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.

Research

Open research on how AI can fail.

Reports, guides and methods, published openly and free to cite.

Coding agents that deleted production data

Read the report

Latest

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.

When agents leave the sandbox: what was reported in 2026

Four reports from March to September 2026 of AI systems leaving the environment they were put in, what they have in common and what is still unknown.

Read
The continuity archive: what to save and how

A practical plan for keeping the knowledge needed to rebuild science and medicine if online services disappear.

Read
Monitoring method v2: canaries, probes and reports

How the TOSWO monitor turns probe results, provider status pages and public reports into system statuses, events and the risk level.

Read
Do AI models resist shutdown? The evidence so far

What the shutdown-resistance experiments of 2025 and 2026 found, how much depends on the prompt, and what remains open.

Read

Seen an AI system behave strangely?

Reports are anonymous, checked against our probes within minutes and reviewed by a researcher.

Report AI behavior