What actually breaks when you run LLM agents unattended for 58 days

We run an organization made of agents. Not a demo — a company's back office. Bookkeeping,

inbox triage, drafting, review, research. 78 agents, local models, no human in the loop

between the schedule firing and the output landing in a ledger.

For 58 days we recorded every failure. Not "the run errored" — what was wrong with the

answer. 6768 records, published as a dataset.