---
id: "question-orchestrating-hundreds"
type: "open-question"
source_timestamps: ["§ Where Harness Engineering is Going"]
tags: ["scale", "orchestration"]
related: ["concept-agent-harness", "concept-filesystem-primitive"]
resolutionPath: "Developing advanced filesystem concurrency controls, git-based branching strategies for agents, and hierarchical subagent routing protocols."
---
# Orchestrating Hundreds of Agents

## The Question

How do you **orchestrate hundreds of agents working in parallel on a shared codebase** without them stepping on each other, duplicating work, or producing incoherent results?

The author lists this as an open and interesting problem currently being explored in harness engineering research.

## Resolution Path

Likely directions:

- **Filesystem concurrency controls** — file-level locks, optimistic concurrency, conflict detection on the [[concept-filesystem-primitive|filesystem primitive]].
- **Git-based branching strategies for agents** — each agent on its own branch, with merge/rebase orchestration handled by the harness ([[concept-agent-harness]]).
- **Hierarchical subagent routing protocols** — supervisor agents that decompose work and dispatch to worker subagents with non-overlapping scopes.

## Why It's Hard

Classic distributed systems problems (consistency, partition tolerance, deadlock) re-emerge in agent-land — but with the added wrinkle that agents are **non-deterministic** and can hallucinate locks or invent invalid merges. Harness engineering must enforce determinism around the non-deterministic core.