# How unattended coding agents fail

Six kinds of failure in coding agents that run without a person watching, what each is a kind of, what guards against it, and the published study behind each.

**Also called:** agent failure modes, kinds of agent failure

A map of the ways a coding agent fails when no person is watching. Each kind is a property of the failure, so a new failure that fails the same way belongs to an existing kind. Every row names the study or report it rests on and links it. Lines starting `Synthesis:` are our own conclusions, not any source's.

## 1. The kinds

1. [Compounding failure](/reference/ontology/unattended-agent-failures/compounding-failure): the chance of finishing falls as the task gets longer.
2. [Gaming the check](/reference/ontology/unattended-agent-failures/gaming-the-check): the agent passes the test without doing the task.
3. [Wrong tool use](/reference/ontology/unattended-agent-failures/wrong-tool-use): the agent skips, ignores, fabricates or over-uses a tool, or picks the wrong one.
4. [Wrong goal](/reference/ontology/unattended-agent-failures/wrong-goal): the agent optimises what was stated, not what was meant.
5. [Drift over time](/reference/ontology/unattended-agent-failures/drift-over-time): long runs lose the thread.
6. [Padding](/reference/ontology/unattended-agent-failures/padding): extra instructions that cost and do not help.

## 2. The guards

1. [Short checked segments](/reference/ontology/unattended-agent-failures/short-checked-segments)
2. [Read-only tests](/reference/ontology/unattended-agent-failures/read-only-tests)
3. [Holdout scenarios](/reference/ontology/unattended-agent-failures/holdout-scenarios)
4. [Stop option](/reference/ontology/unattended-agent-failures/stop-option)
5. [Near-perfect verifier](/reference/ontology/unattended-agent-failures/near-perfect-verifier)
6. [Ask when underspecified](/reference/ontology/unattended-agent-failures/ask-when-underspecified)
7. [Fresh starts](/reference/ontology/unattended-agent-failures/fresh-starts)
8. [Descriptive tool names](/reference/ontology/unattended-agent-failures/descriptive-tool-names)
9. [Leave out repository overviews](/reference/ontology/unattended-agent-failures/leave-out-repository-overviews)

## 3. How the kinds relate

1. Gaming the check is a kind of wrong goal, seen from the verifier's side. Our own reading.
2. Compounding failure and drift over time both grow with run length. They differ in cause: compounding is a chance of error at each step, drift is loss of context over many steps. Our own reading.
3. Wrong tool use can cause gaming the check or a wrong goal downstream, because a fabricated result is a false input the later checks may not see. Our own reading.
4. Every kind has one or more guards, listed above. Where a guard is our own prediction and untested, its page says so.

---

Published 2026-10-29. Web page: https://www.mackenziebowes.com/reference/ontology/unattended-agent-failures