extending events with Sway

how does Sway extend an event?

Many events invite experts to model constructive disagreement for an audience: debates, panels, and moderated dialogues. Sway extends these events by giving audience members a structured way to practice what they have just watched. It's one thing to observe constructive disagreement; it's another to practice it yourself. Audiences often leave a strong event energized but with nowhere to take the conversation; Sway gives every attendee a next step.

how an event deployment works

Before the event, you choose the discussion topics.
At the close of the event, attendees scan a QR code and register their opinions on those topics; this takes about a minute.
Over the following days, Sway matches attendees who disagree and invites them into one-on-one conversations.
Conversations remain open in the weeks that follow; attendees chat from their phones or laptops, on their own schedules.

Set aside about five minutes in the program for opinion registration, while the audience is still in the room. Project the QR code on screen, explain the invitation, and give attendees a minute to respond on their phones. Experience across events has taught us that once the audience disperses, participation drops sharply—however good the flyer or follow-up email.

Once opinions are registered, Sway handles the logistics: it notifies each attendee when they are matched, helps each pair agree on a time to chat (or to exchange messages asynchronously), and sends reminders as the conversation progresses. You choose the discussion window—a few days, the rest of a themed week, or longer.

Setup is light: you provide the topics; the Sway team configures the event and provides a custom link and QR code to project on screen or print on table cards.

Sway is grant-funded. Attendees can volunteer to participate in IRB-reviewed research on civil discourse.

choosing topic statements

Good event topics are short, declarative statements that split the room and pick up the themes attendees have just watched discussed on stage. For a debate or dialogue on polarization, for example:

"Congress should demographically represent the United States: if the country is 51% women, Congress should be 51% women."
"Disliking the opposing political party is now a bigger problem than our disagreements over policy."
"Most Americans have a reasonably accurate picture of the political views of the opposing party."

Three statements are enough to produce good matches in a large audience. Statements about campus speech and protest are evergreen: students hold real views on them and can engage without technical background. The Sway team is happy to workshop statements with you; see also topics that have worked well on Sway.

what the event report shows

After the discussions conclude, you receive a de-identified event report: behavioral evidence of your event's impact, not just attendance and satisfaction numbers.

Not just what your audience believed, but why: the arguments on each side, the common ground, and the persistent disagreements.
Opinion distributions on every topic, with pre/post shifts for attendees who completed surveys. (Pre/post opinion measurement is already built into the platform; adding it to your event requires no extra setup.)
Where attendees reasoned well and where they struggled, including recurring misconceptions worth addressing.
Ready-to-use follow-ups and topic suggestions for your next event.

Browse real reports →

where Sway has been used

Sway has been used at a range of public events including several MIT Free Speech Alliance debates, events at UNC Chapel Hill's School of Civic Life and Leadership, a Committee for Academic Freedom panel in the UK, and a variety of Australian Dialogues. These include MFSA's Great Climate Debate and its fall 2025 debate at MIT, and public dialogues in Brisbane and Melbourne on tariffs and trade, the energy transition, the China–Australia relationship, and Taiwan.

does it change minds?

Participants are nearly 5x more likely to moderate an extreme view than to harden a moderate one: 56% who entered a conversation at a polar extreme left holding a more moderate view.
The effect holds on the hardest topics: 51.5% moderated even on polarizing issues such as abortion, immigration, and gender.
The share holding extreme positions dropped by 23% after a single 30-minute conversation with a partner who disagreed.

From 10,000+ matched pre/post opinion pairs at 80+ institutions. Learn more about improving speech cultures →

inclusion & fairness

Guide does not offer opinions—it pushes participants to reason more carefully, interrogate their assumptions, and engage seriously with the strongest version of the opposing view.
In a survey of over 3,500 participants, 87% agreed Guide treated both sides with equal respect—and only 3% disagreed.
In an empirical study, over 600 politically diverse Americans evaluated real Sway transcripts across multiple topics and perceived no directional bias—while correctly detecting bias when it was experimentally introduced.

Learn more about bias evaluation →

"Students know that Guide is AI and they find it not at all partisan, not at all biased. That was never an issue."

— Diana Mutz, Samuel A. Stouffer Professor of Political Science & Communication, UPenn; member of the National Academy of Sciences and author of Hearing the Other Side (more from instructors)

privacy

Conversations are encrypted; organizers cannot read identifiable transcripts or view individual attendees' opinions. Personal attacks and mere insults are blocked. Attendee data is never used to train commercial AI models. 92% of participants felt comfortable sharing honest opinions; 93% felt respected by their partner. Read our privacy policy →

next steps

Interested in using Sway at your next event? Book a 20-minute demo to learn more, or download this page as a one-page handout: Sway for Events (PDF).