OpinionProvider guide

Don't build multi-agents: share full context and keep decisions in one thread

An essay from Cognition, which makes Devin, argues that agents splitting a task among parallel subagents were fragile in 2025, and sets out two principles of context engineering instead.

From
Provider guide: published by Cognition on its own site, cognition.ai.
Published
, by Cognition
Checked
, against the source

Documented

What the piece reports as fact.

  • As of June 2025, Claude Code started subtask agents but never ran them in parallel with the main agent, and mostly asked them to answer a question rather than write code.
  • In 2024 many coding tools, Devin included, used an edit apply model: a large model described an edit in markdown and a small model rewrote the whole file. The essay says one model now usually decides and applies the edit.
  • Cognition has fine-tuned a smaller model to compress an agent's history of actions and conversation into its key details, events and decisions.
  • OpenAI's Swarm and Microsoft's AutoGen libraries promote multi-agent architectures.

Interpretation

Cognition's argument, in its own terms.

  • Context engineering is the most important job of engineers building AI agents.
  • Principle 1: share context, and share full agent traces, not just individual messages.
  • Principle 2: actions carry implicit decisions, and conflicting decisions carry bad results. Rule out by default any architecture that breaks either principle.
  • A single-threaded linear agent gets you very far. In 2025, running several agents in collaboration only results in fragile systems.

Dossiers

  • Devinthis guide's dossier

Next read

Related story

Cognition launches Devin Bots for outcome‑focused engineering work