Home » Software Dev » AI-DLC brings structured dev workflows to 7 AI coding tools

AI-DLC brings structured dev workflows to 7 AI coding tools

Cagri Sarigoz

Published October 16, 2026

Ad-hoc AI coding works fine for a quick script. It falls apart on anything with moving parts because context leaks, decisions go unrecorded, and nobody put an approval gate in front of the infrastructure change.

AI-DLC (AI-Driven Development Life Cycle) is an MIT-licensed framework from AWS Labs that wraps a structured, verifiable delivery workflow around the AI coding assistant you already use. One harness-neutral core runs across Claude Code, Kiro CLI, Kiro IDE, Codex CLI, Cursor, opencode, and GitHub Copilot.

What the framework adds

The core engine brings a lot of structure that ad-hoc prompting does not have:

• 5 phases and 33 stages covering initialization through ongoing operations
• 14 agents: 11 domain specialists, 2 reviewers, and an adaptive composer
• 11 workflow profiles for features, bug fixes, infrastructure, security, proofs of concept, and enterprise delivery
• Human approval gates before the agent moves forward on consequential steps
• A 119-event audit trail with persistent state, team knowledge, and learned rules

The recommended model is Claude Opus 4.8. The methodology itself is provider-independent, so other capable reasoning models work too.

Installing it

On macOS, Linux, or WSL:

curl -fsSL https://github.com/awslabs/aidlc-workflows/releases/latest/download/install.sh | sh

On Windows PowerShell:

irm https://github.com/awslabs/aidlc-workflows/releases/latest/download/install.ps1 | iex

The installer handles the aidlc command and every harness runtime. No Bun or Node.js required for the native install path. Once installed, point it at your project and pick your harness:

cd /path/to/your-project
aidlc config --harness claude
aidlc doctor

Swap claude for kiro, kiro-ide, codex, cursor, opencode, or copilot. Then open your harness and describe the work:

/aidlc Build a REST API for inventory management

Codex CLI uses $aidlc instead of /aidlc. In Kiro IDE, select aidlc in the chat panel’s agent picker first.

The operator takeaway

If you’re a solo dev or small team using AI coding assistants on anything beyond throwaway scripts, the lack of structure is where things go wrong. AI-DLC is a free layer that adds the approval gates, audit trail, and workflow profiles you’d otherwise have to build yourself. The harness-neutral design means you’re not locked into one tool.

Cagri Sarigoz( Founder )

I’m founder of BizStack at Cagri Sarigoz LLC and a passionate advocate for entrepreneurs.

With over 14 years in tech, marketing, and AI, including my role as Head of SEO at CitizenShipper and co-founder of TaleBot at Intale AI, I’m dedicated to sharing genuine, useful product insights and tips.

At BizStack, I aim to cut through the digital noise to provide clear, actionable advice.

And more than all else, I’m a father to a (always) little girl and a husband.

Contact me at [email protected] for assistance.