What Candor does and how to think about it

Candor helps you decide what to build, ship, and price, using synthetic users grounded in real evidence. Use it for problem discovery, concept testing, value-prop and price testing, and assumption validation on anything from a brand-new idea to a refinement of a live product. The fastest way to use it well is to learn the five things you’ll touch.

The five things

1. Project

A project is the unit of work. One project = one audience you want to understand + one set of personas built for it + the interviews and reports that come from it. You create a project, name it, pick a region, describe the audience, and upload any evidence you already have. Everything else flows from there.

2. Audience

Once your project is set up, Candor researches the audience for you. It reads your uploaded documents, proposes a set of candidate segments, then searches the web for evidence about them, extracting signals as it goes (behaviors, pain points, beliefs, constraints). A critic pass flags weak evidence at the end. You review the segments and decide which ones to include. That selection becomes the foundation for the personas.

3. Personas

Candor generates archetypes (the behavioral shapes that exist in your audience) and then materialises individual personas inside each archetype. Each persona has a personality (sampled from peer-reviewed Big Five distributions), cognitive biases with calibrated intensities, memories, and decision-making patterns. Every trait carries a provenance tag so you can see where it came from.

4. Interviews

Two ways to interview. Live: you type questions, personas respond in real time, and a critic validates each response for consistency before delivery. Auto: Candor runs the interview for you against a guide you configure, with built-in stopping criteria, coverage tracking, and signal extraction. Personas remember everything across sessions within the same project.

5. Reports

An auto-interview run synthesises itself into a report when the last session finishes. It opens with the top learnings, each paired with the next step it implies, then works down through what matters most, the findings, and an evidence appendix. What sits inside the findings is tuned to the kind of interview you ran, so a problem-validation report gives a verdict per hypothesis while a price-testing report gives willingness-to-pay ranges. Every claim links back to source quotes, and you can export the whole thing.

Getting unstuck along the way

Candor Bot sits in the bottom-right corner of every screen in the app. It explains what you’re looking at, interprets a result, and, on the screens where you’re typing, will tell you whether what you’ve written is specific enough before you commit to a run. That last one is worth the habit: the quality of an audience description drives the quality of everything downstream.

How to think about Candor

Candor isn’t a faster way to invent customers. It’s a faster way to test whether what you think you know is supported by evidence. The personas push back. The critic catches drift. The synthesis surfaces tensions you’d miss with a single interview. Use it before you commit, not after.

Where to go next

Common questions

No. Candor isn't an AI persona generator. It's a research platform that builds personas from real evidence (your uploaded research plus targeted web search) and lets you interview them. If you just need a persona slide for a deck, ChatGPT does that for free. If you need to find out whether the audience actually exists, what they care about, and whether your idea lands with them before you commit, that's what Candor is for. The output is decision-grade signal, not a stock photo with a name and a job title.

Most studies run in 1 to 2 hours of elapsed time, with maybe half an hour of your actual attention spread across that window. Audience generation takes 25 to 35 minutes and is queued, so you can close the tab. Personas take another 7 to 12 minutes after you approve segments. An interview guide takes a couple of minutes. Auto-interviews run in parallel and take 25 to 35 minutes. Synthesis adds 3 to 5 minutes once the last interview finishes. The bottleneck is your time spent reading and reviewing, not Candor's processing time.

No, but you'll get sharper personas if you do. Candor can build an audience from a description alone, using web search to find evidence. If you've already done research (PDFs, transcripts, market reports, survey data), uploading it makes the audience tighter, since uploaded documents get weighted higher than web evidence. Even a few well-chosen documents move the audience from generic to specific. Start with what you have and add more later if the audience doesn't feel like yours.

Yes. A project is one audience plus its personas plus everything that's been interviewed inside it. You can run problem discovery first, then concept testing on the same personas a week later. They remember the prior conversation, so the second study builds on what they already told you. That's actually the workflow most teams converge on: open-ended discovery to find what matters, then targeted concept or price testing to pressure-test ideas against it.

ChatGPT will happily roleplay any persona you describe, but it has no evidence behind the character. The persona agrees with whatever you push on. Candor personas are built from real research, carry provenance tags on every trait, hold positions, disagree with each other, and get checked by a critic agent before each response is delivered. The output is something you can audit and trust enough to make a real decision. You won't get that from a roleplay prompt.

More FAQs →

Candor is in development.

Be the first to know when it launches.

No spam. Just a note when Candor is ready. Powered by Highline Beta.