AN AI-NATIVE MESSAGE INTELLIGENCE PLATFORM

Modern message intelligence.

Torus uses emergent data and large-language-model processing to deliver an entirely new messaging capability and campaign management toolkit — built to replace guesswork with a defensible, district-grounded map of belief.

750–2,500
Interviews conducted per district
Emergent data
Population sampled by broad statistical data, themes surfaced from voters’ own words
Message fidelity
The issues that matter to them, in their words
Priority ranked
Maximize campaign spend by efficient targeting
The Torus

Six stages, one loop — cluster, interview, frame, assign, deploy, listen.

A topline and a quarterly memo aren't the cycle a campaign actually runs on. Each stage of the Torus feeds the next: what voters say reshapes what we produce, and what lands reshapes what we say next.

01

Cluster

Archetype formation. Voters are cut from deep, auditable records on stated dimensions — so anyone can inspect exactly how a voter was grouped.

02

Interview

The district in its own words. AI-driven, open-ended interviews invite voters to raise their own issues and priorities, not march through assumed themes.

03

Frame

LLM decomposition and analysis. Every statement is broken into its components — the problem, who is responsible, what they want done, and how strongly they feel it.

04

Assign

Starting position on the message strategy matrix: how often a voter turns out, by how closely they align with the candidate.

05

Deploy

Media in their language, on their issues — the stacked priorities of an archetype decide what gets said first, and to whom.

06

Listen

Measure, correct, reassign. Response moves voters on the matrix, and the next round of messaging starts from where they actually are.

What you get

Three deliverables, one continuous brief.

Torus doesn’t discard polling — it supplies what a topline can’t: the district’s own structure, in the district’s own words, in a workspace your strategy team can act on today.

The Archetype Map

Who is in the district and how they were grouped — archetypes cut on stated dimensions, each with the stacked priorities that rank what to say first.

Auditable groupings · scalable to state, district, county

Bridge Narratives

The convictions that move disparate archetypes at once — messages built on insight, capable of forming broad coalition, in the language voters actually use.

Export to copy doc, ad spec, script

The Message Strategy Matrix

Every voter on one square — turnout by candidate alignment — so the play is explicit: persuade, wake up, turn out, hold, or leave alone.

Reassigned as response comes in
Emergent data — the foundation

Let the data organize itself.

Emergent data is organized by its own properties rather than categories imposed by the viewer. That distinction matters because bias enters research at the moment of design: the buckets a pollster picks and the themes they write into a questionnaire decide most of what can be found. We let the structure and the themes come out of the data instead, and the findings are both authentic and accurately applied.

Emergent clusters

Archetypes, the map of who

Traditional sampling stratifies on a handful of buckets chosen in advance. Archetype clustering forms on scores of verifiable attributes and finds the groupings that already exist — each one internally coherent, so a few hundred interviews represent the district far more faithfully than quotas ever could.

A sampling frame drawn from real structure
Emergent themes

Stacked identities, the map of belief

Open-ended interviews, not a checklist of assumed themes. Nobody hands the district a set of issues in advance; the themes that matter come out of what voters chose to talk about.

Discovered, not assumed · 750–2,500 interviews per district

“They cut the bus that got my mother to her appointments. The county board did that, and nobody asked us. Put the morning run back and I’ll listen to whoever did it.”

Interview excerpt · senior homeowners

The problem“they cut the bus that got my mother to her appointments” — what they name as wrong
Who is responsible“the county board did that, and nobody asked us” — where they place the blame
What they want done“put the morning run back” — the remedy in their terms
How stronglyhigh — “I’ll listen to whoever did it” — intensity, which decides ranking
Archetypes — BIRCH-Ward clustering

Archetypes are statistically derived, not presumed.

Every voter in the district is matched to a deep record of who they verifiably are — household, housing, work, and place — and BIRCH-Ward clustering groups them from those facts alone. Nobody decides in advance how many groups a district has: the clustering finds the number that actually fits, and every voter’s grouping can be traced back to the facts that produced it.

IDArchetypeRelative sizeVoters
12Established Spring Valley Residents35,070
7Mahopac Families34,398
5New City Families33,266
11Established Mahopac Renters33,138
10Established Spring Valley Singles30,906
8Established New City Renters29,394
6Senior Yorktown Heights Homeowners19,702
4Senior New City Homeowners19,500
1Established Monsey Homeowners18,697
3Established New City Homeowners17,803
0Established Ossining Residents13,540
2Established Carmel Homeowners11,153
9Established Nanuet Singles4,625
k = 13 · read off the silhouette frontier, not chosenNY build · voter_feature_matrix_ny · July 2026
Clustering inputs — who a voter verifiably is
Core demographicsAge, gender, marital status, children in household, primary language — voter-file fields, graph-verified.
Household economicsModeled income, net worth, credit band, open trade lines, donor and investor propensity.
Housing & residenceOwner or renter, dwelling value, years at current address, normalized locality.
Work & educationEmployment and sector, seniority band, employer size, attainment from education history.
The message strategy matrix

Every voter occupies exactly one square.

How often they vote, by how closely they align with the candidate. Position sets the play — and tells the campaign what mix of persuasion and mobilization is worth the spend. No voter is counted twice; none is moved along a generic ladder of touches.

Turnoutlikelihoodfrom REAL vote history
1rejects
2restack
3contested
4reinforce
5base
1rarely
votes
6,479F
16,305F
23,271reserveF
18,835act-reinfD
9,781activateD
2votes
sometimes
3,152F
7,953F
11,620reserveD
9,313act-reinfC
4,819activateC
3most
generals
4,686F
11,515reserveD
16,351reinforceC
13,202act-reinfB
6,754activateA
4nearly
every
5,630reserveF
13,874cross-pressD
19,740reinforceB
16,440reinforceA
8,478mobilizeA
5every
election
13,058reserveF
31,381cross-pressD
45,263cross-pressB
37,871reinforceA
20,508mobilizeA
Turnout likelihood (1–5) × candidate alignment (1–5)Illustrative distribution
Cross-pressureReliable turnout, contested alignment — the message decides the vote.
ActivateAligned but low turnout — the vote exists and isn’t being cast.
MobilizeHigh alignment, reliable history — turnout mechanics, not argument.
ReinforceHold the base squares; don’t spend persuasion budget here.
Act-reinfActivate and reinforce at once, where both are still in play.
ReserveRejects with reliable turnout — contact raises their vote, not yours.
Methodology

Built on transcripts, not toplines.

The core limit of polling is methodological and intrinsic: it imposes demographic buckets and assumed framing before a single response is collected, then reads the results as if they were discovered rather than presupposed. The bias lives in the architecture, not the execution.

01

Archetypes cut before a question is asked

Groupings come from a deep, non-public dataset on stated dimensions — auditable, and never a set of demos the campaign hands us in advance.

02

Open-ended interviews, then decomposition

750–2,500 conversations per district. Each statement is broken into problem, blame, remedy, and intensity — then stacked across an archetype into ranked priorities.

03

Every voter assigned exactly one square

Turnout by candidate alignment. No voter is counted twice, and no one is moved along a generic ladder of touches.

04

Transparent provenance

Every recommendation links to the voter quotes and archetype 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 capability brief and walk you through the method.