Operational Document
Methodology
How the weekly digest is collected, ranked, and published
- Product
A weekly curated intelligence digest covering AI & Strategy, Ecommerce & Retail Tech, Luxury & Consumer, and Jewellery Industry. Each issue presents eight ranked articles across four categories, delivered simultaneously to the web, by email, and as a podcast briefing.
- Sources
~53 RSS feeds across six source tiers — global newswires, retail trade press, fashion and luxury publications, jewellery specialist titles, specialist technology feeds, and business commentary. Two static page scrapers supplement the feed list.
A Tavily web-discovery layer runs in parallel each cycle, using LLM-generated search queries per category to surface high-quality articles that fall outside the curated feed list.
- Ingestion
Articles are ingested on an automated schedule into an append-only store. Duplicate detection runs on URL and title similarity — each article appears at most once regardless of how many feeds publish it.
- Weekly window
Monday 00:00 through Sunday 23:59, Europe/Copenhagen timezone (CET/CEST). Each digest covers only articles with a publication date that falls within that window.
- Classification
Articles are assigned to one of four topic categories using a deterministic keyword and source heuristic. Source-level overrides take priority (e.g. a jewellery trade publication is always assigned to Jewellery Industry regardless of article content). Classification uses no LLM inference and is fully auditable.
- Ranking
A deterministic pre-score is computed for each article: recency weight (constant baseline), source tier weight (0–0.15), and keyword relevance boost (0.05 per match). Low-signal markers carry a −0.20 penalty.
The top 100 candidates per category are then passed to
o4-mini(reasoning model), which applies editorial criteria — business materiality, originality, timeliness — to select the final 7 articles per category. A hard diversity guard caps any single source at 3 articles per category.- AI — what it does
- +Reranks pre-scored article candidates using editorial criteria (o4-mini)
- +Generates concise web summaries from title, source, date, and snippet only — no full article required
- +Generates email digest bullets (3 per article) from up to 8,000 characters of the full fetched article text
- +Produces the weekly one-sentence insight via a two-stage process: one model generates four candidates each through a distinct analytical lens (Implication, Paradox, Reframe, Pattern); a second model (gpt-4.1) judges and selects the most original
- +Scripts the podcast briefing (~12–15 min) from the top 8 articles
- +Generates the weekly cover image via a SceneDirector prompt pipeline
- AI — what it doesn't
- —Accessing paywalled or subscription-gated content — articles that cannot be fetched are skipped entirely
- —Human curation or manual editorial override of ranked results
- —Rewriting or editorialising source material — email bullets reflect the article as published
- —Generating content not grounded in a published source article
- Cadence
Published weekly. The pipeline runs automatically each week; new issues appear in the archive as soon as they are built. Subscribers receive the email digest on the same schedule.
- Transparency
Article selection is AI-augmented, explainable-first. Every ranking signal is deterministic and logged; the LLM reranker sees only pre-scored candidates and applies editorial criteria, not preference.
We are not affiliated with any publisher. All links go to original source articles. Summaries are AI-generated and may miss nuances — always read the full piece for complete information.
Questions or source suggestions? Share your feedback →
Pipeline last run: 26 April 2026 · CET · 18 issues archived