Skip to main content
Before deploying the demo, ensure you have the following tools installed and configured.

​
Required tools

​
AWS CLI v2 or later

The AWS Command Line Interface is required to interact with AWS services.
1

Install AWS CLI

Download and install from aws.amazon.com/cliOr use a package manager:
brew install awscli
2

Verify installation

Check that AWS CLI is properly installed:
aws --version
Expected output:
aws-cli/2.x.x Python/3.x.x ...
3

Configure credentials

Set up your AWS credentials:
aws configure
You’ll be prompted to enter:
  • AWS Access Key ID
  • AWS Secret Access Key
  • Default region (e.g., us-west-2)
  • Default output format (use json)
4

Test authentication

Verify that your credentials work:
aws sts get-caller-identity
You should see your AWS account information in JSON format.

​
AWS SAM CLI v1.130 or later

The AWS Serverless Application Model CLI is used to build and deploy the Lambda functions.
1

Install SAM CLI

brew install aws-sam-cli
SAM CLI requires Docker to be installed for local testing, but Docker is not required for deployment.
2

Verify installation

sam --version
Expected output:
SAM CLI, version 1.130.0

​
Python 3.11 or later

Python is required for the Lambda runtime and local development.
1

Check Python version

python3 --version
Expected output:
Python 3.11.x or higher
2

Install Python (if needed)

brew install [email protected]

​
AWS account requirements

You need an AWS account with permissions to create and manage the following resources:
  • AWS Lambda functions
  • API Gateway REST APIs
  • AWS Verified Permissions policy stores
  • IAM roles and policies

​
Required AWS permissions

Your IAM user or role needs permissions for:
  • lambda:* - Create and manage Lambda functions
  • apigateway:* - Create and manage API Gateway
  • verifiedpermissions:* - Create policy stores and schemas
  • iam:CreateRole - Create execution roles for Lambda
  • iam:AttachRolePolicy - Attach policies to Lambda roles
  • cloudformation:* - SAM uses CloudFormation for deployment
The AdministratorAccess managed policy includes all required permissions, but you should use more restrictive permissions in production environments.

​
Optional: Anthropic API key

The AI agent feature requires an Anthropic API key. This is optional - you can skip it and still use the main AVP demo.
1

Create Anthropic account

Sign up at console.anthropic.com
2

Add credits

Add at least 5increditstoyouraccount.ThedemousesClaudeHaiku,whichcostsapproximately5 in credits to your account. The demo uses Claude Haiku, which costs approximately 0.25 per million tokens.
3

Generate API key

Navigate to API Keys section and create a new key. It will start with sk-ant-.
Keep this key secure. Never commit it to version control or expose it in frontend code.
If you don’t want to use the AI agent, you can enter placeholder as the Anthropic API key during deployment. The main demo (index.html) will work perfectly without it.

​
Verification checklist

Before proceeding to the quickstart, verify you have:
  • AWS CLI v2+ installed and configured
  • SAM CLI v1.130+ installed
  • Python 3.11+ installed
  • AWS credentials configured and tested
  • (Optional) Anthropic API key with credits
Run this combined verification command: 
aws --version && sam --version && python3 --version && aws sts get-caller-identity
If all commands succeed, you’re ready to proceed!

Next: Deploy the demo

Follow the step-by-step quickstart guide to create your Policy Store and deploy with SAM

Build docs developers (and LLMs) love

Get started for freeTalk to us