Build AI agents and automate UI workflows from your web browser - Amazon Nova Act and Kiro
Source: Dev.to
Lesson Objectives
In this lesson you will learn how to:
- Build an AI agent from UI‑automated workflows.
- Identify use cases for Amazon Nova Act.
Amazon Nova Family
AWS introduces a family of AI offerings under Amazon Nova, which includes:
a) Amazon Nova 2 Foundation Models
| Model | Description | Data Types |
|---|---|---|
| Nova 2 Lite | Cost‑effective foundation model for reasoning tasks such as building chatbots. | Text, video, image |
| Nova 2 Pro (preview) | Intelligent reasoning model for AI tasks such as agentic coding. | Text, video, image, speech |
| Nova 2 Omni (preview) | Multimodal foundation model capable of … (description to be added) | |
| Nova 2 Sonic | Speech‑to‑speech model for conversational AI. | Text, speech |
| Nova Multimodal Embeddings | Multimodal embedding model for agentic RAG and semantic search. | Text, image, audio, video |
b) Frontier Model
- Amazon Nova Forge – Allows you to combine your organization’s data with curated training data from Amazon Nova.
c) Automate Web‑Browser Workflows at Scale
Amazon Nova Act
Amazon Nova Act is an AWS service built on the architecture of Nova 2 Lite to create AI agents that automate web‑browser UI workflows. It enables you to:
- Build and manage AI agents for massive‑scale UI automation of repetitive tasks.
- Deploy agents quickly using natural‑language prompts and Python code.
Key Features
- Extract information from web pages.
- Confirm bookings and other transactions.
- Fill out forms automatically.
- Perform web searches and navigate results.
Benefits
- Completes repetitive tasks, launches APIs, and handles escalations.
- Takes a prototype to production in a matter of hours.
- Deploys and manages fleets of agents at scale.
Typical Use Cases
| Use Case | Description |
|---|---|
| Data entry | Populate details without manual copy‑and‑paste. |
| Web QA testing | Validate user‑journey workflows directly in the browser (no separate test scripts). |
| Checkout flows | Automate purchases, refunds, validations, and UI changes. |
| Data extraction | Navigate sites and pull data from unstructured sources that are hard to export. |
Getting Started with Amazon Nova Act
Prerequisites
- Kiro – the agentic IDE.
- AWS Builders ID (or IAM credentials).
Step‑by‑Step Guide
| Step | Action |
|---|---|
| 1 | Launch Kiro from your desktop and sign in with your AWS Builders ID. Allow Kiro to access your data when prompted. |
| 2 | In Kiro, go to Extensions → Search for Amazon Nova Act and install it. Choose Trust publisher and confirm the installation. |
| 3 | Open the Amazon Nova Act Playground ( ) to experiment with user journeys and generate an API key. (Note: the playground may be unavailable from some regions, e.g., Sydney (ap‑southeast‑2)). |
| 4 | Install the Nova Act Python SDK in the Kiro terminal: bash\npip install --upgrade nova-act\n |
| 5 | Create a project folder named UTS enrolment folder (e.g., under Documents). |
| 6 | In Kiro IDE: File → Open Folder → UTS enrolment folder. |
| 7 | Switch to Vibe coding mode and enter the following prompt to generate a prototype: “Create a prototype for a UTS psychology enrollment workflow that automates the web UI for data entry, form filling, and confirmation.” |
| 8 | Kiro will generate the files, including an uts-psychology-enrollment-workflow.html and a README.md. Review them and share with your team. |
| 9 | Use Kiro to create Steering files and SPECS. The staged process will produce: • Requirements • Design document • Acceptance criteria • Implementation plan These artifacts are stored in a hidden .kiro subfolder. |
| 10 | Open Visual Studio Code (VS Code) and open the same project folder. |
| 11 | In the VS Code chat (Amazon Q), paste the deployment prompt to generate the deployment script (see below). |
| 12 | Run the generated script to deploy the workflow to AWS (requires configured AWS CLI credentials). |
Deployment Script (PowerShell)
# UTS Psychology Enrollment - AWS Deployment Script
param(
[string]$BucketName = "uts-psychology-enrollment",
[string]$Region = "us-east-1"
)
Write-Host "=== UTS Psychology Enrollment - AWS S3 Deployment ===" -ForegroundColor Cyan
Write-Host ""
# Verify AWS CLI configuration
Write-Host "Checking AWS CLI configuration..." -ForegroundColor Yellow
aws sts get-caller-identity 2>$null
if ($LASTEXITCODE -ne 0) {
Write-Host "ERROR: AWS CLI not configured. Run: aws configure" -ForegroundColor Red
exit 1
}
Write-Host "✓ AWS CLI configured" -ForegroundColor Green
# Create (or confirm) the S3 bucket
Write-Host ""
Write-Host "Creating S3 bucket: $BucketName..." -ForegroundColor Yellow
aws s3 ls "s3://$BucketName" 2>$null
if ($LASTEXITCODE -eq 0) {
Write-Host "✓ Bucket already exists" -ForegroundColor Green
} else {
aws s3 mb "s3://$BucketName" --region $Region
if ($LASTEXITCODE -eq 0) {
Write-Host "✓ Bucket created successfully" -ForegroundColor Green
} else {
Write-Host "ERROR: Failed to create bucket" -ForegroundColor Red
exit 1
}
}
# Sync local project files to the bucket
Write-Host ""
Write-Host "Syncing project files to S3..." -ForegroundColor Yellow
aws s3 sync . "s3://$BucketName" --exclude ".git/*" --exclude ".kiro/*"
if ($LASTEXITCODE -eq 0) {
Write-Host "✓ Sync completed" -ForegroundColor Green
} else {
Write-Host "ERROR: Sync failed" -ForegroundColor Red
exit 1
}
Write-Host ""
Write-Host "Deployment finished!" -ForegroundColor Cyan
Next Steps
- Test the deployed workflow by invoking the generated Nova Act agent from a browser session.
- Monitor agent performance via the Amazon Nova Act console and iterate on prompts or specifications as needed.
PowerShell Deployment Script
# Create the S3 bucket (if it doesn't already exist)
aws s3 mb "s3://$BucketName" --region $Region 2>&1 | Out-Null
if ($LASTEXITCODE -eq 0) {
Write-Host "✓ Bucket created" -ForegroundColor Green
} else {
Write-Host "ERROR: Failed to create bucket" -ForegroundColor Red
exit 1
}
# Enable website hosting
Write-Host ""
Write-Host "Enabling static website hosting..." -ForegroundColor Yellow
aws s3 website "s3://$BucketName" --index-document uts-psychology-enrollment-workflow.html
Write-Host "✓ Website hosting enabled" -ForegroundColor Green
# Set up public access
Write-Host ""
Write-Host "Configuring public access..." -ForegroundColor Yellow
$policy = @"
{
"Version": "2012-10-17",
"Statement": [{
"Sid": "PublicReadGetObject",
"Effect": "Allow",
"Principal": "*",
"Action": "s3:GetObject",
"Resource": "arn:aws:s3:::$BucketName/*"
}]
}
"@
$policy | Out-File -FilePath "bucket-policy.json" -Encoding utf8
aws s3api put-public-access-block `
--bucket $BucketName `
--public-access-block-configuration "BlockPublicAcls=false,IgnorePublicAcls=false,BlockPublicPolicy=false,RestrictPublicBuckets=false" `
2>&1 | Out-Null
aws s3api put-bucket-policy `
--bucket $BucketName `
--policy file://bucket-policy.json `
2>&1 | Out-Null
Write-Host "✓ Public access configured" -ForegroundColor Green
# Upload the HTML file
Write-Host ""
Write-Host "Uploading HTML file..." -ForegroundColor Yellow
aws s3 cp uts-psychology-enrollment-workflow.html "s3://$BucketName/" --content-type "text/html"
if ($LASTEXITCODE -eq 0) {
Write-Host "✓ File uploaded successfully" -ForegroundColor Green
} else {
Write-Host "ERROR: Upload failed" -ForegroundColor Red
exit 1
}
# Clean up temporary files
Remove-Item "bucket-policy.json" -ErrorAction SilentlyContinue
# Show results
Write-Host ""
Write-Host "=== Deployment Complete ===" -ForegroundColor Green
Write-Host ""
Write-Host "Website URL:" -ForegroundColor Cyan
Write-Host " http://$BucketName.s3-website-$Region.amazonaws.com" -ForegroundColor White
Write-Host ""
Note: A
deployment.mdfile was created as part of this process.
Additional Resources
- Amazon Nova Act CLI – You can also deploy this workflow using the Amazon Nova Act command‑line interface.
- Amazon Nova Act CDK Templates – Production‑grade deployments can be built with Nova Act CDK templates.
Documentation & Guides
- Amazon Nova Act User Guide
- Amazon Nova Act API Reference
- Introducing Amazon Nova Act
- Amazon Nova Act with SDK
- Set Python Interpreter (for SDK usage)
- Amazon Nova Act Extension
Until the next update, happy learning! 😀