It listens. It judges.
Set your phone on the table and hit listen. It hears both sides, tracks the flow, and hands you a real ballot when the round ends: who won, why, and speaker points per side.
- 1 Hit listen. Debate the round.
- 2 Hit stop when it's over.
- 3 Read the ballot.
Round details optional. It works these out from the round itself.
Reason for decision
Pro feedback
Con feedback
Built for the lay-judge gap
Public Forum runs on parent judges who never flowed a round in their life. You can give the cleanest summary of the year and still drop the ballot because the judge voted on who sounded more confident. This gives you an objective second opinion: a ballot that engages the arguments, walks the weighing, and names the clash that decided the round.
Names the clashes
The RFD identifies the two or three key clashes by name, says who won each and why, and flags the arguments that got dropped. Drops decide rounds.
Speaker points per side
Both speakers get a score on the format's real scale, calibrated honestly. No clustering everyone at 28 to be polite.
Format-aware
It judges through the lens of your format: PF summary-to-final-focus rules, LD framework, Policy collapse, APDA tight calls. Not generic feedback.
How it works
One. Hit listen and set the phone down where it can hear both sides. It transcribes the round as it goes. Two. Hit stop when the round ends. It weighs the clashes the way a tournament judge does. Three. You get a winner, speaker points per side, a reason-for-decision, and one concrete fix per speaker. You never have to type the motion or pick the format: it works those out from the round. If you would rather not record, you can paste a transcript instead.
AI debate judge FAQ
Is there an AI that can judge a debate round?
Yes. Hit listen and it hears the round through your device's microphone, then returns a tournament-grade ballot: winner, speaker points per side, and a reason-for-decision that names the key clashes and walks the weighing. It judges through your format's adjudication norms, not generic feedback. You can also paste a transcript if you already have one.
Does this work for Public Forum?
Public Forum is the default format and the case this page was built for. PF runs on lay parent judges who don't flow, so an objective ballot that tracks the summary-to-final-focus chain and the first-versus-second-speaker rules is exactly the gap. LD, Policy, Congress, APDA, BP, Worlds, Asian Parliamentary, and a Quick Clash mode are all supported too.
How accurate is the AI ballot?
It runs the same adjudication engine as our live rounds: format-pinned judging rules, explicit weighing across magnitude, probability, timeframe, and reversibility, and a speaker-point scale calibrated to use the full range. Treat it as a sharp second opinion, not a replacement for a real tournament panel. It catches drops and weighing gaps that a lay judge misses.
Where should I put the phone?
Somewhere it can hear both sides. A table between the two speakers works; so does a laptop at the front of the room. It handles normal debate delivery, including fast speaking, but it cannot judge what it cannot hear, so keep it off the far side of a large room and away from an air vent. It shows you the words as it picks them up, so you can tell within a few seconds whether it is hearing the round.
Do I have to fill anything in?
No. The motion, the format, and who is on which side all get worked out from the round itself. Fill in the optional details only if you want the motion quoted word for word, or want to pin the format rather than let it infer one.
Does it replace a tournament judge?
No. It gives you an objective ballot when you don't have a flowing judge in the room, and a second read after a round you think you got robbed in. The point is to fill the lay-judge gap, not to stand in for a real panel.
Is it free?
Yes, while Debatable is in beta every tier is $0. Anonymous visitors get a handful of rounds; signing in with Google adds more. The post-beta plans on /pricing are reference only.
The lens, not just the format
A judge decides through a paradigm. The AI judge adopts the one your format expects and names it in the ballot. Tap one to see how it decides.
Tabula rasa
No preconceptions. Whatever framework you set up and win, the judge adopts. The flow decides.
Most paradigms sit between "the flow decides" and "the better idea decides." The ballot tells you where it landed. In a spar or live round, both debaters can agree the paradigm before the first speech.