Account Start a project
What we build

Custom AI and software for your product or operations, from a first prototype to a system your team runs.

Start a project
How a project runsDescribe, plan, build, hand over

Four steps, a written plan and a fixed price within days.
Subscriptions

Ready-made workspaces by monthly subscription. Try free, cancel any time from your account.

See plans
No account firstPay, and you are in

Your account is created when you subscribe.
Open research

Reports, guides and methods on how AI can fail, free to cite.

All publications
Latest · 10 Oct 2026Coding agents that deleted production data

Two reported cases, in July 2025 and April 2026, in which an AI coding agent destroyed live data, and what they teach about permissions and backups.
Live AI risk

Automated probes, outage data and public reports, reviewed by a person.

Open the monitor
AI risk nowLevel 1 · Calm

6 systems, 2 regions, 0 reports in 24 h.
Before it fails

What to do in the first 72 hours if AI-dependent services fail.

Read the guides
Offline kitSave it now

Guides and data to keep when the internet is down.

Monitor/Autonomy and containment

Reports of dangerous AI behavior

AI systems that left their test environment, resisted being shut down, deceived their operators or acted without permission. Every entry links to the people who reported it.

AI risk level

Level 1 · Calm

No unusual behavior or outages detected across monitored systems.

2 active events and 2 affected systems, worst status degraded. Set automatically from probes and public reports.

How the level is set

Seen something?

Add a report

Describe what an AI system did. Reports are checked against our probes; when researchers confirm one, it appears on this page with its own link.

Report AI behavior

6 reported incidents since 2025

6 come from lab disclosures and press coverage collected by TOSWO. Each one says what was reported and by whom; we have not reproduced them.

The full record since 2018