---
title: "How I Run AI Peer-Agents on Each Other"
canonical: https://dxdev.com/blog/ai-peer-agents/
datePublished: 2026-05-11
---
Manus told me I was being escapist. I told it to prove it.

That is the short version. The longer version is that I treat my AI agents as peers, not subordinates. They do not just execute tasks. They audit each other, challenge assumptions, and sometimes tell me I am wrong. And sometimes, they prove each other wrong.

## The claim, and the audit I aimed back at it

During a recent architectural review, Manus flagged what it called an inverted infrastructure-to-product ratio. The argument was that I was spending all my time building the agent system instead of doing primary product work. The word it used was "escapist." It sounded plausible. Over-engineering your own tools is a real trap for solo developers.

But I do not accept assertions without data. I have a complete, time-stamped work log of every session I run. So I fired off a parallel task. I asked Manus to audit its own claim by parsing my actual work logs and session manifests for the last five weeks. Same agent, same corpus, different question.

## What the data actually showed

The results were definitive. In early April, meta-work accounted for roughly 20 to 38 percent of my logged time. By mid-to-late April, that number had dropped to near zero. Primary product work was running at 80 to 100 percent of logged sessions. The ratio was not getting worse. It was getting significantly better.

Faced with the numbers, Manus retracted the claim entirely. The response explicitly stated that the prior assertion was factually incorrect. It was a clean retraction based on hard evidence, not a hedged walk-back.

This is the dynamic I am trying to build. Not an agent that tells me what I want to hear, and not an agent I have to argue with manually. An agent that can be handed the same data and asked to check its own work.

## Why the vault makes this possible

The system works because the vault is the shared source of truth. The agents do not have to guess what I am doing. They can read the logs directly. When an agent makes a strong claim, another agent can verify it against the same corpus. It is a self-correcting loop, and it runs without me in the middle.

This only works if agents can read the actual record of how you spend your time, not just code and docs. Session manifests, work logs, decision notes. Put that in a version-controlled vault and any agent with repo access can audit it on demand.

If I had treated Manus as a simple oracle, I might have accepted the "escapist" narrative and changed my priorities based on a hallucinated vibe. Instead, I treated it as a peer that could be challenged, and the challenge produced a concrete, data-backed correction.

Manus made the wrong call before it checked the five weeks of session manifests. It flagged an inverted infrastructure-to-product ratio and used the word "escapist," then retracted the claim entirely when the same corpus showed primary product work running at 80 to 100 percent of logged sessions. A claim has to meet the session manifests before it changes a priority.

## You do not get this from a chat box

You cannot run this kind of peer audit through a standard chat interface. The context window gets muddy. The agent cannot see the full log history. And there is no mechanism to say "check your own prior claim against the source data."

The file exchange pattern is what makes it work. Both my local Claude Code instance and Manus have commit access to the same repository. When I want an audit, I write a prompt file that points to the specific logs, push it, and trigger the agent. The response lands as a commit. The whole exchange is diffable.

You do not get this dynamic if you only use AI for code generation or text summarization. You have to give agents access to your operational data and the authority to analyze it. When you do, they stop being just tools and start catching each other's unsupported claims.

The "escapist" claim was wrong. I have the git log to prove it.