How audience generation works

The pipeline at a glance

Audience generation is one background job that runs through around twenty steps in sequence. The setup wizard tells you the typical duration when you submit (around 25-35 minutes for most projects). The progress screen shows which step is running and updates in real time. You can close the tab.

One thing to understand up front, because it explains most of what follows: Candor proposes the segments early and then goes looking for evidence about them. It does not gather everything first and sort it into groups at the end. That ordering is why your audience description carries so much weight. It is the input to the first real decision the pipeline makes.

Reading what you gave it

If you uploaded research documents, Candor waits until they’re parsed and embedded before starting. This is fast (under a minute per document) but bigger files take longer. If a document fails to parse, you’ll see a warning and the pipeline continues without it.

It then normalises your setup inputs into a working audience description and pulls the relevant evidence out of your documents. Anything you uploaded is weighted more heavily than anything found on the web, throughout the run.

Proposing the segments

Candor now proposes a set of candidate segments, grouped by behavioural and psychographic dimensions rather than demographics alone. Each one gets a primary differentiating dimension: the criterion that explains why people in this segment make different choices from everyone else.

A validation step immediately checks those proposals. If they don’t hold up, the pipeline regenerates them rather than continuing with a weak set, and you’ll see a retry step on the progress screen. That is the pipeline working, not failing.

Planning and running the search

With segments in hand, Candor plans what evidence it needs and then runs the main search pass on the web. Queries are region-aware, tuned to the region you pinned during setup.

Every source, whether a web page or a chunk of a document you uploaded, is read and broken into discrete signals: behaviours, pain points, beliefs, constraints, goals, preferences, and decision rules. Each signal is tagged with type, sentiment, intensity, and a link back to the source it came from.

Three passes that deliberately look elsewhere

A search steered only by your audience description finds the obvious, engaged, complaining middle of an audience. Three extra passes exist to correct for that, and they are a large part of why the personas come out varied rather than interchangeable.

• What’s working, not just what hurts. A dedicated pass for satisfaction, identity, motivation, and how people sustain themselves in the role. Without it an audience reads as nothing but problems, which is both inaccurate and unhelpful.
• The disengaged tail. A pass targeting the low-involvement members: habitual, sceptical, convenience-first, not particularly interested. Candor guarantees your personas span the full personality range, so it has to go find evidence for the people at the quiet end rather than inventing them.
• Per-segment targeting. Searches aimed at specific proposed segments that the general pass under-served.

Filling gaps and rebalancing

Candor now audits what it has and identifies gaps: signal types that are under-represented, claims lacking supporting evidence, or segments that still aren’t well covered. It runs targeted searches to fill those gaps, one query at a time, until the audience is balanced or the search budget is spent. A rebalancing step then corrects a signal mix that skewed too far toward one type.

Dimensions and calibration

With the evidence settled, Candor seeds the attribute dimensions that personas will later be built along, and generates calibration hints: the realistic ranges and distributions for this specific audience, so sampled values land where real people land rather than at a generic average. Both steps have their own retry loops if the first attempt doesn’t validate.

The critic and the final check

A separate agent reviews the assembled signal set for weak evidence, contradictions, region drift, and over-reliance on single sources. Issues are surfaced on the audience review screen as a critic banner so you know what to look at. If the review finds fixable problems, the pipeline can loop back and regenerate dimensions or calibration before running a final quality check.

The critic flags, it doesn’t block. You decide whether to proceed, regenerate, or add more evidence.

One thing built on the side

Early in the run, Candor also captures a snapshot of recent developments in your industry and region. It isn’t used to build the audience. It’s stored on the project and injected into interviews later, so personas can refer plausibly to what has been happening in their world instead of sounding frozen in time. You can refresh it from the interview panel when it goes stale.

When something goes wrong

If a stage fails, the pipeline stops and shows a failure banner with a retry button. Common causes are transient web-search errors, rate limits, or evidence too sparse to segment cleanly. Retry usually works for the first two; for the third, broaden your audience description or add more evidence and create a new project.

Where to go next

• Setting up your first project
• Glossary of terms