AIDD · Manifesto · v1.1 · 2026
A standard for building software in the age of AI — written by developers, for developers.
A way of building software in which a developer works with AI as a deliberate partner — planning, decomposing, and reviewing every change — while remaining the architect accountable for what ships.
Also known as AI-assisted development, AI-assisted coding, AI-augmented engineering, AI-native development, agentic coding, spec-driven development, prompt-driven development, AI pair programming, context engineering
Do not care about code quality.
High quality legacy code output.
These non-technical values guide every AI-assisted coding session.
plan ──→ implement ↑ ↓ assert ←── review ——————————————— any ide · any model workflow leads.
$ claude $ codex $ cursor $ copilot … swap tools · same speed.
$ git commit → reviewed ✓ → tested ✓ Signed-off-by: you ✓ ——————————————— the human owns it.
$ ai "ship it" + 1,240 lines merged ——————————————— ⚠ no review nobody read it. who owns this?
ai: auth via JWT. $ why? we use HttpOnly sessions. ai: rewriting. ✓ ——————————————— you understood.
ai: auth via JWT. $ ok accept ——————————————— ⚠ 3am why is this here? nobody knows.
features shipped ✓ bugs avoided ✓ users impacted +410 ——————————————— the business moved.
lines generated 12k tokens burned 1.2M commits/day 38 ——————————————— … vanity · zero impact.
Ship in verified increments.
Working software is the output of spec, plan, tests, review, and release.
Start from a clear spec.
A story, PRD, or spec gives AI work a contract humans can inspect.
Plan before generation.
The plan is the handoff between human judgment and agent execution.
Decompose until delegable.
Small tasks survive async work, model changes, and team handoffs.
Craft context with the care we give code.
Specs, markdown, rules, skills, and memory deserve the same quality bar as software.
Capture learning for reuse.
Each lesson becomes memory, a rule, a decision, or a skill others can use.
Own every shipped change.
AI may produce it; humans approve, merge, and maintain it.
Do not delegate what you cannot evaluate.
Use AI where you can judge tradeoffs, read the output, and prove behavior.
Improve the system before forcing the model.
When output degrades, clarify boundaries, names, tests, and context before asking harder.
Rebuild context when coherence drops.
Reset from memory, docs, rules, and the current plan instead of improvising.
Treat AI failure as a signal.
When the model stalls, inspect scope, context, assumptions, and tests before pushing harder.
Make the practice transferable.
A shared method lets different people produce the same quality of code across tools.
Public signature registry
Be among the first to sign the AI-Driven Development Manifesto and help shape the future of software development.
This is how I already build software with AI, and how I want the trade to mature.
AI-Driven Ops
AI-Driven Development. Craft first, always.
AI-Driven Development, create things and have fun with it
AI-Driven Development, the method that helps me to keep control of my codebase quality in an AI driven world.
AI-Driven Dev
Master AI for speed and excellent products that people love
AI is not a trend, it's how we work. AI-Driven Dev is the path I chose to build better, faster.
AI-Driven Dev
AI is a tool and like every tools, you need practice and guidance to produce the best quality possible with it !
Context is the new code. The value has moved from typing to thinking.
You can build saas alone with AI, or you can contribute to make great projects greater. Don't measure your value on token spending.
AI-Driven Devevelopment? Build smarter. Ship with confidence. Always.
AI-Driven Development, the method that lets me move faster with AI while keeping quality, understanding, and ownership under control.
Embracing the future without throwing away decades of software development knowledge.
Not prototypes. Production. AIDD is how AI ships client work I can stand behind.
with great power comes great responsibility
Smart delegation of mastered tasks to AI delivers real speed gains while shipping code of the highest quality. It's how we build tomorrow."
Tools come and go; the method stays. AI speeds me up, judgment keeps me right — quality is non-negotiable.
AI is only as valuable as the problems it solves. I build to serve the business and the people who actually use the software.
I use AI to move faster, but I keep the hard parts human: intent, taste, judgment, and accountability.
Building with AI to solve business problems is better with the best Method
AI-Driven
Perseverance is the mother of success, AI lights my way there.
AIDD dev crafter
Retaining ownership and responsibility on code / artifacts seems key to reducing the inherent risks of this AI transformation.
Adapting and developing our business using the best AI tools and the best structured methodology: AIDD
AI is reshaping how we write code. I'm here to do it thoughtfully, and help others navigate that shift.
Shaping the next era of development, line by line.
AI is the accelerator. You are the driver.
AI is the new cloud...
Don\'t be framed
AI makes me a better developer — faster, more consistent, always in control.
AI turns up the volume. You write the song.
We don't build software for AI—we build it for people. AI accelerates the journey, understanding the destination is our job.
Context Engineering taught me that AI doesn't need better prompts — it needs the right context. At Kestra, we automated our full plugin SDLC by encoding our engineering knowledge into agents, not by bypassing it.
Better code, bigger impact. That's what AI-driven development means to me.
This is how I actively build software today, and the evolutionary path I advocate for the engineering discipline.
du bon sens
Building the future of education
I've completely automated my development workflow. I now only review and refine the code.
Une manière d'industrialiser le process de dev AI
AI-driven development means building faster and better, so I can work less and live more :D
Crafting with purpose and business value. While using a local-first, and open source approach.
This is how I build software with AI.
