EVERYWEAR
Methodology

How EVERYWEAR Works

Every article you see on EVERYWEAR has been scored, ranked, and categorised by an automated pipeline running daily across 60 RSS sources. Here is exactly how it works — the scoring formula, the category logic, the source selection, and the prediction system.

The EWEAR Score

Every article receives an EWEAR score from 0 to 100. This is a composite of five components, each measuring a different dimension of editorial value. The score determines article placement across all sections of the site — leaderboard, Best feed, category rankings, and the weekly briefing.

A score of 70+ indicates a strong, highly relevant article. Top scores typically land between 80 and 85. The theoretical maximum is 100, but multi-component scoring means very few articles approach it.

Relevance 0 – 30 points
Measures how specifically wearable-focused the article is. Keyword density across titles, previews, and URLs determines category match. An article matching four or more wearable categories scores the maximum. A single-category match scores 20. Brand-only mentions with wearable context score partial credit. General tech articles with no wearable keywords score near zero — this is the primary filter that keeps the feed focused.
Freshness 0 – 25 points
Hour-based decay from publication time. An article published within the last two hours scores the maximum. Score decays as the article ages, with a floor of 8 points to prevent older-but-excellent articles from disappearing entirely. This means a highly relevant two-day-old article can still outrank a mediocre article published an hour ago.
Authority 0 – 20 points
A per-source editorial weight reflecting the publication's rigour, wearable-specificity, and track record. Specialist wearable publications like Wareable and DC Rainmaker score highest (18–20). Major tech publications score 12–14. General consumer tech aggregators score 10–12. This score is fixed per source and does not change between articles — it reflects our editorial judgement about the source, not the individual piece.
Brand Signal 0 – 15 points
Counts how many recognised wearable brands appear in the article. One brand earns 8 points. Two brands earn 12. Three or more earn 15. An article covering no named brands scores zero on this component — it may still rank well on relevance and freshness, but brand-named coverage signals editorial depth and specificity.
Depth 0 – 10 points
Distinguishes substantive analysis from thin press releases. Signals of depth include: longer word counts, presence of data or benchmarks, use of analysis language versus promotional language, and source type. A full review or comparative analysis scores higher than a product announcement or deal post. Hard-exclude rules filter out pure deal posts, giveaways, and listicle buying guides before scoring begins.

The Eight Categories

Every article is classified against eight categories using keyword matching across titles, previews, and URLs. An article can match multiple categories simultaneously — a review of bone-conduction earbuds that also tracks heart rate might sit in both Hearables and Fitness & Health.

SMARTWATCHES
HEARABLES
AR / VR / XR
FITNESS & HEALTH
SMART HOME
SMART CLOTHING
HEALTH DEVICES
ROBOTICS & AI WEARABLES

The category vocabulary is hand-curated and updated regularly. Brand names are handled separately — a Garmin article defaults to Smartwatches, a Meta article defaults to AR/VR/XR — but only when wearable context words are also present, preventing off-topic brand coverage from slipping through.

Sources

The pipeline fetches from 60 RSS feeds daily, spanning three tiers:

Wearable specialists — Wareable, The Ambient, DC Rainmaker, Gadgets & Wearables, SoundGuys, The Hearing Review, Wareable PULSE, UploadVR, Road to VR. Highest authority weighting.

Major tech publications — The Verge, TechCrunch, Wired, Engadget, Ars Technica, CNET, Tom's Guide, Android Authority. Strong authority, lower wearable density.

Category specialists — MobiHealthNews, Fierce Biotech, IEEE Spectrum Robotics, The Robot Report, Textile World, Innovation in Textiles, STAT News, Biometric Update, Athletech News, Cycling News. Targeted coverage for thin categories.

Sources are evaluated continuously via a source quality tracker that computes the average EWEAR score of all articles from each publication. Sources that consistently produce low-scoring articles are candidates for removal. New sources are added when a category is underserved.

The WTI Signal

Each day's editorial signal — the WTI Signal (Wearable Technology Intelligence) — is generated by Claude Sonnet, Anthropic's language model, using the day's top five articles by EWEAR score plus the current trending topics. The model is prompted to produce a 2–3 sentence editorial that identifies the underlying story, not just the surface events.

The WTI Signal is not a summary. It is an editorial interpretation — what the day's coverage means for the industry, what's being missed, and where the industry is heading. If the AI step fails, a rule-based fallback generates a plain signal from the top article's metadata. The source is always disclosed.

Article-level "So what?" implications — the one-line interpretations visible in each card's score breakdown — are also generated by Claude Sonnet across the top 10 articles daily.

Predictions

EVERYWEAR maintains a public prediction ledger — specific, falsifiable calls about where wearable technology is heading. Each prediction has a deadline, a confidence level (0–100%), and a signal explaining what evidence informed it.

Example prediction
"Samsung Galaxy Ring 2 will launch with cross-platform iPhone compatibility — no Samsung account required — before end of 2026, responding directly to Oura's platform-agnostic model"
Confidence: 55% Deadline: 31 Dec 2026 Category: Health Devices

Predictions are resolved manually when sufficient evidence exists — either a confirmed announcement or a confirmed miss. The pipeline flags potential resolutions daily by scanning top articles for entity matches and resolution-signal language, suppressing speculation words (reportedly, rumour, leak). All resolved predictions remain on the ledger with their outcomes.

The hit rate is public and updated as predictions resolve. EVERYWEAR's track record is part of its editorial accountability — wrong calls stay on the record.

View the full prediction ledger →