Measuring a group's collective intelligence through interventions requires selecting an aspect of their performance and observing their response. However, this can be challenging for large groups. For instance, a comprehensive intervention like starting a competing organization or offering substantial discounts to assess an organization's intelligence has limitations due to its scale. Smaller interventions, such as using "mystery shoppers" to evaluate customer service, are effective for assessing specialized intelligence. If these interactions involve diverse tasks, they can partially measure the organization's collective general intelligence. For example, by having a variety of mystery shoppers contact smartphone vendors' customer-service lines with different issues, one can assess collective intelligence across problem types. Discovering a common factor that predicts performance across these scenarios, as seen in small working groups, is an intriguing possibility.