AI-DLC (AI-Driven Development Life Cycle) — Complete Guide & Instructions

A comprehensive reference for understanding, installing, and operating AWS's open-source AI-Driven Development Life Cycle (AI-DLC) methodology and its awslabs/aidlc-workflows steering rules.

---

Table of Contents

1. What Is AI-DLC?
2. Core Philosophy & Tenets
3. The Three-Phase Adaptive Workflow
4. Key Features
5. Prerequisites
6. Common Setup (All Platforms)
7. Platform-Specific Setup
8. Usage Workflow
9. The Extension System
10. Supporting Tools
11. Generated Documentation (aidlc-docs/)
12. Experimental: AI-Assisted Setup
13. Version Control Recommendations
14. Troubleshooting
15. Updating AI-DLC
16. Additional Resources
17. QA / Testing Angle

---

1. What Is AI-DLC?

AI-DLC (AI-Driven Development Life Cycle) is a methodology, introduced by AWS in late July 2025, that reimagines the traditional Software Development Life Cycle (SDLC) with AI agents placed at the center of the process rather than bolted on as tooling.

The central shift is:

From "humans build, AI helps" → to "agents build, humans govern."

AI agents execute tasks across planning, design, implementation, testing, review, deployment, and operations, while humans validate outcomes at defined checkpoints.

The open-source implementation lives at awslabs/aidlc-workflows and ships a set of steering rules you drop into your AI coding agent. Once installed, you start work by typing Using AI-DLC, ... in the chat, and the workflow activates and guides you from there.

Key facts:

• Repository: github.com/awslabs/aidlc-workflows
• License: MIT-0
• A 2.0 Preview exists on the v2 branch, aimed at making autonomous development more verifiable and self-correcting.
• AI-DLC is fundamentally a methodology, not a tool — you don't need to install anything special to get started beyond a supported coding agent.

⚠️ Note: Generative AI can make mistakes. Review all output, artifacts, and costs generated by your AI model and agentic coding assistant.

---

2. Core Philosophy & Tenets

These are the guiding principles behind AI-DLC:

• No duplication. The source of truth lives in one place. Files for new tools or formats are generated from the source rather than maintained as separate copies.
• Methodology first. AI-DLC is a methodology, not a tool. Users shouldn't need to install anything to get started, though convenience tooling may be added over time.
• Reproducible. Rules should be clear enough that different models produce similar outcomes. The methodology minimizes variance through explicit guidance.
• Agnostic. The methodology works with any IDE, agent, or model — no lock-in to specific tools or vendors.
• Human in the loop. Critical decisions require explicit user confirmation. The agent proposes; the human approves.

---

3. The Three-Phase Adaptive Workflow

AI-DLC follows a structured three-phase approach that adapts to project complexity. It only executes stages that add value to a given request.

🔵 Inception Phase — determines WHAT to build and WHY

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

🟢 Construction Phase — determines HOW to build it

• Detailed component design
• Code generation and implementation
• Build configuration and testing strategies
• Quality assurance and validation

🟡 Operations Phase — deployment and monitoring (future)

• Deployment automation and infrastructure
• Monitoring and observability setup
• Production readiness validation

---

4. Key Features

Feature	Description
Adaptive Intelligence	Only executes stages that add value to your specific request
Context-Aware	Analyzes existing codebase and complexity requirements
Risk-Based	Complex changes get comprehensive treatment; simple changes stay efficient
Question-Driven	Structured multiple-choice questions delivered in files, not chat
Always in Control	Review execution plans and approve each phase
Extensible	Layer custom rules (security, compliance, org-specific) on top of the core workflow

---

5. Prerequisites

You need one of the following supported AI coding platforms installed:

Platform	Install
Kiro	https://kiro.dev/
Kiro CLI	https://kiro.dev/cli/
Amazon Q Developer IDE Plugin	AWS docs → Q in IDE
Cursor IDE	https://cursor.com/
Cline (VS Code Extension)	VS Code Marketplace → saoudrizwan.claude-dev
Claude Code CLI	https://github.com/anthropics/claude-code
GitHub Copilot	VS Code Marketplace → GitHub.copilot + GitHub.copilot-chat

---

6. Common Setup (All Platforms)

1. Download the latest release zip named ai-dlc-rules-v<release-number>.zip from the Releases page to a folder outside your project directory (e.g. ~/Downloads).
2. Extract the zip. It contains an aidlc-rules/ folder with two subdirectories:
   • aws-aidlc-rules/ — the core AI-DLC workflow rules
   • aws-aidlc-rule-details/ — detailed rules conditionally referenced by the core rules
3. Follow the setup instructions for your coding agent and platform (below).

🪟 Windows users: File Explorer's Extract All... dialog defaults to creating a wrapper folder named after the zip (e.g. ai-dlc-rules-v0.1.8\aidlc-rules\...). Either edit the destination so the contents land directly in Downloads\aidlc-rules\, or prepend ai-dlc-rules-v<version>\ to each Downloads\ path in the commands.

---

7. Platform-Specific Setup

All commands below assume the zip was extracted so the path is Downloads/aidlc-rules/. Replace Downloads with your actual folder if different.

7.1 Kiro

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

macOS/Linux:

mkdir -p .kiro/steering
cp -R ~/Downloads/aidlc-rules/aws-aidlc-rules .kiro/steering/
cp -R ~/Downloads/aidlc-rules/aws-aidlc-rule-details .kiro/

Windows (PowerShell):

New-Item -ItemType Directory -Force -Path ".kiro\steering"
Copy-Item -Recurse "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rules" ".kiro\steering\"
Copy-Item -Recurse "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rule-details" ".kiro\"

Windows (CMD):

mkdir .kiro\steering
xcopy %USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rules .kiro\steering\aws-aidlc-rules\ /E /I
xcopy %USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rule-details .kiro\aws-aidlc-rule-details\ /E /I

Resulting structure:

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

Verify:

• Kiro IDE: Open the steering files panel; confirm a core-workflow entry under Workspace.
• Kiro CLI: Run kiro-cli, then /context show; confirm .kiro/steering/aws-aidlc-rules.
• Run AI-DLC in Vibe mode. If Kiro nudges you to switch to spec mode, select No to stay in Vibe mode.

7.2 Amazon Q Developer IDE Plugin/Extension

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

macOS/Linux:

mkdir -p .amazonq/rules
cp -R ~/Downloads/aidlc-rules/aws-aidlc-rules .amazonq/rules/
cp -R ~/Downloads/aidlc-rules/aws-aidlc-rule-details .amazonq/

Windows (PowerShell):

New-Item -ItemType Directory -Force -Path ".amazonq\rules"
Copy-Item -Recurse "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rules" ".amazonq\rules\"
Copy-Item -Recurse "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rule-details" ".amazonq\"

Windows (CMD):

mkdir .amazonq\rules
xcopy %USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rules .amazonq\rules\aws-aidlc-rules\ /E /I
xcopy %USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rule-details .amazonq\aws-aidlc-rule-details\ /E /I

Resulting structure:

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

Verify: In the Amazon Q Chat window, click Rules (lower-right); confirm entries for .amazonq/rules/aws-aidlc-rules.

7.3 Cursor IDE

AI-DLC uses Cursor Rules.

Option 1 — Project Rules (recommended)

macOS/Linux:

mkdir -p .cursor/rules

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

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

mkdir -p .aidlc-rule-details
cp -R ~/Downloads/aidlc-rules/aws-aidlc-rule-details/* .aidlc-rule-details/

Windows (PowerShell):

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

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

"@
$frontmatter | Out-File -FilePath ".cursor\rules\ai-dlc-workflow.mdc" -Encoding utf8
Get-Content "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rules\core-workflow.md" | Add-Content ".cursor\rules\ai-dlc-workflow.mdc"

New-Item -ItemType Directory -Force -Path ".aidlc-rule-details"
Copy-Item "$env:USERPROFILE\Downloads\aidlc-rules\aws-aidlc-rule-details\*" ".aidlc-rule-details\" -Recurse

Windows (CMD):

mkdir .cursor\rules
(
echo ---
echo description: "AI-DLC (AI-Driven Development Life Cycle) adaptive workflow for software development"
echo alwaysApply: true
echo ---
echo.
) > .cursor\rules\ai-dlc-workflow.mdc
type "%USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rules\core-workflow.md" >> .cursor\rules\ai-dlc-workflow.mdc
mkdir .aidlc-rule-details
xcopy "%USERPROFILE%\Downloads\aidlc-rules\aws-aidlc-rule-details" ".aidlc-rule-details\" /E /I

Option 2 — AGENTS.md (simple alternative)

macOS/Linux:

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

Verify: Open Cursor Settings → Rules, Commands. Under Project Rules, you should see ai-dlc-workflow. AGENTS.md is auto-detected.

Structure (Option 1):

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

7.4 Cline

AI-DLC uses Cline Rules.

Option 1 — .clinerules directory (recommended)

macOS/Linux:

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

Option 2 — AGENTS.md

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

Verify: In Cline's chat, find the Rules popover under the chat input; confirm core-workflow.md is listed and active. Toggle on/off as needed.

7.5 Claude Code

AI-DLC uses Claude Code's project memory file (CLAUDE.md).

Option 1 — Project root (recommended)

macOS/Linux:

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

Option 2 — .claude directory

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

Verify: Start Claude Code in the project. Use /config to view configuration, or ask "What instructions are currently active in this project?"

7.6 GitHub Copilot

AI-DLC uses GitHub Copilot custom instructions. The file .github/copilot-instructions.md is auto-detected and applied to all chat requests in the workspace.

macOS/Linux:

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

Verify: Open Copilot Chat (Cmd/Ctrl+Shift+I) → Configure Chat (gear) → Chat Instructions; verify copilot-instructions is listed. Or type /instructions in the chat input.

7.7 OpenAI Codex

AI-DLC uses the Codex AGENTS.md convention. Codex auto-discovers and loads AGENTS.md from your project root at session start.

macOS/Linux:

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

Verify: Start a Codex session and ask — for an existing project: "Using AIDLC analyze the project?"; for a new one: "Using Aidlc what workflow do you see?" Codex should describe the three-phase workflow (Inception → Construction → Operations).

If Codex reports the project docs exceed its instruction limit, raise it in config.toml, e.g. project_doc_max_bytes = 65536.

7.8 Other Agents

AI-DLC works with any coding agent that supports project-level rules or steering files:

1. Place aws-aidlc-rules/ wherever your agent reads project rules from.
2. Place aws-aidlc-rule-details/ at a sibling level so the rules can reference it.
3. If your agent has no rules convention, place both folders at the project root and point the agent to aws-aidlc-rules/ as its rules directory.

---

8. Usage Workflow

1. Start any software development project by stating your intent beginning with Using AI-DLC, ... in the chat.
2. The AI-DLC workflow automatically activates and guides you from there.
3. Answer the structured questions that AI-DLC asks.
4. Carefully review every plan the AI generates — provide your oversight and validation.
5. Review the execution plan to see which stages will run.
6. Carefully review the artifacts and approve each stage to maintain control.
7. All artifacts are generated in the aidlc-docs/ directory.

---

9. The Extension System

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

How Extensions Work

Each extension consists of two files in the same directory:

• A rules file (e.g. security-baseline.md) — the extension's rules.
• An opt-in file (e.g. security-baseline.opt-in.md) — a structured multiple-choice question presented 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. When you opt in, the corresponding rules file is loaded (by naming convention: strip .opt-in.md, append .md). When you opt 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 the stage can proceed.

Built-in Extensions

aws-aidlc-rule-details/
└── extensions/
    ├── security/
    │   └── baseline/
    │       ├── security-baseline.md
    │       └── security-baseline.opt-in.md
    ├── testing/
    │   └── property-based/
    │       ├── property-based-testing.md
    │       └── property-based-testing.opt-in.md
    └── resiliency/
        └── baseline/
            ├── resiliency-baseline.md
            └── resiliency-baseline.opt-in.md

⚠️ The security and resiliency extensions are directional references. Each organization should build, customize, and thoroughly test its own rules before deploying to production workflows.

Adding Your Own Extensions

1. Create a directory under extensions/ (e.g. security/compliance/ or performance/baseline/).
2. Add a rules file (e.g. compliance.md) following the same structure as security-baseline.md:
   • Define each rule as a heading ## 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 appear 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 for the model to evaluate.
3. Add a matching opt-in file using <name>.opt-in.md. Omitting it means the extension is always enforced with no opt-out.
4. Rules are blocking by default — if verification criteria aren't met, the stage cannot proceed until the finding is resolved.

---

10. Supporting Tools

Located in the scripts/ directory.

10.1 AIDLC Evaluator — scripts/aidlc-evaluator/

Automated testing and reporting framework for validating changes to AI-DLC workflows:

• Golden Test Cases — curated baseline test cases for validation
• Execution Framework — orchestration for running test cases through pipelines
• Semantic Evaluation — AI-based assessment of output correctness and completeness
• Code Evaluation — static analysis (linting, security scanning, duplication detection)
• NFR Evaluation — non-functional requirements testing (token usage, execution time, cross-model consistency)
• CI/CD Integration — automated pipelines for PR validation

Quick start:

cd scripts/aidlc-evaluator
uv sync
uv run python run.py test

10.2 AIDLC Design Reviewer — scripts/aidlc-designreview/ (experimental)

AI-powered design review tool analyzing AIDLC design artifacts using Claude models via AWS Bedrock.

• Multi-Agent Review — three specialized agents (Critique, Alternatives, Gap Analysis)
• Quality Scoring — weighted severity analysis with actionable recommendations
• Two deployment modes — CLI tool (for CI/CD) and Claude Code Hook (real-time, experimental)

Install (CLI):

cd scripts/aidlc-designreview
uv sync --extra test
source .venv/bin/activate   # Linux/Mac
design-reviewer --aidlc-docs /path/to/aidlc-docs

Install (Claude Code Hook):

./scripts/aidlc-designreview/tool-install/install-linux.sh       # Linux
./scripts/aidlc-designreview/tool-install/install-mac.sh         # macOS
.\scripts\aidlc-designreview\tool-install\install-windows.ps1    # Windows PowerShell

The installer auto-detects the workspace root and installs the hook to .claude/.

10.3 AIDLC Code Reviewer — aws-samples/sample-aidlc-code-reviewer

Now lives in its own repository (moved out of scripts/aidlc-codereview/).

Agent-native code review toolkit pairing local static analysis with assistant-guided phases:

• Three review phases — critical technical findings, structure critique, business logic review
• Static + AI analysis — combines ruff, mypy, bandit with AI critique; attribution badges (AI, Static, AI + Static)
• Multi-assistant support — Claude Code, Kiro, GitHub Copilot, Codex

---

11. Generated Documentation (aidlc-docs/)

All artifacts produced by the AI-DLC workflow are written to the aidlc-docs/ directory. For the complete reference of every generated artifact, see docs/GENERATED_DOCS_REFERENCE.md in the repository.

---

12. Experimental: AI-Assisted Setup

Instead of copying files manually, you can let your agent handle setup (validated with Kiro, Claude Code, Cursor, Antigravity). Requires an agent with shell access.

Paste this prompt into your AI agent:

Set up AI-DLC in this project by doing the following:

1. Download the latest AI-DLC release:
   - Use the GitHub API to find the latest release asset URL:
     curl -sL https://api.github.com/repos/awslabs/aidlc-workflows/releases/latest \
       | grep -o '"browser_download_url": *"[^"]*"' \
       | head -1 \
       | cut -d'"' -f4
   - Download the zip from that URL to /tmp/aidlc-rules.zip
   - Extract it: unzip -o /tmp/aidlc-rules.zip -d /tmp/aidlc-release
   - Copy the aidlc-rules/ folder from the extracted contents into .aidlc at the project root
   - Clean up: rm -rf /tmp/aidlc-rules.zip /tmp/aidlc-release

2. Create the appropriate rules/steering file for your IDE using the options below.
   Pick the one that matches the agent you are running in:

   - Kiro IDE or Kiro CLI     -> create `.kiro/steering/ai-dlc.md`
   - Amazon Q Developer       -> create `.amazonq/rules/ai-dlc.md`
   - Antigravity              -> create `.agent/rules/ai-dlc.md`
   - Cursor                   -> create `.cursor/rules/ai-dlc.mdc` with frontmatter:
                                  ---
                                  description: "AI-DLC workflow"
                                  alwaysApply: true
                                  ---
   - Cline                    -> create `.clinerules/ai-dlc.md`
   - Claude Code              -> create `CLAUDE.md`
   - GitHub Copilot           -> create `.github/copilot-instructions.md`
   - Any other agent          -> create `AGENTS.md`

3. The file content should be:
   When the user invokes AI-DLC, read and follow
   `.aidlc/aidlc-rules/aws-aidlc-rules/core-workflow.md` to start the workflow.

4. Add `.aidlc` to `.gitignore` unless I explicitly ask you not to.

5. Confirm what file you created and that `.aidlc` is gitignored.

The agent downloads the latest release, creates the correct config file for your IDE, and gitignores .aidlc automatically.

---

13. Version Control Recommendations

Commit to the repository:

CLAUDE.md
AGENTS.md
.amazonq/rules/
.amazonq/aws-aidlc-rule-details/
.kiro/steering/
.kiro/aws-aidlc-rule-details/
.cursor/rules/
.clinerules/
.github/copilot-instructions.md
.aidlc-rule-details/

Optionally add to .gitignore:

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

---

14. Troubleshooting

General Issues

Problem	Solution
Rules not loading	Check the file exists in the correct location for your platform
File encoding issues	Ensure files are UTF-8 encoded
Rules not applied in session	Start a new chat session after file changes
Rule details not loading	Verify .aidlc-rule-details/ exists with subdirectories

Platform-Specific

Amazon Q Developer / Kiro

• Use /context show to verify rules are loaded
• Check .amazonq/rules/ or .kiro/steering/ directory structure

Cursor

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

Cline

• Check the Rules popover under the chat input; toggle rule files as needed

Claude Code

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

GitHub Copilot

• Configure Chat (gear) → Chat Instructions to verify instructions are loaded
• Type /instructions in the chat input to view active instruction files
• Confirm .github/copilot-instructions.md exists in the workspace root

File Path Issues on Windows

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

---

15. Updating AI-DLC

Re-run the AI-assisted setup prompt (Section 12). The agent downloads the latest release and overwrites the existing .aidlc/ folder. For manual setups, download the newest release zip and re-copy the rule folders into place.

---

16. Additional Resources

Resource	Link
AI-DLC Method Definition Paper	https://prod.d13rzhkk8cj2z0.amplifyapp.com/
AI-DLC Methodology Blog	https://aws.amazon.com/blogs/devops/ai-driven-development-life-cycle/
AI-DLC Open-source Launch Blog	https://aws.amazon.com/blogs/devops/open-sourcing-adaptive-workflows-for-ai-driven-development-life-cycle-ai-dlc/
AI-DLC Example Walkthrough (Amazon Q)	https://aws.amazon.com/blogs/devops/building-with-ai-dlc-using-amazon-q-developer/
2.0 Preview Specification	assets/AI-DLC-Workflows-2.0-Specification.pdf (v2 branch)
Working with AI-DLC (patterns & tips)	docs/WORKING-WITH-AIDLC.md
Repository	https://github.com/awslabs/aidlc-workflows

---

17. QA / Testing Angle

For a QA/test engineering context, the most directly relevant pieces of AI-DLC are:

• Property-based testing extension (extensions/testing/property-based/) — an opt-in, blocking constraint that enforces property-based testing rules at each construction stage.
• AIDLC Evaluator — its NFR evaluation (token usage, execution time, cross-model consistency), semantic evaluation, and static code evaluation mirror a test-harness mindset and integrate with CI/CD for PR validation.
• Custom extensions — you can author your own testing/compliance rules with unique PREFIX-NN IDs that surface in audit logs, turning test governance into a blocking gate.
• Human-in-the-loop gates — every stage requires explicit approval, which aligns naturally with QA sign-off checkpoints.

Because extension rules are blocking and verification-driven, AI-DLC effectively lets you encode quality gates (security, testing, resiliency, compliance) as first-class, enforceable steps in the development lifecycle rather than after-the-fact checks.

---

Compiled from the awslabs/aidlc-workflows repository README and official AWS AI-DLC resources.