I don't have time to build these things, will you?

2026-06-22 · Source: Theo - t3․gg · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Advanced, extended

Summary

The author presents five ambitious software development ideas, arguing that AI agent capabilities now make these foundational projects viable. Key proposals include a "better NPM" addressing security, publishing, and package visibility, alongside a "reimagined NPX" offering enhanced security context for agent execution. The article advocates for "reinventing source control" to overcome Git's limitations regarding private files, granular permissions, and inefficient file system interactions, citing APFS performance issues. A "new mobile platform" is envisioned to counter restrictive app store policies and poor developer experiences, promoting an open, customizable OS that supports Android apps while fostering native development. A "better chat app" is also proposed to improve team collaboration beyond Slack's limitations, suggesting a "posts" primitive for superior context management and agent integration. Finally, the author calls for more diverse benchmarks to measure AI model capabilities in niche domains, incentivizing targeted improvements.

Key takeaway

For software engineers and entrepreneurs seeking impactful projects, consider challenging existing software paradigms. Your AI agent capabilities now make ambitious undertakings like rebuilding NPM, reinventing Git, or creating a new mobile OS more feasible. Focus on solving fundamental problems in security, permissions, and developer experience. You should utilize these new tools to experiment and build bigger solutions, pushing the boundaries of what's currently possible in core infrastructure.

Key insights

AI agents enable tackling ambitious, foundational software problems previously deemed too complex or expensive.

Principles

• Existing software infrastructure has critical, solvable flaws.
• Granular permissions are essential for secure, flexible systems.
• Open, customizable platforms foster innovation and development.

In practice

• Implement package manager with security audits.
• Design source control for granular file/branch permissions.
• Develop mobile OS fostering open, customizable app development.

Topics

• Package Management
• Source Control Systems
• Mobile Platforms
• AI Agents
• Software Benchmarking
• Developer Tools

Best for: Software Engineer, AI Engineer, Entrepreneur

Related on AIssential

• Mitchell Hashimoto’s new way of writing code — AI agents are transforming software development workflows and challenging traditional open source and version control paradigms.
• It’s time to go bigger — AI's impact on software development mirrors the cloud's, enabling broad, functional "horizontal plays" over deep vertical specialization.
• What Developers Actually Need to Know Right Now — AI's true frontier lies in orchestrating agents to solve real problems with control and traceability.
• I Stopped Coding for 30 Days — AI Agents Built Everything Instead — AI agents can autonomously handle a broad spectrum of software engineering tasks, fundamentally altering development paradigms.
• Why Agents are Driving Software Development to the Cloud — AI coding agents are shifting to cloud-native platforms, fundamentally changing software development and application paradigms.
• Presentation: Directing a Swarm of Agents for Fun and Profit — Orchestrating AI agent swarms enables rapid, cost-effective, and lower-carbon software development, shifting focus to platform engineering.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Theo - t3․gg.