This is sample code, for non-production usage. You should work with your security and legal teams to meet your organizational security, regulatory and compliance requirements before deployment.

AI-DLC Lite is a lightweight version of the AI-DLC intelligent software development workflow that prioritizes speed over technical depth. It follows the same three-phase lifecycle and preserves core quality guardrails like approval gates, audit logging, and state tracking, but reduces the number of questions, follow-up rounds, and review cycles so you get to working code faster.

For the full AI-DLC methodology, read the blog post and the Method Definition Paper.

AI-DLC Lite takes the same structured workflow as the full version and optimizes it for speed:

What is preserved: Approval gates (one per stage), audit logging, state tracking, code location rules, brownfield file modification rules, artifact quality standards, and the three-phase lifecycle structure.

For a detailed breakdown of every change, see aidlc-rules/aws-aidlc-lite-rule-details/LITE-CHANGES.md.

• Quick Start
• Platform-Specific Setup
• Usage
• Three-Phase Adaptive Workflow
• Key Features
• Extensions
• When to Use Lite vs. Full AI-DLC
• Prerequisites
• Troubleshooting
• Version Control Recommendations
• Additional Resources
• Security
• License

Clone this repo:

git clone <this-repo>

Create a new project folder with a name of your choosing if you're working on a greenfield application:

mkdir <my-project>

Assuming your project is located under the same parent folder as the cloned repo, change directory to your project folder:

cd <my-project>

Then follow the platform-specific setup instructions below to copy the AI-DLC Lite rules into your project.

• Kiro
• Amazon Q Developer IDE Plugin
• Cursor IDE
• Cline
• Claude Code
• GitHub Copilot
• Other Agents

AI-DLC Lite uses Kiro Steering Files within your project workspace.

The commands below assume your project is located under the same parent folder as the cloned repo.

On macOS/Linux:

mkdir -p .kiro/steering
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules .kiro/steering/
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details .kiro/

On Windows (PowerShell):

New-Item -ItemType Directory -Force -Path ".kiro\steering"
Copy-Item -Recurse "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules" ".kiro\steering\"
Copy-Item -Recurse "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".kiro\"

On Windows (CMD):

mkdir .kiro\steering
xcopy ..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules .kiro\steering\aws-aidlc-lite-rules\ /E /I
xcopy ..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details .kiro\aws-aidlc-lite-rule-details\ /E /I

Your project should look like:

<project-root>/
    ├── .kiro/
    │     ├── steering/
    │     │      ├── aws-aidlc-lite-rules/
    │     ├── aws-aidlc-lite-rule-details/

To verify the rules are loaded:

Open the steering files panel and confirm you see an entry for lite-core-workflow under Workspace as shown in the screenshot below.

We use Kiro IDE in Vibe mode to run the AI-DLC Lite workflow. This ensures that the AI-DLC Lite workflow guides the development workflow in Kiro. At times, Kiro may nudge you to switch to spec mode. Select No to such prompts to stay in Vibe mode.

Run kiro-cli, then /context show, and confirm entries for .kiro/steering/aws-aidlc-lite-rules.

AI-DLC Lite uses Amazon Q Rules within your project workspace.

The commands below assume your project is located under the same parent folder as the cloned repo.

On macOS/Linux:

mkdir -p .amazonq/rules
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules .amazonq/rules/
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details .amazonq/

On Windows (PowerShell):

New-Item -ItemType Directory -Force -Path ".amazonq\rules"
Copy-Item -Recurse "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules" ".amazonq\rules\"
Copy-Item -Recurse "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".amazonq\"

On Windows (CMD):

mkdir .amazonq\rules
xcopy ..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules .amazonq\rules\aws-aidlc-lite-rules\ /E /I
xcopy ..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details .amazonq\aws-aidlc-lite-rule-details\ /E /I

Your project should look like:

<project-root>/
    ├── .amazonq/
    │     ├── rules/
    │     │     ├── aws-aidlc-lite-rules/
    │     ├── aws-aidlc-lite-rule-details/

To verify the rules are loaded:

1. In the Amazon Q Chat window, click the Rules button in the lower right corner.
2. Confirm you see entries for .amazonq/rules/aws-aidlc-lite-rules.

AI-DLC Lite uses Cursor Rules to implement its intelligent workflow.

The commands below assume your project is located under the same parent folder as the cloned repo.

Unix/Linux/macOS:

mkdir -p .cursor/rules

cat > .cursor/rules/ai-dlc-lite-workflow.mdc << 'EOF'
---
description: "AI-DLC Lite (AI-Driven Development Life Cycle — Lightweight Edition) adaptive workflow for software development"
alwaysApply: true
---

EOF
cat ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules/lite-core-workflow.md >> .cursor/rules/ai-dlc-lite-workflow.mdc

mkdir -p .aidlc-lite-rule-details
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details/* .aidlc-lite-rule-details/

Windows PowerShell:

New-Item -ItemType Directory -Force -Path ".cursor\rules"

$frontmatter = @"
---
description: "AI-DLC Lite (AI-Driven Development Life Cycle — Lightweight Edition) adaptive workflow for software development"
alwaysApply: true
---

"@
$frontmatter | Out-File -FilePath ".cursor\rules\ai-dlc-lite-workflow.mdc" -Encoding utf8

Get-Content "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" | Add-Content ".cursor\rules\ai-dlc-lite-workflow.mdc"

New-Item -ItemType Directory -Force -Path ".aidlc-lite-rule-details"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details\*" ".aidlc-lite-rule-details\" -Recurse

Windows CMD:

mkdir .cursor\rules

(
echo ---
echo description: "AI-DLC Lite (AI-Driven Development Life Cycle — Lightweight Edition) adaptive workflow for software development"
echo alwaysApply: true
echo ---
echo.
) > .cursor\rules\ai-dlc-lite-workflow.mdc

type "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" >> .cursor\rules\ai-dlc-lite-workflow.mdc

mkdir .aidlc-lite-rule-details
xcopy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".aidlc-lite-rule-details\" /E /I

Unix/Linux/macOS:

cp ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules/lite-core-workflow.md ./AGENTS.md
mkdir -p .aidlc-lite-rule-details
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details/* .aidlc-lite-rule-details/

Windows PowerShell:

Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".\AGENTS.md"
New-Item -ItemType Directory -Force -Path ".aidlc-lite-rule-details"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details\*" ".aidlc-lite-rule-details\" -Recurse

Windows CMD:

copy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".\AGENTS.md"
mkdir .aidlc-lite-rule-details
xcopy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".aidlc-lite-rule-details\" /E /I

Verify Setup:

1. Open Cursor Settings → Rules, Commands
2. Under Project Rules, you should see ai-dlc-lite-workflow listed
3. For AGENTS.md, it will be automatically detected and applied

Directory Structure (Option 1):

<my-project>/
├── .cursor/
│   └── rules/
│       └── ai-dlc-lite-workflow.mdc
└── .aidlc-lite-rule-details/
    ├── common/
    ├── inception/
    ├── construction/
    └── operations/

AI-DLC Lite uses Cline Rules to implement its intelligent workflow.

The commands below assume your project is located under the same parent folder as the cloned repo.

Unix/Linux/macOS:

mkdir -p .clinerules
cp ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules/lite-core-workflow.md .clinerules/
mkdir -p .aidlc-lite-rule-details
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details/* .aidlc-lite-rule-details/

Windows PowerShell:

New-Item -ItemType Directory -Force -Path ".clinerules"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".clinerules\"
New-Item -ItemType Directory -Force -Path ".aidlc-lite-rule-details"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details\*" ".aidlc-lite-rule-details\" -Recurse

Windows CMD:

mkdir .clinerules
copy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".clinerules\"
mkdir .aidlc-lite-rule-details
xcopy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".aidlc-lite-rule-details\" /E /I

Unix/Linux/macOS:

cp ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules/lite-core-workflow.md ./AGENTS.md
mkdir -p .aidlc-lite-rule-details
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details/* .aidlc-lite-rule-details/

Windows PowerShell:

Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".\AGENTS.md"
New-Item -ItemType Directory -Force -Path ".aidlc-lite-rule-details"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details\*" ".aidlc-lite-rule-details\" -Recurse

Windows CMD:

copy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".\AGENTS.md"
mkdir .aidlc-lite-rule-details
xcopy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".aidlc-lite-rule-details\" /E /I

Verify Setup:

1. In Cline's chat interface, look for the Rules popover under the chat input field
2. Verify that lite-core-workflow.md is listed and active
3. You can toggle the rule file on/off as needed

Directory Structure (Option 1):

<my-project>/
├── .clinerules/
│   └── lite-core-workflow.md
└── .aidlc-lite-rule-details/
    ├── common/
    ├── inception/
    ├── construction/
    └── operations/

AI-DLC Lite uses Claude Code's project memory file (CLAUDE.md) to implement its intelligent workflow.

The commands below assume your project is located under the same parent folder as the cloned repo.

Unix/Linux/macOS:

cp ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules/lite-core-workflow.md ./CLAUDE.md
mkdir -p .aidlc-lite-rule-details
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details/* .aidlc-lite-rule-details/

Windows PowerShell:

Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".\CLAUDE.md"
New-Item -ItemType Directory -Force -Path ".aidlc-lite-rule-details"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details\*" ".aidlc-lite-rule-details\" -Recurse

Windows CMD:

copy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".\CLAUDE.md"
mkdir .aidlc-lite-rule-details
xcopy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".aidlc-lite-rule-details\" /E /I

Unix/Linux/macOS:

mkdir -p .claude
cp ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules/lite-core-workflow.md .claude/CLAUDE.md
mkdir -p .aidlc-lite-rule-details
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details/* .aidlc-lite-rule-details/

Windows PowerShell:

New-Item -ItemType Directory -Force -Path ".claude"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".claude\CLAUDE.md"
New-Item -ItemType Directory -Force -Path ".aidlc-lite-rule-details"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details\*" ".aidlc-lite-rule-details\" -Recurse

Windows CMD:

mkdir .claude
copy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".claude\CLAUDE.md"
mkdir .aidlc-lite-rule-details
xcopy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".aidlc-lite-rule-details\" /E /I

Verify Setup:

1. Start Claude Code in your project directory (CLI: claude or VS Code extension)
2. Use the /config command to view current configuration
3. Ask Claude: "What instructions are currently active in this project?"

Directory Structure (Option 1):

<my-project>/
├── CLAUDE.md
└── .aidlc-lite-rule-details/
    ├── common/
    ├── inception/
    ├── construction/
    └── operations/

AI-DLC Lite uses GitHub Copilot custom instructions to implement its intelligent workflow. The .github/copilot-instructions.md file is automatically detected and applied to all chat requests in the workspace.

The commands below assume your project is located under the same parent folder as the cloned repo.

Unix/Linux/macOS:

mkdir -p .github
cp ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rules/lite-core-workflow.md .github/copilot-instructions.md
mkdir -p .aidlc-lite-rule-details
cp -R ../aidlc-workflows/aidlc-rules/aws-aidlc-lite-rule-details/* .aidlc-lite-rule-details/

Windows PowerShell:

New-Item -ItemType Directory -Force -Path ".github"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".github\copilot-instructions.md"
New-Item -ItemType Directory -Force -Path ".aidlc-lite-rule-details"
Copy-Item "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details\*" ".aidlc-lite-rule-details\" -Recurse

Windows CMD:

mkdir .github
copy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rules\lite-core-workflow.md" ".github\copilot-instructions.md"
mkdir .aidlc-lite-rule-details
xcopy "..\aidlc-workflows\aidlc-rules\aws-aidlc-lite-rule-details" ".aidlc-lite-rule-details\" /E /I

Verify Setup:

1. Open VS Code with your project folder
2. Open the Copilot Chat panel (Cmd/Ctrl+Shift+I)
3. Select Configure Chat (gear icon) > Chat Instructions and verify that copilot-instructions is listed
4. Alternatively, type /instructions in the chat input to view active instructions

Directory Structure:

<my-project>/
├── .github/
│   └── copilot-instructions.md
└── .aidlc-lite-rule-details/
    ├── common/
    ├── inception/
    ├── construction/
    └── operations/

AI-DLC Lite works with any coding agent that supports project-level rules or steering files. The general approach:

1. Place aws-aidlc-lite-rules/ wherever your agent reads project rules from (consult your agent's documentation).
2. Place aws-aidlc-lite-rule-details/ at a sibling level so the rules can reference it.

If your agent has no convention for rules files, place both folders at your project root and point the agent to aws-aidlc-lite-rules/ as its rules directory.

1. Start any software development project by stating your intent starting with the phrase "Using AI-DLC, ..." in the chat.
2. AI-DLC Lite workflow automatically activates and guides you from there.
3. Answer targeted questions that AI-DLC Lite asks (fewer rounds than the full version).
4. Review the execution plan to see which stages will run.
5. Review the artifacts and approve each stage to maintain control.
6. All the artifacts will be generated in the aidlc-docs/ directory.

AI-DLC Lite follows the same structured three-phase approach as the full version, with reduced overhead at each stage:

• INCEPTION PHASE: Determines WHAT to build and WHY

  • Requirements analysis and validation
  • User story creation (when applicable)
  • Application design and creating units of work for parallel development

• CONSTRUCTION PHASE: Determines HOW to build it

  • Functional and non-functional design
  • Code generation and implementation
  • Build configuration and testing

• OPERATIONS PHASE: Deployment and monitoring (future)

  • Deployment automation and infrastructure
  • Monitoring and observability setup

AI-DLC supports an extension system that lets you layer additional rules on top of the core workflow. Extensions are markdown files organized under aws-aidlc-lite-rule-details/extensions/ and grouped by category (e.g., security/, testing/).

Each extension consists of two files placed in the same directory:

• A rules file (e.g., security-baseline.md) containing the extension's rules.
• An opt-in file (e.g., security-baseline.opt-in.md) containing a structured multiple-choice question presented to the user during Requirements Analysis.

At workflow start, AI-DLC scans the extensions/ directory and loads only *.opt-in.md files. During Requirements Analysis, it presents each opt-in prompt to the user. When the user opts in, the corresponding rules file is loaded (derived by naming convention: strip .opt-in.md, append .md). When the user opts out, the rules file is never loaded. Extensions without a matching *.opt-in.md file are always enforced.

Once enabled, extension rules are blocking constraints — at each stage, the model verifies compliance before allowing the stage to proceed.

The extensions/ directory ships with the following (new extensions may be added over time):

aws-aidlc-lite-rule-details/
└── extensions/
    ├── security/                      # Extension category
    │   └── baseline/
    │       ├── security-baseline.md          # Baseline security rules
    │       └── security-baseline.opt-in.md   # Opt-in prompt
    └── testing/                       # Extension category
        └── property-based/
            ├── property-based-testing.md          # Property-based testing rules
            └── property-based-testing.opt-in.md   # Opt-in prompt

You can extend an existing category or create an entirely new one.

1. Create a directory under extensions/ (e.g., security/compliance/ or performance/baseline/).
2. Add a rules file (e.g., compliance.md). Follow the same structure as security-baseline.md:
   • Define each rule as a heading in the format ## Rule <PREFIX-NN>: <Title> where the prefix is a short category identifier and NN is a sequential number (e.g., COMPLIANCE-01, COMPLIANCE-02). These IDs are referenced in audit logs and compliance summaries, so they must be unique across all loaded extensions.
   • Include a Rule section describing the requirement.
   • Include a Verification section with concrete checks the model should evaluate.
3. Add a matching opt-in file using the naming convention <name>.opt-in.md (e.g., compliance.opt-in.md). See security-baseline.opt-in.md for the expected format. Omitting this file means the extension is always enforced with no user opt-out.
4. Rules are blocking by default — if verification criteria are not met, the stage cannot proceed until the finding is resolved.

AI-DLC Lite is for anyone who wants a faster workflow with less overhead. It is not limited to a specific project type — it trades depth of analysis for speed of delivery.

Note: AI-DLC Lite can be used for production work on straightforward changes. However, for complex or high-risk production deployments, the full AI-DLC workflow provides more thorough analysis and validation. Use your judgment based on the complexity and risk of the work.

Have one of our supported platforms/tools for Assisted AI Coding installed:

• Use /context show in Kiro CLI to verify rules are loaded
• Check .kiro/steering/ directory structure
• Note: Kiro uses aws-aidlc-lite-rule-details (not .aidlc-lite-rule-details/) under the .kiro/ directory

• Check .amazonq/rules/ directory structure
• Verify rules are listed in the Amazon Q Chat Rules panel
• Note: Amazon Q uses aws-aidlc-lite-rule-details (not .aidlc-lite-rule-details/) under the .amazonq/ directory

• For "Apply Intelligently", ensure a description is defined in frontmatter
• Check Cursor Settings → Rules to ensure the rule is enabled
• If rule is too large (>500 lines), split into multiple focused rules

• Check the Rules popover under the chat input field
• Toggle rule files on/off as needed using the popover UI

• Use /config command to view current configuration
• Ask "What instructions are currently active in this project?"

• Select Configure Chat (gear icon) > Chat Instructions to verify instructions are loaded
• Type /instructions in the chat input to view active instruction files
• Check that .github/copilot-instructions.md exists in your workspace root

• Use forward slashes / in file paths within markdown files
• Windows paths with backslashes may not work correctly

Commit to repository:

# These should be version controlled
CLAUDE.md
AGENTS.md
.amazonq/rules/
.amazonq/aws-aidlc-lite-rule-details/
.kiro/steering/
.kiro/aws-aidlc-lite-rule-details/
.cursor/rules/
.clinerules/
.github/copilot-instructions.md
.aidlc-lite-rule-details/

Optional - Add to .gitignore (if needed):

# Local-only settings
.claude/settings.local.json

For the complete reference of all documentation artifacts generated by the AI-DLC workflow, see docs/GENERATED_DOCS_REFERENCE.md.

See CONTRIBUTING for more information.

This library is licensed under the MIT-0 License. See the LICENSE file.