive in, here's what you need to get started creating AI agents connected to live data:

1. DigitalOcean GenAI Platform: Set up an account. This is DigitalOcean’s tool for building production-ready AI agents.
2. DigitalOcean Functions: You will need DigitalOcean Functions, a serverless environment for running code (Python, Node.js, PHP, Go).

Step-by-Step: Crafting Your Real-Time AI Agent

Here's a breakdown of how to build an AI agent that can answer questions about your DigitalOcean account using real-time data.

Step 1: Create the Serverless Function to Retrieve Data

First, you'll create a serverless function that the AI agent will call to get live data from the DigitalOcean API:

1. Create a Namespace: In the DigitalOcean control panel, go to Functions and click "Create Namespace."

2. Choose a Location: Pick a data center location (e.g., Toronto).

3. Connect with doctl: Use the doctl command line tool to connect to your namespace:

   doctl serverless connect
   

   Copy

4. Initialize a Python Project: Start a sample Python project:

   doctl serverless init --language python example-project
   

   Copy

Step 2: Configure Your Serverless Function for the DigitalOcean API

Now, let's configure the Function to grab data about your DigitalOcean resources:

1. Modify the Project File: Adjust the runtime settings and add security headers.

2. Set Up Environment Variables: Create an environment file for your DigitalOcean API token. This keeps your credentials secure.

3. Add API Function Code: Replace the sample code with your Python function to pull droplet information.

4. Build Script: Create a script to import any Python dependencies.

5. Deploy: Launch the function with:

   doctl serverless deploy
   

   Copy

After deployment, you can test your function through the web interface to ensure it returns the expected information about your droplets.

Check out this repository for a complete code example.

Step 3: Bring Your AI Agent to Life

Ready to create the agent? You can use the web interface or the API:

Option 1: Build Your AI Agent Using the Web UI

This simple method is perfect if you prefer a visual approach:

1. Create Agent: In the GenAI platform, click "Create Agent."

2. Name Your Agent: Give your agent a relevant name (e.g., "Droplet Agent").

3. Set Instructions: Define its purpose using a system prompt:

   You are a helpful assistant that provides information about DigitalOcean customer accounts. Your role is to help users understand their account details, team information, resource usage, and account status.

4. Pick a Model: Choose a language model (e.g., Llama 3.3 Instruct-70B).

5. Create! Finalize the agent.

Option 2: Build Your AI Agent Programmatically through the API

For those who prefer to code, the API offers greater flexibility:

curl -X POST \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $API_TOKEN" \
 "https://api.digitalocean.com/v2/gen-ai/agents" \
 -d '{
 "name": "Droplet Agent",
 "model_uuid": "d754f2d7-d1f0-11ef-bf8f-4e013e2ddde4",
 "instruction": "You are a helpful assistant that provides information about DigitalOcean customer accounts. Your role is to help users understand their account details, team information, resource usage, and account status.",
 "description": "AI agent for retrieving and explaining DigitalOcean account information",
 "project_id": "YOUR_PROJECT_ID",
 "tags": ["droplet-info"],
 "region": "tor1"
 }'

Required Parameters:

• name: A descriptive name for your agent
• model_uuid: The UUID of the language model to use
• instruction: System prompt that defines the agent’s purpose and behavior
• region: The datacenter region where the agent will be deployed

Optional Parameters:

• description: A brief description of the agent’s purpose
• project_id: The project to associate the agent with
• tags: Array of tags for organizing your agents

Replace $API_TOKEN with your API token and YOUR_PROJECT_ID with your project’s ID.

Step 4: Connecting Your Function to the Agent

Now, link your function to your AI agent so it can fetch live data:

Option 1: Connecting Your Function via the Web UI

This is another easy method for less technical users.

1. Navigate to the Resources tab in the agent playground

2. Add a function route

3. Select your namespace and function

4. Provide function instructions to guide when the agent should call the function

   Call this function when the user asks about their DigitalOcean droplets, virtual machines, instances, or servers. Use this function to retrieve information about one or more droplets in a DigitalOcean account.

5. Define input and output schemas to help the language model understand how to use the function

Option 2: Connecting Your Function through the API

Connect your function programmatically using the DigitalOcean API:

curl -X POST \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_TOKEN" \
"https://api.digitalocean.com/v2/gen-ai/agents/1b418231-b7d6-11ef-bf8f-4e013e2ddde4/functions" \
-d '{
 "agent_uuid": "1b418231-b7d6-11ef-bf8f-4e013e2ddde4",
 "function_name": "droplet",
 "description": "Call this function when the user asks about their DigitalOcean droplets, virtual machines, instances, or servers. Use this function to retrieve information about one or more droplets in a DigitalOcean account.",
 "input_schema": {
 "droplet_id": {
 "required": false,
 "description": "Specific droplet ID to retrieve information for. If not provided, returns a list of droplets",
 "type": "string"
 },
 "tag": {
 "description": "Filter droplets by tag",
 "type": "string",
 "required": false
 },
 "limit": {
 "type": "number",
 "required": false,
 "description": "Maximum number of droplets to return (default: 10)"
 }
 },
 "output_schema": {
 "droplets": {
 "type": "string",
 "description": "JSON string containing list of droplet information"
 },
 "count": {
 "type": "number",
 "description": "Total number of droplets returned"
 },
 "error": {
 "type": "string",
 "required": false,
 "description": "Error message if the request failed"
 },
 "status": {
 "type": "string",
 "description": "Status of the API request (success or error)"
 }
 }'

Required Parameters:

• agent_uuid: The UUID of your agent
• function_name: A name for the function route
• input_schema: JSON schema defining the function's input parameters
• output_schema: JSON schema defining the function's return values
• faas_namespace: Your Functions namespace ID
• faas_name: The path to your function (namespace/function-name)

Optional Parameters:

• description: Instructions for when the agent should use this function

Sample input and output schemas for your DigitalOcean AI Agent:

• Input Schema: Specifies what the agent can send to your function (like droplet ID).

{
 "droplet_id": {
  "required": false,
  "description": "Specific droplet ID to retrieve information for. If not provided, returns a list of droplets",
  "type": "string"
 },
 "tag": {
  "description": "Filter droplets by tag",
  "type": "string",
  "required": false
 },
 "limit": {
  "type": "number",
  "required": false,
  "description": "Maximum number of droplets to return (default: 10)"
 }
}

• Output Schema: Helps the agent understand the data it receives.

{
 "droplets": {
  "type": "string",
  "description": "JSON string containing list of droplet information"
 },
 "count": {
  "type": "number",
  "description": "Total number of droplets returned"
 },
 "error": {
  "type": "string",
  "required": false,
  "description": "Error message if the request failed"
 },
 "status": {
  "type": "string",
  "description": "Status of the API request (success or error)"
 }
}

Step 5: Time to Test! Put Your AI Agent to Work

Time to see your creation in action! Ask your agent questions such as:

• "What droplets do I have in my account?"
• "Tell me more about droplet [ID]"

The agent will call your function, access the DigitalOcean API for real-time information, and provide a smart answer.

Troubleshooting Common Issues

Here are a few common issues you might see:

• Incorrect API Responses: Double-check your DigitalOcean API token and permissions.
• Function Errors: Use doctl serverless logs to debug function runtime issues.
• Agent Doesn't Respond: Make sure the function is properly connected and that your schemas are accurate.