What we're measuring
What the agents do
The same booking scenarios, run through Muse and Instinct again and again from test accounts. Where each one routes the booking, which merchant it lands on, where it fails.
How people use them
A survey of current users on how they use the agent, when they take over from it, and why.
The moment they take over
Live sessions with current users: what they ask for, and the exact moment they decide to take the booking back.

