The Pattern is an automated daily intelligence brief. This page explains how signals are generated, what counts as a prediction hit, and why we publish misses as publicly as wins.
Every day, an automated pipeline ingests articles from 151 curated feeds across fashion, brand, design, culture, entertainment, tech, and lifestyle. The pipeline runs at 06:00, 14:00, and 22:00 UTC.
What the AI does and doesn't do: The AI synthesises and interprets. Every signal is grounded in a real article from a real source — URLs are published with each signal. The AI adds the layer of "so what." It does not invent stories or sources.
Every edition includes one prediction. Predictions are scored against strict criteria. There are no soft calls.
Binary outcome only. A prediction is either correct or wrong. No partial credit, no "directionally right." If the specific claim didn't happen by the deadline, it's a miss.
Named entity required. Every prediction must name a specific company, person, product, or platform. "A major brand will..." is not a valid prediction — it can't be falsified. "Nike will announce..." can.
Hard deadline required. Every prediction includes a specific timeframe: "by June 2026", "within 2 weeks", "end of Q3." Predictions without a deadline are not scored.
Third-party verification required. A hit requires a credible external source confirming the outcome — news coverage, official announcement, or verified data. Self-reported confirmations don't count.
Expired means wrong. If a prediction's deadline passes without resolution, it is automatically marked expired and scored as a miss. Pending predictions are never held indefinitely.
These rules exist to prevent the most common prediction failure mode: vague calls that can be retrospectively claimed as right. We'd rather be wrong and specific than right and useless.
Each prediction includes a confidence score from 1 to 10. This is the model's subjective probability estimate at time of writing, not a retrospective rating.
Signals carry a lead time estimate: the number of days before this story is expected to reach mainstream business or trade press coverage.
Lead time is estimated based on the source tier of the originating article. Primary sources — specialist journals, niche trade reports, early industry data — carry longer lead estimates than secondary sources already in major trade press. A signal from a specialist publication not yet in mainstream business media might carry a 14–21 day estimate. A story already in trade press might carry 3–7 days.
These are estimates, not measurements. The figures reflect the estimated gap between source tier and mainstream coverage, based on typical diffusion patterns for that story type. We're transparent about this distinction.
It must reveal a shift, not a state. "Luxury is popular" is a state. "Luxury brands are hiring game designers as creative directors" is a shift. Signals describe direction, not position.
Category diversity is enforced. No two signals in the same edition may share a category. This prevents any one sector dominating the brief — culture is cross-sector by definition.
No repeats within 48 hours. If a subject appeared in a signal yesterday or the day before, it is excluded today. The brief should teach you something new every day.
Tech product launches are lowest priority. A new model, feature, or funding round is not a cultural signal unless it directly changes how people live, work, or signal status. Technology as behaviour change is always more interesting than technology as product announcement.
The "so what" must be board-level. Every signal includes a strategic implication aimed at a CMO or Head of Strategy. "Brands should consider this" is not acceptable — the implication must be specific, timed, and actionable.