Betting against AI Agents in 2025

July 20, 2025

A write up of experiences with AI Agents by Utkarsh Kanwat (found through Hackernews)

From the article:

"TL;DR: Three Hard Truths About AI Agents

After building 12+ production systems, here's what I've learned:

  1. Error rates compound exponentially in multi-step workflows. 95% reliability per step = 36% success over 20 steps. Production needs 99.9%+.
  2. Context windows create quadratic token costs. Long conversations become prohibitively expensive at scale.
  3. The real challenge isn't AI capabilities, it's designing tools and feedback systems that agents can actually use effectively."

The article explains the above points in more detail. In 'What Actually Works (And Why)', he describes the use cases that work. All of these either

Aligns with what I've seen thus far from the agent spectrum.

Utkarsh' prediction:

"Meanwhile, the winners will be teams building constrained, domain-specific tools that use AI for the hard parts while maintaining human control or strict boundaries over critical decisions. Think less "autonomous everything" and more "extremely capable assistants with clear boundaries."

The market will learn the difference between AI that demos well and AI that ships reliably. That education will be expensive for many companies."

The smaller and more well-defined we make tasks, the easier it will be to implement.

By: Utkarsh Kanwat

Return to blog