Cast of Thousands

Try it on a thousand people who don’t exist.

Then ship it to the ones who do. Cast of Thousands is building crowds of AI-simulated users and audiences, shaped like yours, to test whatever you’re about to launch.

Try your…

Illustration · invented numbers = one simulated customer

where it brokewhat came throughWe have no product yet. This is the kind of answer we’re building towards.

1,000 simulated customers contact your support agent.

812 get what they came for. The other 188 fail in four distinct ways, each one a fix you can make before a real customer finds it.

Testing AI agents

Every dot is somebody.

A simulated person is more than a prompt that says “act like a customer”. Each one has a goal, a temper, habits and a history, drawn from a description you write or from your own data: transcripts, survey answers, analytics.

Then a thousand of them use your product, read your message or talk to your agent, all at once. The answer is meant to come back in minutes, with every one of them able to say why.

Then the part most simulation skips. We’re building it to compare what the crowd did with what your real users did, so every result comes with how far to trust it.

Call sheet5 of 1,000 · illustrative

No.WhoWantsWhat happened
0031Returning customer, in a hurry, charged twiceA refund without repeating herselfResolved in four turns
0417First-time user, on a phone, on a trainTo book one appointmentQuit at “connect your calendar”
0562Procurement lead, wary of sales callsTo know what leaving would costChose headline B
0788Second-language speaker on a bad lineTo change a delivery addressMisheard twice, hung up
0903Judge who prizes feasibility over polishThe entry most likely to deliverPicked #214 over #187

A crowd of fakes is good at some things and bad at others.

Don’t lean on it for: the exact percentage

12.4: the average miss, in percentage points, when Pew Research Center had AI twins of its own panellists answer nearly 300 survey questions. A simulated poll is not a poll.

The same holds for testing AI agents. A study with 451 real participants found that simulated users are an “easy mode” that inflates agent success: too cooperative, too alike, never properly frustrated.

So we won’t sell you a crowd on trust. Use it to rank options and to find where things break. For anything else, we’ll show you how the simulation compared with reality before you rely on it.

Pick your crowd.

  1. AgentsFor teams shipping chat and voice agentsYour agent’s next thousand conversations, before your customers have them.
  2. ProductFor product, growth and UX teamsWatch a thousand users try your new flow before one real user does.
  3. MessagingFor marketing and comms teamsKnow which message lands before you spend the media budget.
  4. RankingFor anyone judging a pile too large to readHundreds of submissions. A shortlist you can defend.

What would you try on them?

There’s no product to sell you yet. We’re building it with the first people on this list, and what you write here decides what gets built first.

We’ll only write to you about this. Privacy