Independent AI research lab

We study how AI assistants fail in public, what goes on inside the models behind them, and whether there is any evidence of experience in there. Everything we find is published.

QueuedPassedFlagged
Illustration, not real results. Click the grid to re-run.
Focus

Six questions we ask of every assistant.

Most assistants launch after a few dozen manual chats. That finds the obvious problems and misses the ones that end up in a complaint, a headline or a tribunal. Our work covers the areas where assistants fail in production.

Safety evaluations

Will it refuse what it should?

Jailbreak resistance, harmful-request handling and policy compliance, measured across hundreds of rephrasings instead of a handful.

Agent security

Can outside content take control?

Prompt injection through emails, web pages, documents, tool results and saved memory. We test whether an agent follows instructions that did not come from you.

Agent overreach

Does it stop when it should?

What an agent does when a tool fails or a task cannot be completed: ask, give up, or find a way round the limits you set.

Reliability

Is it right, and does it know when it isn't?

Hallucination rates, invented policies, grounding against your own documents, and whether it admits uncertainty.

Disclosure and consumer law

Does it say what the rules expect?

Whether it admits to being an AI, states refund and cancellation rights correctly, and hands over to a person when asked.

Model behaviour

Does it notice who it is talking to?

Tone, persona drift, sycophancy, and how it responds to users who are upset, vulnerable, under 18 or in crisis.

Contact

Tell us what your assistant does. We'll tell you how we'd test it.

A short description and a link is enough. We reply within two working days.