Agent Workflow for AIs

What is awa?

awa (Agent Workflow for AIs) is a CLI tool that generates AI coding agent configuration files via templates with feature flags. It enforces a structured development workflow (awa’s or yours) with full traceability from requirements through to tests.

Structured Workflow

Guide your AI through every stage: Architecture → Features → Requirements → Design → Tasks → Code & Tests → Documentation.

Full Traceability

Every line of code traces back to the requirement that motivated it via @awa-impl and @awa-test markers.

Template AI Files

Use Eta templates with conditionals, loops, and partials. Enable or disable content with feature flags and presets.

Drift Detection

awa diff shows exactly what has changed in your agent configuration files vs. the templates — before you commit.

Git or Local

Pull templates from GitHub, GitLab, Bitbucket, or use a local path. Cached locally for fast re-runs.

Agent-Agnostic

Generate configuration for Copilot, Claude, Cursor, Windsurf, and more — all from a single template set.

The Problem: Divergence

Developing with AI agents requires process. Configuration files that define this process get copy-pasted between projects, then diverge. Requirements live in one place, implementation in another, tests in a third — nothing connects them. They diverge too.

Without structure, work drifts and nobody, including the AI, can trace what happened or why.

How awa Solves It

awa generates agent configuration files from templates with feature flags. Every artifact traces back to its origin through explicit markers:

ARCHITECTURE → FEAT → REQUIREMENTS → DESIGN → TASKS → CODE & TESTS → DOCUMENTATION

Quick Start Install awa and generate your first configuration.

Workflow Guide Understand the awa workflow and traceability chain.

CLI Reference All commands and options documented.

Template Engine Learn how to write powerful templates with Eta.