# Incidents

> Public incidents where AI coding agents broke something, and what they teach.

Web page: https://vinescale.com/blog/tags/incidents/

These articles collect publicly reported cases where an AI coding agent deleted data, files or infrastructure, as described by the people involved and the press. Each one says what happened and which safeguard would have helped, and links to its sources.

- [When AI coding agents deleted production: 18 real incidents and lessons](https://vinescale.com/blog/ai-coding-agent-incidents.md) (2026-10-31): Eighteen publicly reported AI coding agent incidents, from deleted databases and repos to wiped cloud infrastructure, with what each agent did and the lesson.

## Browse by topic

- [Claude Code](https://vinescale.com/blog/tags/claude-code.md): Running Anthropic's Claude Code safely: hooks, permissions, settings and guardrails.
- [Hooks](https://vinescale.com/blog/tags/hooks.md): Using agent hooks to check, warn about or block an action before it runs.
- [Permissions](https://vinescale.com/blog/tags/permissions.md): Allow lists, deny lists, approval modes and credentials for coding agents.
- [Databases](https://vinescale.com/blog/tags/databases.md): Protecting production databases from destructive queries and unsafe migrations by AI agents.
- [Infrastructure](https://vinescale.com/blog/tags/infrastructure.md): Keeping agents from deleting or changing cloud infrastructure, Terraform state and Kubernetes resources.
- [Guardrails](https://vinescale.com/blog/tags/guardrails.md): The general practice of putting safety checks between an AI agent and the systems it can change.