I Built an AI Development Team in My Terminal
Projectinator turns one app idea into a Scrum backlog, working files, and a browser-tested result. Here is how the pipeline works, what it costs, and where it still needs human judgment.

Projectinator turns one app idea into a Scrum backlog, working files, and a browser-tested result. Here is how the pipeline works, what it costs, and where it still needs human judgment.

Less spectacle. More working software.
01 / From the notebook
ai engineering
omp is the open-source terminal harness I run my coding agents in. Here is what it does when a model goes down mid-task, how subagents, the advisor, and memory work, and the small config I actually use.
AI can write more code every month. That is not a reason to stop learning programming. It is a reason to become the developer who can direct, verify, and deliver with it.
ai engineering
I use Codex and Claude Code only from the terminal. Here is the exact repository workflow, prompt structure, and safety boundary you can copy.
02 / Off the page
Your Mac's notch, turned into a command deck.
Make sense of where your money goes.
You're the PM — your dev team is a roster of AI models.
Write markdown. Press Ctrl+E. Read it.
The open experiment
Compare the first results from different AI models. Look past the claims and judge the work.
Step into the ArenaKeep the curiosity going
Practical AI engineering, real builds, and the decisions behind them. Follow along on YouTube, or keep up with the writing through RSS.

About Stepan
I'm Stepan Manookian. Friends call me Steve. I have spent more than twelve years across full-stack development, IT project management, automotive software, and independent product work.
Stevinator is where I build production-minded AI systems in public, explain the decisions, and share what changes when software meets real users, teams, and deadlines.