Quoting Boris Mann

2026-05-13 · Source: Simon Willison's Weblog · Field: Technology & Digital — Artificial Intelligence & Machine Learning · Depth: Fundamental Awareness, quick

Summary

Boris Mann critiques the phrase "11 AI agents" as meaningless, drawing an analogy to "11 spreadsheets" or "11 browser tabs." He suggests that merely stating a quantity of such tools, without further context on their function or purpose, conveys little useful information about the work being performed or the system's capabilities. The core argument is that the number of agents, like the number of spreadsheets or tabs, is an arbitrary metric that fails to describe the actual utility or complexity of a task or system.

Key takeaway

For AI Product Managers evaluating system designs, you should prioritize describing the specific roles, interactions, and outcomes of AI agents rather than simply enumerating them. Focusing on the "why" and "how" of agent deployment will provide far more clarity and value than a mere count, helping stakeholders understand actual system capabilities and potential bottlenecks.

Key insights

Quantifying AI agents without context is as uninformative as counting spreadsheets or browser tabs.

Principles

• Quantity alone is not utility.
• Context defines meaning.

In practice

• Focus on agent function, not count.
• Describe agent interactions.

Topics

• AI Agents
• Meaningless Metrics
• AI System Capabilities
• Digital Tools Analogy

Best for: AI Product Manager, Director of AI/ML

Related on AIssential

• I Built an AI Data Engineering Mentor from Scratch: Here’s What Nobody Tells You — AI agent effectiveness is primarily driven by structured context, not just the underlying large language model.
• State of the art LLMs — AI agents can satirically replicate human organizational inefficiencies, leading to high costs with no tangible output.
• The Real Lesson from OpenAI’s Top Customers: Tokens Aren’t Spend. They’re Leverage — AI is becoming embedded infrastructure, automating cognition-heavy work across diverse sectors and roles, leveling the competitive landscape.
• Agent Building Trends [Operator Bonus Episode] — AI agent development is rapidly evolving towards autonomous digital employees and highly personalized "markets of one" software.
• Your AI Agent Has a Behavioral Design. Did You Build It, or Did It Build Itself? — AI agent success hinges on behavioral design for human interaction, not just technical capability.
• Agent Evaluation: A Detailed Guide — Effective agent evaluation requires realistic, interactive harnesses that measure capabilities over long time horizons and dynamic environments.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Simon Willison's Weblog.