A software engineer details how he went from merging eight to 20 pull requests per month to 200+ after joining AI-native creator startup Tano eight months ago

Your coding output can increase tenfold as AI agents build features, allowing you to merge over 200 pull requests monthly.

Software engineer Neil Kakkar reported a tenfold increase in his monthly pull requests (PRs) after joining Tano, an AI-native startup, eight months ago. Previously at PostHog, he merged eight to 20 PRs per month, a rate that was already significantly higher than his initial three years at Bloomberg. Kakkar attributes this massive productivity jump to AI tools, specifically mentioning Claude Code Desktop, which allows AI agents to build entire features with minimal human input. The AI agents handle tasks within one to two hours, generating PRs that are then reviewed by Kakkar. This shift has eliminated traditional engineering bottlenecks like communication overhead and extensive code reviews, enabling faster iteration and development cycles. The new workflow involves Kakkar managing multiple tasks concurrently, with AI agents working in parallel on different components or features.

The dramatic increase in individual engineering output, exemplified by Kakkar's tenfold jump in pull requests, signals a fundamental shift in how software development is performed. AI agents are not just assisting with menial tasks but are capable of end-to-end feature development, effectively automating large portions of the coding and integration process. This allows engineers to move beyond traditional bottlenecks like code reviews and cross-team communication, focusing instead on higher-level problem-solving and architectural decisions, or managing multiple AI-driven projects simultaneously.

This evolution has significant implications for the tech industry, potentially redefining team structures, skill requirements, and the overall pace of innovation. Startups embracing AI-native approaches can achieve unprecedented development velocity, creating a competitive advantage over established companies. Engineers who can effectively leverage and manage AI agents, shifting their focus from code writing to oversight and strategy, will be best positioned to thrive in this rapidly changing landscape.