Skip to content
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion cspell.json
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,7 @@
"AppClientIDWeb",
"AppClientSecret",
"appcompat",
"APPDATA",
"AppDelegate.m",
"AppDelegate.swift",
"AppDelegate",
Expand Down Expand Up @@ -1631,7 +1632,9 @@
"HTTPAPI",
"AWSSDK",
"uppercased",
"autoclosure"
"autoclosure",
"Kiro",
"kiro"
],
"flagWords": ["hte", "full-stack", "Full-stack", "Full-Stack", "sudo"],
"patterns": [
Expand Down
11 changes: 11 additions & 0 deletions src/directory/directory.mjs
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,17 @@ export const directory = {
},
{
path: 'src/pages/[platform]/start/platform-setup/index.mdx'
},
{
path: 'src/pages/[platform]/start/mcp-server/index.mdx',
children: [
{
path: 'src/pages/[platform]/start/mcp-server/set-up-mcp/index.mdx'
},
{
path: 'src/pages/[platform]/start/mcp-server/amplify-workflows/index.mdx'
}
]
}
]
},
Expand Down
1 change: 0 additions & 1 deletion src/pages/[platform]/ai/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@ import { getCustomStaticPath } from '@/utils/getCustomStaticPath';
export const meta = {
title: 'AI kit',
description: 'The quickest way for fullstack developers to build web apps with AI capabilities such as chat, conversational search, and summarization',
isNew: true,
route: '/[platform]/ai',
platforms: [
'angular',
Expand Down
354 changes: 354 additions & 0 deletions src/pages/[platform]/start/mcp-server/amplify-workflows/index.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,354 @@
import { getCustomStaticPath } from '@/utils/getCustomStaticPath';

export const meta = {
title: 'Pre-built Amplify workflows',
description: 'Learn about the pre-built workflows available in AWS MCP Server for building Amplify applications.',
route: '/[platform]/start/mcp-server/amplify-workflows',
platforms: [
'android',
'angular',
'flutter',
'javascript',
'nextjs',
'react',
'react-native',
'swift',
'vue'
]
};

export const getStaticPaths = async () => {
return getCustomStaticPath(meta.platforms);
};

export function getStaticProps(context) {
return {
props: {
platform: context.params.platform,
meta
}
};
}

AWS MCP Server includes pre-built workflows (called "Agent SOPs" in AWS terminology) that guide your AI coding assistant through complex Amplify development tasks. These workflows encode best practices and ensure consistent, production-ready implementations.

This page describes the three main workflows available and shows you how to use them effectively.

## Available workflows

AWS MCP Server provides three pre-built workflows designed for different stages of Amplify development:

| Workflow | Purpose |
| --- | --- |
| **Backend Implementation** | Set up authentication, data models, storage, functions, and AI features |
| **Frontend Integration** | Connect your frontend framework to Amplify backend services |
| **Deployment Guide** | Configure sandbox environments, production deployments, and CI/CD |

## Backend Implementation workflow

The Backend Implementation workflow helps you set up Amplify backend features following best practices. When you ask your AI assistant to implement a backend feature, it uses this workflow to guide the implementation.

### Supported features

<Accordion title="Authentication (Auth)" headingLevel="4">

The workflow guides you through setting up Amplify Auth, including:

- Configuring sign-up and sign-in flows
- Setting up multi-factor authentication (MFA)
- Configuring social sign-in providers (Google, Facebook, Apple, Amazon)
- Customizing authentication UI components
- Implementing password policies and account recovery

**Example prompt:**
```
Set up authentication for my app with email sign-in and Google social login.
```

</Accordion>

<Accordion title="Data modeling (Data)" headingLevel="4">

The workflow helps you design and implement your data layer:

- Creating GraphQL schemas with proper relationships
- Setting up authorization rules for data access
- Configuring real-time subscriptions
- Implementing optimistic UI updates
- Setting up conflict resolution for offline scenarios

**Example prompt:**
```
Create a data model for a blog with posts, comments, and user profiles.
Posts should only be editable by their authors.
```

</Accordion>

<Accordion title="File storage (Storage)" headingLevel="4">

The workflow guides storage implementation:

- Configuring S3 buckets with proper access controls
- Setting up file upload and download functionality
- Implementing access levels (public, protected, private)
- Configuring file validation and size limits

**Example prompt:**
```
Add file storage so users can upload profile pictures with a 5MB limit.
```

</Accordion>

<Accordion title="Serverless functions (Functions)" headingLevel="4">

The workflow helps you create and deploy Lambda functions:

- Setting up function triggers (API, scheduled, event-driven)
- Configuring environment variables and secrets
- Implementing function layers for shared code
- Setting up proper IAM permissions

**Example prompt:**
```
Create a function that sends a welcome email when a new user signs up.
```

</Accordion>

<Accordion title="AI features (AI)" headingLevel="4">

The workflow guides AI/ML feature integration:

- Setting up Amazon Bedrock for generative AI
- Implementing text generation and summarization
- Adding image analysis capabilities
- Configuring conversation flows

**Example prompt:**
```
Add an AI feature that summarizes long articles for users.
```

</Accordion>

## Frontend Integration workflow

The Frontend Integration workflow helps you connect your frontend application to Amplify backend services. It provides framework-specific patterns and best practices.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think that this is maybe missing that the frontend SOP can be applied to already existing frontend applications. I know that this is implied with this sentence, but maybe we should make it a bit more obvious.


### Framework patterns

The workflow adapts its guidance based on your frontend framework:

<Accordion title="React and Next.js" headingLevel="4">

- Setting up the Amplify client library
- Using React hooks for authentication state
- Implementing data fetching with proper loading states
- Configuring server-side rendering (SSR) for Next.js
- Using Amplify UI components

**Example prompt:**
```
Connect my React app to the Amplify backend and add a sign-in page.
```

</Accordion>

<Accordion title="Vue and Angular" headingLevel="4">

- Configuring Amplify with framework-specific patterns
- Implementing authentication guards and state management
- Setting up data binding with Amplify Data
- Using framework-appropriate UI components

**Example prompt:**
```
Set up Amplify in my Vue app and create a protected dashboard route.
```

</Accordion>

<Accordion title="React Native" headingLevel="4">

- Configuring Amplify for mobile development
- Implementing secure storage for tokens
- Setting up push notifications
- Handling offline scenarios with DataStore

**Example prompt:**
```
Add offline support to my React Native app so users can work without internet.
```

</Accordion>

<Accordion title="Flutter" headingLevel="4">

- Setting up Amplify Flutter packages
- Implementing authentication flows
- Configuring API and storage access
- Using Amplify UI components for Flutter

**Example prompt:**
```
Set up authentication in my Flutter app with the Amplify Authenticator widget.
```

</Accordion>

<Accordion title="Swift (iOS)" headingLevel="4">

- Configuring Amplify Swift packages
- Implementing async/await patterns for Amplify operations
- Setting up Combine publishers for real-time updates
- Using SwiftUI with Amplify

**Example prompt:**
```
Add real-time data sync to my SwiftUI app using Amplify DataStore.
```

</Accordion>

<Accordion title="Android (Kotlin)" headingLevel="4">

- Setting up Amplify Android libraries
- Implementing coroutines for async operations
- Configuring Jetpack Compose with Amplify
- Handling Android lifecycle with Amplify

**Example prompt:**
```
Connect my Kotlin Android app to Amplify and implement user authentication.
```

</Accordion>

## Deployment Guide workflow

The Deployment Guide workflow helps you deploy your Amplify application through different stages, from local development to production.

### Sandbox environments

The workflow guides you through setting up personal cloud sandbox environments for development:

- Creating isolated sandbox environments
- Configuring hot-reload for backend changes
- Managing sandbox lifecycle
- Sharing sandbox configurations with team members

**Example prompt:**
```
Set up a sandbox environment so I can test my backend changes.
```

### Production deployment

The workflow helps you deploy to production:

- Configuring production-ready settings
- Setting up custom domains
- Implementing environment variables for different stages
- Configuring monitoring and logging

**Example prompt:**
```
Deploy my app to production with a custom domain.
```

### CI/CD integration

The workflow guides continuous integration and deployment setup:

- Configuring Amplify Hosting for automatic deployments
- Setting up branch-based deployments (preview, staging, production)
- Implementing pull request previews
- Configuring build settings and environment variables

**Example prompt:**
```
Set up CI/CD so my app automatically deploys when I push to the main branch.
```

## Practical example: Building a fullstack app

Here's an example of how you might use AWS MCP Server to build a complete Amplify application. This demonstrates how the pre-built workflows guide your AI assistant through each step.

### Step 1: Set up the backend

Start by describing your application to your AI assistant:

```
I want to build a task management app. Users should be able to:
- Sign up and sign in with email
- Create, edit, and delete their own tasks
- Mark tasks as complete
- See their tasks in real-time across devices
```

Your AI assistant uses the **Backend Implementation workflow** to:
1. Configure authentication with email sign-in
2. Create a Task data model with proper authorization rules
3. Set up real-time subscriptions for task updates

### Step 2: Connect the frontend

Next, ask your assistant to connect your frontend:

```
Connect my React app to the backend. I want a sign-in page and a
dashboard that shows the user's tasks.
```

Your AI assistant uses the **Frontend Integration workflow** to:
1. Install and configure Amplify libraries
2. Set up the Authenticator component
3. Create data fetching hooks for tasks
4. Implement real-time updates in the UI

### Step 3: Deploy the application

Finally, deploy your application:

```
Set up deployment so the app deploys automatically when I push to GitHub.
Configure preview deployments for pull requests.
```

Your AI assistant uses the **Deployment Guide workflow** to:
1. Connect your GitHub repository to Amplify Hosting
2. Configure branch-based deployments
3. Set up pull request previews
4. Configure production environment settings

## Tips for effective prompts

To get the best results from AWS MCP Server, keep these tips in mind:

<Callout info>

**Be specific about your requirements.** Instead of "add authentication," try "add authentication with email sign-in, Google social login, and MFA."

</Callout>

- **Describe the user experience** you want, not just the technical implementation
- **Mention your framework** so the workflow can provide framework-specific guidance
- **Ask follow-up questions** if you need clarification on any step
- **Request explanations** if you want to understand why certain patterns are recommended

## Next steps

Now that you understand the pre-built workflows, try using them in your next Amplify project:

1. [Set up AWS MCP Server](/[platform]/start/mcp-server/set-up-mcp/) if you haven't already
2. Start a conversation with your AI assistant about what you want to build
3. Let the pre-built workflows guide you through implementation

For more information about specific Amplify features, explore the documentation:

- [Authentication](/[platform]/build-a-backend/auth/)
- [Data](/[platform]/build-a-backend/data/)
- [Storage](/[platform]/build-a-backend/storage/)
- [Functions](/[platform]/build-a-backend/functions/)
Loading
Loading