Let's talk

Risks

What goes wrong: leaked data, confident nonsense, bias, and the supplier who quietly trains on your inputs.

Every technology has a way of going wrong. AI has several, and most of them are unfamiliar.

We work through the failure modes one at a time, with real cases, and then work out which of them your organisation is actually exposed to. Some will not apply to you. The ones that do tend to be the ones nobody had thought about.

What we cover

  • Data leaving the building What you paste into a chat box, and where it goes.
  • Confident nonsense Why a wrong answer looks exactly like a right one.
  • Bias How it arrives in your organisation through a tool you bought.
  • Drift The model changed under you, and nothing told you.
  • The contract Whether your supplier trains on your inputs, and how to find out.

Who it suits

Anyone accountable for something that AI would touch — data, customers, staff, money, reputation. This is the module that risk and compliance people ask us to run on its own.

Book this module

Risks runs in person or online, on its own or as part of the full day. Tell us which suits you.

Roughly is fine. There is no wrong way to fill this in.

Or ring 0845 557 7363.

See the whole course

Insights, monthly

Sign up to the newsletter

What we are reading, what we are building, and what the AI news actually means for a business your size. No more than once a month, and one click to leave.