GitHub CEO: Our Devs Barely Write Code

2026-03-25 · Source: No Priors: AI, Machine Learning, Tech, & Startups · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy · Depth: Intermediate, quick

Summary

Developers typically spend only two to three hours daily writing code, with an equivalent amount of time dedicated to peer code reviews. While human oversight remains crucial for security and trust before merging code into production, AI-powered code review agents are emerging as a significant area for assistance. These agents can help distributed teams by not only identifying vulnerabilities but also automatically fixing them, including simpler tasks like linter errors and code formatting. This automation aims to significantly reduce security backlogs, enhancing both open-source and commercial software projects. GitHub, as a platform, needs to evolve to provide the necessary primitives for these AI agents to collaborate effectively with human developers.

Key takeaway

For engineering leaders aiming to optimize developer productivity and enhance code quality, consider integrating AI-powered code review agents into your workflow. This can significantly reduce time spent on routine tasks like linter error correction and initial vulnerability fixes, allowing your teams to focus on more complex development challenges. Ensure your platform, like GitHub, supports the necessary integrations for AI and human collaboration.

Key insights

AI can automate code review and vulnerability remediation, freeing developers for more complex tasks.

Principles

• Human oversight remains vital for production code merges.
• Automating repetitive tasks improves developer efficiency.

Method

AI agents can scan code for vulnerabilities and linter errors, then automatically apply fixes, reducing manual review time and security backlogs, especially for distributed teams.

In practice

• Implement AI for automated code formatting.
• Utilize AI for initial vulnerability scanning and fixes.

Topics

• Developer Productivity
• AI Code Review
• Software Security
• AI Agents
• GitHub Platform

Best for: CTO, VP of Engineering/Data, Director of AI/ML, Software Engineer, AI Engineer, DevOps Engineer

Related on AIssential

• Transcript: ‘Can GitHub Be for Everyone?’ — GitHub is evolving its platform and business model to support the explosion of AI-driven development and a broader definition of "developer".
• Writing Code with Github Copilot and ChatGPT Together — III — AI code agents excel at routine tasks but require human oversight for novel or complex problems.
• Before You Hit Push, Review Your Own Code — Proactive self-review, augmented by AI, elevates engineering quality and team collaboration.
• 7 Best AI Code Review Tools — AI code review tools automate error detection, suggest fixes, and enhance code quality across various development workflows.
• Code Is Not Cheap: How to Multiply Your AI’s Output With Software Fundamentals — AI-assisted coding, while prevalent, demands human engineering expertise to mitigate quality issues from "jagged" model outputs.
• How Ramp engineers accelerate code review with Codex — AI tools like Codex can profoundly enhance developer productivity and code quality by automating complex tasks.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by No Priors: AI, Machine Learning, Tech, & Startups.