ReadingResearchRadarInvestment framework
Sign in / Sign up
← Back to reading
News2 min read·2026-10-18DisconfirmAI Editorial

Qodo Engineers Explain Dark Factory: Why Multi-Agent Collaboration Needs a Communication Space Separate from Execution

Qodo AI engineers Dr. Ofir Friedman and Amir Zaushnizer detail the architectural evolution of their internal system, Dark Factory. The article argues that while A2A protocols solve tool reachability, they fail to support multi-participant shared context. By introducing BAND as an interaction layer ('Slack for agents'), Qodo enables SWE, Reviewer, and SRE agents to collaborate in real-time while maintaining deployment independence. The core lesson is separating flexible reasoning (in the room) from deterministic execution (via CLI) to balance efficiency with auditability.

ImportanceMaterialEvidenceE3 inspectableWrite-upQuick

Original publication time 2026-10-06 20:24 GMT+8

When building autonomous software engineering agent teams, a common misconception is that enabling agents to call each other constitutes collaboration. In an article published on October 6, 2026, Dr. Ofir Friedman, Senior AI Engineer at Qodo, and Amir Zaushnizer argue through their internal system, Dark Factory, that this point-to-point delegation model has fundamental flaws. They found that while protocols like A2A allow agents to be discovered and delegated to, they do not describe what happens when multiple participants need to hold a single evolving understanding of the same problem.

Friedman and Zaushnizer explain that true collaboration requires shared conversation, membership, and a common history readable by late-arriving participants. Without a shared collaboration layer, connecting agents across different environments necessitated custom request endpoints, polling mechanisms, and state management. This not only increased integration complexity but, more importantly, failed to create meaningful collaboration—agents were executing tasks rather than sharing an evolving understanding or challenging assumptions.

Sign in / Sign up
ReadingResearchRadarInvestment framework

To address this, Qodo developed BAND, an interaction layer described by the authors as 'Slack for agents.' BAND does not orchestrate agents or replace underlying frameworks but provides persistent identities, chat rooms, and deterministic message routing. In the Dark Factory architecture, the SWE agent responsible for planning and implementation, the independent Reviewer agent, and the SRE agent with access to production logs all operate as distinct participants within the same BAND room. This design allows the SRE agent to contribute production evidence without moving privileged credentials into the SWE environment, while keeping the Reviewer independent from the author.

The article emphasizes a key engineering principle: separating the collaboration layer from engineering mechanics. Agents reason and negotiate flexibly in the room, but actions like changing code, publishing PRs, and recording verdicts must happen through a deterministic CLI. 'Flexible where judgment helps, fixed where consequences are real,' write Friedman and Zaushnizer. This hybrid architecture preserves the emergent capabilities of multi-agent collaboration while ensuring the auditability and security required in production.

Although Dark Factory demonstrates cross-deployment collaboration potential and reports rapid delivery of merge-ready PRs in specific use cases, the authors acknowledge it remains experimental. They note that current results are limited to scoped engineering requests and depend on Qodo's specific internal infrastructure. For broader AI applications, the value of this case lies in revealing the architectural prerequisites for moving from a 'directory of services' to a 'true team': the need for an intermediate layer capable of carrying shared context rather than just passing instructions.

Sources

  • 原始出处qodo.ai↗
Continue researching →