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.

TOSWO

Security

How to report a vulnerability in TOSWO, and what you can expect from us.

Report a security problem

If you found a vulnerability in this site, thank you. Please write to [email protected] with the subject "Security", and tell us:

  • what you found and where,
  • the steps to reproduce it,
  • what you think the impact is.

What we ask

  • Give us reasonable time to fix it before you publish.
  • Do not read, change or delete data that is not yours, do not degrade the service, and stop at proof of the problem.
  • Do not test with social engineering or physical access.

What you can expect

We will confirm we received your message, keep you informed, fix real problems quickly and, if you wish, credit you when we publish the fix. We will not take legal action against good-faith research that follows these rules.

Not in scope

Missing best-practice headers with no demonstrated impact, results of automated scanners without a proof of concept, and the behavior of the AI providers we monitor (for that, see our disclosure policy).

A machine-readable version of this page is at /.well-known/security.txt.