The Candor
Platform

Describe what you want to learn. Candor recruits participants, generates the right interface, prevents bias, and delivers results — so you can focus on building.

The Infrastructure

Built into every study

🔀

Randomized ordering

Tasks and display positions are shuffled per participant to prevent position bias. Pairwise items are counterbalanced 50/50 AB/BA.

📦

Smart batching

Tasks grouped into right-sized assignments: 5 for comparisons, 10 for ratings, 20 for labeling. Prevents fatigue.

💰

Auto-calculated pricing

Rewards estimated from media type + task complexity, targeting $12–18/hr. Audio comparisons priced higher.

🛡️

Attention checks

10% of tasks are known-answer pairs. Participants who fail are excluded. Only engaged evaluator data reaches results.

📊

Agreement metrics

Krippendorff’s alpha for inter-rater reliability. Per-pair disagreement breakdowns. Know when you have signal.

Task Archetypes

Five participant experiences

vs

Pairwise Comparison

All N*(N-1)/2 pairs generated. Display order counterbalanced. Produces ranked leaderboards with win rates.

Learn more →

Rating Scale

Independent item evaluation on numeric scales. Per-item means, medians, and standard deviations.

Learn more →

Categorization

Custom label taxonomies. Label distributions and confidence scores per item. Inter-annotator agreement included.

Learn more →

Free Text

Open-ended descriptions, transcriptions, and reviews. Each reviewer writes independently.

Learn more →
AI Interview

AI-Moderated Voice Interview

Participants browse your product while an AI voice moderator asks questions. The moderator never asks leading questions, never collects PII, and adapts follow-ups in real time. Custom interview guides shape the conversation.

Explore methodology →
app.candor.ai/session_x92j
AI Moderator
“Tell me more about how you found that button...”
“It was a bit hidden behind the...”
Adaptive Intelligence

Four levels of AI moderation

Every task type can be combined with an AI moderator. Choose the right scope for your research — from hands-off structured tasks to a study-level moderator that learns across sessions.

See scope × task type matrix →

Ready to create your first study?

Install the CLI and launch a study in under two minutes.

Get started