How a Specialty Weekly is made
Each specialty publishes one ~3–10 minute audio briefing per week. Here is exactly how it is assembled, what is automated, what is AI, and what a clinician decides.
“Where is the human–AI bridge — do you choose the articles, or does the AI?”
Neither extreme. A clinician sets the boundaries once — which journals, how recent, how often. Then every week, automatically, PubMed retrieves what is eligible inside those boundaries, and the AI selects and narrates from that retrieved set.
The AI never roams the open web, and no one hand-picks papers week to week. A citation guard rejects any paper the AI names that was not actually in that week’s PubMed results.
“What is the range of journals that gets scanned?”
~24 journals per specialty: the 14 elite generalist journals (NEJM, Lancet, JAMA, BMJ, Annals, Nature, Science…) scanned for every specialty, plus that specialty’s ~10 leading journals.
Drawn from a curated, impact-factor-ranked catalog of ~200 journals across 30 specialties, maintained by the clinician. Bounded to the last 7 days; it broadens only if a week is unusually thin.
For each specialty, a clinician sets the journal allow-list (from the catalog), the search scope, the recency window (7 days), the weekly cadence, and the narration voice. This is a one-time decision per specialty, then revisited only when the journal catalog is updated.
This is the upstream half of the human–AI bridge: the human decides what is eligible, not which individual paper is featured.
A scheduled job searches PubMed / NCBI: papers published in the last 7 days, matching the specialty, and appearing in one of the allow-listed journals. It returns up to ~30 candidates and tags each with impact-factor data.
This is a plain database query against the U.S. National Library of Medicine — not AI. Conceptually: (specialty) AND (last 7 days) AND (allow-listed journals). If a week is unusually sparse (≤5 papers), it broadens beyond the list so the briefing is never empty.
From that retrieved pool, the AI shortlists and ranks the papers most likely to matter clinically this week — the editorial judgment of which of the eligible papers to feature.
The AI can only choose from what step 1 actually retrieved. It cannot add a paper from memory or the open web.
The AI drafts the ~3–10 minute script from the selected papers’ abstracts — a connected roundup with the key findings and their citations, in plain spoken language.
A citation guard checks each paper the script names against this week’s actual PubMed pool. Any citation that was not retrieved — or whose title doesn’t match — is dropped. If more than 30% are dropped, the whole episode is failed rather than published.
This is the safeguard against the AI inventing or mis-attributing references. Every drop is logged for audit.
The verified script is converted to natural-sounding audio (Google Cloud text-to-speech) and added to that specialty’s podcast RSS feed — the same feed that appears in Apple Podcasts, Spotify, and other players.
The clinician listens, can remove or archive any episode, maintains the journal catalog, and reviews a per-episode “report an inaccuracy” channel. This is the downstream half of the bridge — human judgment closes the loop.
The human–AI bridge, in one line
No step lets the AI reach outside a clinician-defined, citation-verified boundary. The human’s choices are structural and upstream (which journals, how recent, how often) and supervisory and downstream (listen, correct, remove) — not week-to-week paper-picking. The AI’s job is the editorial middle: choose the most significant of what was retrieved, and explain it.
The journals scanned
Every specialty briefing scans the same 14 elite generalist journals; most also scan a curated set of that specialty’s leading journals. Pick a specialty to see exactly which journals are scanned for it.
If a week has very few papers in these journals, the search broadens beyond the list so the briefing is never empty. The catalog is clinician-maintained and expanding.
Feedback
Spotted a journal we should add, a specialty to cover, or anything else worth knowing? Tell us.