Built, launched and handed over an AI innovation assistant

The situation

Amplify runs an innovation management systems program. Participants work through a structured innovation practice. Along the way, they tend to ask the same kinds of questions, about how the program’s frameworks and steps apply to their own situation and what to do next. To answer those questions well, an assistant has to draw on the program’s own material, and it has to run at a cost that makes sense for the business.

What we did

The engagement ran from design through to live operation.

• Designed the solution: what the assistant needed to do and what it needed to refuse to do, scoped against the program content and participant questions.
• Built it on Voiceflow, chosen for conversational design control and operating cost: conversation design, knowledge grounding in the program material, and routing to a human where that is the right answer.
• Set up evaluations that check response quality against a standard, so the team can see whether a change made the answers worse before it goes live.
• Enabled Amplify's own team to run, update and extend the assistant.
• Maintained and improved the assistant during live use, based on the questions participants asked.
• Extended the work into co-creating the AI for Innovation module inside the same program.

What it produced

Ainno is live, and Amplify’s team owns and operates it. It answers from the program’s own material, and the team checks each change against the evaluations before it goes live.