Vision

AI DevKit exists to make AI coding agents follow a repeatable engineering workflow.

It inherits the idea from The New Engineering Workflow in AI changes the Tools, you still own the Craft: empowering engineers to integrate AI effectively into a structured, test-driven, and craftsmanship-focused development process.

We believe that AI coding assistants are most powerful when they work within a well-defined engineering framework where documentation is clear, plans are systematic, and architecture is intentional.

AI DevKit provides the workflow layer for that structure. It helps engineers reduce repeated prompting, keep context in sync, share memory across sessions, verify work before completion claims, and make the same process available across coding agents.

Our goal is simple: To make working with AI feel as natural and reliable as working with your favorite teammate, the one who already knows your project, your style, and your standards.

A toolkit that enables developers to:

• Plan before code - Capture requirements, design decisions, and implementation tasks before agents edit files
• Remember project context - Reuse decisions, conventions, and fixes across sessions
• Verify completion - Require fresh evidence before work is marked done
• Review before push - Make code review part of the agent workflow, not an afterthought
• Keep agents consistent - Use one config so every supported coding agent follows the same workflow

1. Plan before code - Start with clear requirements and design before implementation
2. Evidence before done - Treat test/build output as part of completion, not an optional follow-up
3. Durable context - Keep project knowledge in docs and memory so agents do not start from zero
4. One config, all agents - Make the workflow travel across the coding tools your team uses
5. Low friction - Make disciplined engineering easier than repeating prompts manually

We envision a future where AI coding agents plan before code, remember project decisions, verify work with fresh evidence, and review changes before you push. The goal is not a fully autonomous software factory; it is a disciplined agentic software development loop where humans keep ownership and agents follow the same engineering standards every time. One config. All agents. Same workflow.

AI DevKit is our contribution to that future.