Skip to slide
16 / 41

CH 03 · The Case Against: Cognition's "Don't Build Multi-Agents" · 01/10

Read as one page

The Case Against: Cognition's "Don't Build Multi-Agents"

Cognition argues long-running agents need one unified context to contain compounding errors, since split work across subagents causes conflicting decisions.

10 slides · 6 min read

Contour map for The Case Against: Cognition's "Don't Build Multi-Agents"

In this chapter

  1. 01Why think in principles at all
  2. 02The foundation: context engineering and reliability
  3. 03The fragile architecture, illustrated with Flappy Bird
  4. 04Principle 1: Share context, and share full traces
  5. 05Principle 2: Actions carry implicit decisions
  6. 06What to build instead
  7. 07Real-world examples Yan offers
  8. 08On multi-agent collaboration specifically
  9. 09Key takeaways

This chapter explains Walden Yan's article "Don't Build Multi-Agents," written from Cognition, the team behind the Devin software engineering agent. Where Chapter 2 made the case for multi-agent systems, this article argues that for serious, long-running, reliable agents, you should usually avoid them. The two are not as contradictory as they sound, which Chapter 5 resolves, but first it is worth taking this argument on its own terms, because it is sharp and well reasoned.

Finished this idea?

Your learning progress stays in this browser.