✳flâneur — a map of the web's best reading

Why I'm Betting Against AI Agents in 2025 (Despite Building Them)

utkarshkanwat.com · 1,787 words · saved by 1 readers

I've built 12+ production AI agent systems across development, DevOps, and data operations. Here's why the current hype around autonomous agents is mathematically impossible and what actually works in production. Subscribe to get my latest articles on AI engineering, development tools, and lessons from building production systems. No spam, unsubscribe anytime. I write about AI engineering and development tools. © 2024 Utkarsh Kanwat Building AI systems for the future

Everyone says 2025 is the year of AI agents. The headlines are everywhere: "Autonomous AI will transform work," "Agents are the next frontier," "The future is agentic." Meanwhile, I've spent the last year building many different agent systems that actually work in production. And that's exactly why I'm betting against the current hype. I'm not some AI skeptic writing from the sidelines. Over the past year, I've built more than a dozen production agent systems across the entire software development lifecycle: Development agents : UI generators that create functional React components from natura

Explore this link on the map →

saved by

related reading