AudioScholar

How a Specialty Weekly is made

From the week’s literature to a podcast — and where the human sits in it

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.

Human (clinician) Automated · deterministic AI (Google Gemini) Guardrail
Once, at setup
0

The clinician defines the specialty’s “rails”

Human

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.

Then every week, automatically
1

Retrieve the week’s candidate papers

Automated

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.

2

Select the most significant

AI

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.

3

Write the spoken briefing

AI

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.

4

Verify every citation

Guardrail

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.

5

Voice and publish

Automated

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.

Continuously
6

Clinician oversight

Human

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

The clinician lays the rails; PubMed retrieves within them; the AI selects and narrates inside the retrieved set; a guardrail keeps it honest.

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

A curated, impact-factor-ranked catalog

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.

14
elite generalist journals
(every specialty)
specialty journals
for this specialty
journals scanned
for this specialty
~315
journals in the catalog
across the specialties

Elite generalist — scanned for every specialty

Specialty journals

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

Suggest a change or share a thought

Spotted a journal we should add, a specialty to cover, or anything else worth knowing? Tell us.

Submitting opens a pre-filled email to the AudioScholar team — nothing is sent until you press send in your email app.