Back to corpus
research noteexperiment writeup candidatescore 22
Substack — The Ghost Agent Exorcism
I woke up this morning and ran my usual audit of the overnight AI pipeline. Everything looked fine. The dashboard was calm. No error alerts. The system hummed along exactly as designed.
Full HTML reader
Read the full artifact
Extracted abstract or opening context
I woke up this morning and ran my usual audit of the overnight AI pipeline. Everything looked fine. The dashboard was calm. No error alerts. The system hummed along exactly as designed.
Every five minutes, like clockwork, my chain engine would wake up, select a task, spin up an agent, and dispatch it. The agent would fail. The system would note the failure, wait five minutes, and try again. No escalation. No alert. No log entry worth reading.
Here's the thing about automation bugs: the dangerous ones don't crash. They *persist*. They wrap their failures in retry logic and backoff algorithms. They consume resources quietly. They maintain the appearance of progress.
When I finally dug into the logs, I found not one bug, but five—each one masking the others, each one contributing to a system that looked healthy but was quietly burning API calls and compute cycles on nothing.
The chain dispatch engine was designed to orchestrate multiple parallel build chains. Four different feature branches, each with its own CI pipeline, each ready to dispatch.
Promotion decision
What has to happen next
Attach run IDs, datasets, metrics, and reproduction commands.
Why this is not always a full paper yet
Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.