Use cases
Causal experiments answer one shape of question: given a set of options, which features change the decision, and by how much. That shape recurs across domains.
Product and feature design
Which features drive choice, and which are table stakes. A conjoint design prices each feature in units of choice probability, so a roadmap argument becomes a measurement rather than an opinion.
Pricing
Include a price attribute and effects can be expressed as willingness to pay. This gives a defensible answer to "how much is this feature worth to the customer" rather than a guess anchored on cost.
Positioning and messaging
Treat claims and framings as attributes. The experiment measures which positioning moves choice, for whom, and whether a message that works for one segment repels another.
Market structure
With competing profiles specified, simulated market share shows how a change redistributes choice across the set — including cannibalisation of your own options.
Policy and public health
The academic conjoint literature is largely policy work: vaccine acceptance, immigration preferences, transport choice. These are the studies the platform replicates, and the same designs run unchanged.
When not to use it
- When you do not yet know the options. Use qualitative research first; a conjoint design needs attributes to test.
- When the decision is not a choice among alternatives.
- When the answer needs an absolute number rather than a relative effect.
The replication showcase covers specific published studies reproduced on the platform, which is the most direct evidence for a given domain.