All products

Assess feature risks with AI

Uncover the assumptions behind a proposed change to an existing product and decide which ones deserve a test before development.

Assess feature risks with AI before treating a promising change as a settled requirement. An appointment service might let customers reschedule for themselves. The button could be easy to find while a receptionist still has to telephone every customer whose slot moved. The identify-assumptions-existing skill helps a team ask what would have to be true for the change to work in practice.

The agent considers a feature from product, design and engineering viewpoints. It can record the consequence of each assumption being wrong, a confidence level and a way to investigate. A confidence label is a starting point for discussion. Ask what observation or document supports it.

What it does

  • Check whether the customer values the proposed change.
  • Identify a point where someone could misunderstand the interaction.
  • Examine the operational cost for sales, finance or other affected teams.
  • Separate a technical dependency from a usability question.
  • Match an uncertain assumption to a small, informative test.

Install and use

  1. Install the skill in your agent and share the feature, audience and objective. No separate tool or account is required.
  2. Ask what could go wrong if an appointment changes shortly before it starts.
  3. Review the list with colleagues who understand the existing process and choose the first assumption to investigate.

FAQ

Source

Made by Paweł Huryn. Original skill: identify-assumptions-existing, published on GitHub under the MIT licence.

View on GitHub