Serial entrepreneur Pavlo Kharmanskyi launches Open Steps to help non-engineers build with AI coding agents
Technology entrepreneur Pavlo Kharmanskyi has launched Open Steps, an open-source project designed to help non-technical users work more effectively with AI coding agents.
The project is intended for founders, product managers and other builders who increasingly use AI tools to create software despite having little or no engineering background.
Kharmanskyi’s career spans more than two decades and several waves of technological change. He began building websites as a teenager and has since launched businesses across online communities, e-commerce, software development, cryptocurrency, fintech, NFTs, and creator technology. Across eight ventures, he has achieved three exits.
An early online community network grew to more than 10 million followers before being acquired in a seven-figure deal. He later invested more than $1 million of his own capital into FinSafe, a company aiming to create a unified trading layer across cryptocurrency exchanges. In 2023, he launched OnlyMonster with one part-time developer and fewer than ten users in a private Telegram group.
OnlyMonster has since grown into his largest business, providing operational software for agencies and creators working across fan platforms. The company now serves users in more than 100 countries and operates within the emerging CreatorOps software category.
Kharmanskyi says the idea for Open Steps emerged from his own experience using AI coding agents. Although the technology is increasingly capable of writing code, he found that many tools still communicate in a way that assumes users have an engineering background.
As he explains on the Open Steps website: “The agent does excellent work, then tells me about it in commit hashes and jargon, and I genuinely cannot tell whether we are done.”
Rather than replacing coding agents, Open Steps is designed to improve how they communicate progress, tasks and outcomes. The system provides plain-language explanations of completed work, identifies outstanding actions and highlights any steps that require human input.
The project currently includes tools for assessing whether work is complete, translating technical explanations into non-technical language, identifying next steps and independently verifying claims made during coding sessions.
Open Steps is available free of charge under an MIT licence, with its methodology and testing data published openly. Since its release, the project has attracted more than 1,000 stars on GitHub.
Kharmanskyi argues that advances in AI coding tools could broaden access to software development beyond traditional engineering teams. Open Steps focuses on helping less technical users understand and manage the work carried out by those systems.
“This technology is just starting. I want to be part of building it,” he says.
For more startup news, check out the other articles on the website, and subscribe to the magazine for free. Listen to The Cereal Entrepreneur podcast for more interviews with entrepreneurs and big-hitters in the startup ecosystem.
