A PERSUASION INTELLIGENCE PLATFORM FOR DEMOCRATIC CAMPAIGNS

See the electorate as it actually is.

Torus interviews voters at scale, models the narratives that move them, and turns a fragmented electorate into a working map — so your campaign can speak to voters in the language they use, on the issues they care about.

750–2,000
Interviews conducted per district
Scalable
Resolution across voter groupings & narrative segments
Per-archetype
Sentiment- & idiom-accurate message recommendations
Real-time
Feedback loop — rapid response rate
The Torus

A continuous loop — investigation, message, deployment, feedback.

Static polling and a quarterly memo aren't the cycle democracy actually runs on. Torus closes the loop — each stage feeds the next, building feedback into iteration.

01

Listen

Conduct 15-30 minute interviews with stratified samples of the target electorate — in voters' own words, not closed-end checkboxes.

02

Learn

Train a campaign-specific narrative model on the transcripts plus environmental context. Surface the latent segments and the language that binds them.

03

Lead

Generate dynamic message recommendations by segment, channel, and moment — ranked by predicted persuasion lift on the voters who matter.

04

Learn again

Field response, ad recall, and follow-up interviews close the loop. The model re-weights as needed — the brief you get in October is not the brief from June.

What you get

Three deliverables, one continuous brief.

Torus replaces the polling memo, the segmentation deck, and the messaging guide with a living workspace your strategy team can count on for integrated data and current action.

The Sentiment Map

A living portrait of the electorate — multiple thematic narrative segments, the language that defines them, and how to approach them.

regularly updated · scalable to state, district, county

The Message Brief

Segment-tuned message recommendations with predicted lift, sample copy, and channel mix — in the language your voters actually use.

 Export to copy doc, ad spec, script

The Feedback Loop

Track how a deployed message lands — in ad recall, in social listening and in the field — and the model re-weights itself before your next buy.

Real-time signal · MODEL updates
Thematic narrative segments

An electorate is not partisan coalitions — it's a kaleidoscope.

Torus identifies the latent narratives voters carry — the stories they tell themselves about the country and their place in it — and surfaces where seemingly disparate voters share belief, priority, and emotional register.

Longitudinal model

A voter is not a data point — they are a trajectory.

A single survey tells you where a voter stands today. Torus follows voters within and across cycles — modeling not just position, but velocity, bearing, and the events that bend the line. The electorate is a system in motion; we treat it as one.

Maria T. — Lucas County, OH · age 54 · registered '04
8 readings · 22 months · 2 inflection events
Maria's trajectory (focus) Cohort peers (Lucas County, n=312) Reading cycle (quarterly)
'24 Q3 READING 01
Hometown Pragmatist
“We just need someone honest. Both parties forgot us a long time ago.”
'25 Q2 READING 03 · POST-LAYOFF
Independent Skeptic
“They shut the plant on a Friday. No one in DC called. So why would I call them?”
'26 Q1 READING 06 · POST-HOSPITAL
Bridge Builder, emerging
“The hospital closing — that's the one. I'm listening to whoever talks about that.”
NOW READING 08 · CURRENT
Bridge Builder, persuadable
“Care close to home — that lands. Tell me how, not just that.”
01 First derivative

Velocity

How fast a voter is moving through narrative space. Rapid shifts mark a persuadability window — the moment to enter the conversation. Slow drift means stable cohort behavior; don't waste the buy.

Δposition ÷ Δcycle
02 Vector direction

Bearing

Two voters in the same segment today can be heading in opposite directions. Bearing forecasts where they'll be next cycle — so the brief reflects who they are becoming, not just who they were.

arctan(Δy / Δx) per voter
03 External signal

Inflection

Events bend the line — a layoff, a school board fight, a hospital closure, a wedge ad. We model both the event and the magnitude of response, so you see causation, not just correlation.

∂narrative ÷ ∂event
The Workspace

A working surface, not a quarterly memo.

Strategists, organizers, and creative teams all live in the same view — segments, messages, lift, and the voter language behind every recommendation.

app.torus.vote / OH-09 / sentiment-map
Sentiment Map — Ohio 9th, Week 32
Refreshed 4h ago · 412 interviews
Persuadable share 27.4% ↑ 2.1 pt / 14d
Top narrative lift +8.7 pt "Honest day's pay"
Active segments 9 2 emerging
Confidence High ↓ vs. week 30
Segment composition · 14 weeks
Stacked share %
W19 W23 W27 W31 W32
Top message recs
Predicted lift
"An honest day's pay." Hits Hometown Pragmatists + Working Faithful. +8.7
"Care close to home." Resonates with Care Coalition on rural hospital cuts. +6.4
"Run for the people you raised." Reaches Bridge Builders — family-frame. +5.1
"Make Washington answer." Anchors Independent Skeptics — accountability frame. +4.6
"Your land, your say." Land-use frame for Quiet Stewards on water policy. +3.9
Methodology

Built on transcripts, not toplines.

Closed-end polling tells you what people will agree to. Torus is built on what they actually say — long-form interviews, contextual data, and a model that treats narrative as the unit of analysis, not the issue.

01

Open-ended, subject-guided interviews

15-30 minute conversations sampled to district-level quotas. We start from voter language, not pollster categories.

02

Campaign-specific narrative model

An LLM trained on transcripts plus environmental data: media diet, regional economy, ballot context. Each campaign gets its own model, not a shared one.

03

Lift simulated, then field-tested

Message candidates are scored against the model, then validated against held-out interviews and in-field ad recall waves before recommendation.

04

Transparent provenance

Every recommendation links to the voter quotes and segment evidence it rests on. Your team can audit the chain back to the human voice.

For 2026, and the cycles after

A campaign that listens first
wins more than once.

Tell us about your race. We'll send a sample sentiment brief and walk you through the workspace.