Agentic AI FactoryGitHub

Start

Get started

Pick one of the four samples for agentic AI on Amazon Bedrock and Amazon Bedrock AgentCore, clone the repository, and take its first steps here. The full quickstart and the teardown live on each project page; every path deploys real AWS resources.

Workshop
About 30 to 45 minutes for the self-paced deploy script (five CloudFormation stacks) source
Self-Service
Roughly 15 to 20 minutes for a first-time deploy source
MCP Gateway
About 5 minutes for the five quickstart steps; the gateway stack itself takes about 2 minutes source
Blueprint
not documented

First ten minutes by project

Each section gives the clone and folder lines, the expected time and the first two steps of one project, then hands over to the project page for the rest. source

1. LearnBuilding an Enterprise Agentic AI Platform

Learn the platform patterns hands-on. Workshop project page.

At an AWS event

Workshop Studio provisions a pre-configured account for you. There is nothing to deploy.

Expected time: No deploy; start the modules as soon as you have the account source

  1. Open the workshop source

    The workshop guide is published on AWS Builder Center (Workshop Studio).

  2. Sign in to the pre-provisioned AWS account source

    All workshop resources are deployed to us-west-2. Log out of other AWS console sessions first.

Self-paced in your own account

One deploy script provisions the same five CloudFormation stacks and browser IDE that events use. Use a dedicated account you can tear down.

Expected time: About 30 to 45 minutes for the self-paced deploy script (five CloudFormation stacks) sourceThe self-paced guide (content/introduction/getting-started/self-service.en.md) notes that the Registry stack alone takes 20 to 30 minutes. At an AWS event the account arrives pre-provisioned, so there is nothing to deploy.

  1. Clone the repository and enter the project folder source
    git clone https://github.com/aws-samples/sample-ai-agent-factory.git
cd sample-ai-agent-factory/workshop-building-agentic-ai-platform

    Folder names are exact and case-sensitive.

  2. Set a validated region source
    aws configure set region us-west-2   # or us-east-1, eu-west-1

    us-west-2 is the default. us-east-1 and eu-west-1 are also validated. Other regions are not supported.

  3. Deploy all five stacks source
    ./scripts/self-service-deploy.sh

    About 30 to 45 minutes. The script runs a preflight check, then prints the IDE URL and password at the end.

2. BuildAgentCore Visual Workflow Platform

Build and ship agents visually. Self-Service project page.

Deploy the platform

One script validates prerequisites, deploys the CDK stack, builds the frontend and prints the URLs.

Expected time: Roughly 15 to 20 minutes for a first-time deploy source

  1. Clone the repository and enter the project folder source
    git clone https://github.com/aws-samples/sample-ai-agent-factory.git
cd sample-ai-agent-factory/Agentic-ai-self-service

    Folder names are exact and case-sensitive.

  2. Deploy with at least one Cognito user source
    # Minimal deploy (dev environment, us-east-1)
COGNITO_USERS="user@example.com" ./scripts/deploy.sh

# Specific environment
COGNITO_USERS="user@example.com" ENVIRONMENT_NAME=prod ./scripts/deploy.sh

# Another region (Frankfurt)
COGNITO_USERS="user@example.com" AWS_REGION=eu-central-1 ./scripts/deploy.sh

    A first-time deploy takes roughly 15 to 20 minutes. Lambda code is packaged by CDK; no Docker build or ECR push is needed.

  3. Assign a persona on first sign-in source
    POOL_ID=$(aws cognito-idp list-user-pools --max-results 40 --region us-east-1 \
  --query "UserPools[?Name=='agentcore-workflow-dev-users'].Id | [0]" --output text)

# Full access (all scopes) + admin UI + registry approver:
for g in g-admins-super t-admin registry-admin; do
  aws cognito-idp admin-add-user-to-group --user-pool-id "$POOL_ID" \
    --username you@example.com --group-name "$g" --region us-east-1
done

    COGNITO_USERS puts each pre-created user in g-users-default + t-user (build, deploy, invoke, browse and clone). Admin personas are a manual grant; a user in no group gets 403 on every call. Always pass the region you deployed to. Sign out and back in after changing groups.

3. GovernEnterprise MCP Governance Gateway

Govern every tool call. MCP Gateway project page.

Deploy and prove the governance

Five steps, about 5 minutes. Prerequisites: Node.js with the CDK CLI at 2.1129.0, Python 3.12+, and AWS credentials for the target account.

Expected time: About 5 minutes for the five quickstart steps; the gateway stack itself takes about 2 minutes source

  1. Clone the repository and enter the project folder source
    git clone https://github.com/aws-samples/sample-ai-agent-factory.git
cd sample-ai-agent-factory/enterprise-mcp-governance-gateway

    Folder names are exact and case-sensitive.

  2. Set the region and install the Python dependencies source
    export AWS_REGION=us-west-2
python3 -m venv .venv && source .venv/bin/activate
pip install -r cdk/requirements.txt -r requirements-dev.txt

    Run from the enterprise-mcp-governance-gateway folder of the cloned repository.

  3. 1. Deploy the gateway source
    cd cdk && cdk bootstrap && cdk deploy EnterpriseMcpGatewayStack --require-approval never && cd ..

    One stack, about 2 minutes.

4. ScaleEnterprise Agentic AI Platform Blueprint

Evaluate the enterprise reference. Blueprint project page.

Prerequisites and deployment sequence

The Blueprint is a multi-account rollout, not a single command. Start with one representative Workstream cell and prove the complete lifecycle before onboarding more.

Expected time: not documentedThe README documents the deployment sequence (sections 6.1 to 6.6: one-time setup, configuration, scoped bootstrap, Platform pipeline, Workstream onboarding, validation) but no duration.

  1. Clone the repository and enter the project folder source
    git clone https://github.com/aws-samples/sample-ai-agent-factory.git
cd sample-ai-agent-factory/enterprise-agentic-ai-platform-blueprint

    Folder names are exact and case-sensitive.

  2. Confirm the prerequisites (README section 5) source

    Node.js 20 or later, Python 3.12 or later, AWS CLI v2 and AWS CDK v2. An AWS Organizations landing zone with Management, Platform and Workstream account roles. A GitHub organization with an AWS CodeConnections connection. Bedrock model access in the target Region. Administrator access for the initial bootstrap only.

    README section 5, Prerequisites

  3. 6.1 One-time setup source
    git clone https://github.com/aws-samples/sample-ai-agent-factory.git
cd sample-ai-agent-factory/enterprise-agentic-ai-platform-blueprint
npm ci
npm run build
npm test
npm run lint
npm run scrub

export AWS_REGION=eu-west-1
export AWS_DEFAULT_REGION="$AWS_REGION"
export CDK_DEFAULT_REGION="$AWS_REGION"

    Set all three Region variables; setting only CDK_DEFAULT_REGION is insufficient.

    README section 6.1, One-time setup

Support and feedback