From PubMed to a brief you can audit.
Curata is an AI-assisted orientation service for new clinical literature. Its workflow is designed to keep the source visible, separate selection from writing, and stop synthesis sections that have not cleared the current verification gate.
Last updated August 2026
At a glance
A staged pipeline, not one prompt
Search, selection, deterministic ranking, Card writing, and Essay verification are separate stages. Different checks answer different questions, and deterministic code handles the parts that should not be left to a language model.
Search a defined PubMed topic
Each topic has a maintained PubMed query. For actively followed topics, a scheduled monthly run searches records entered in PubMed during the preceding 30 days, requests results in publication-date order, and fetches the available citation and abstract data. The current retrieval cap is 400 records per topic and run.
Select from each title and abstract
An Anthropic model sees the specific topic, professional audience, active boundary rules, and each complete title and available abstract. It routes every record to the main Card candidates, a separate Additional studies area, or an objective exclusion. Unclear or adjacent research remains additional rather than disappearing. If PubMed supplies no abstract, the title alone cannot justify a Card or exclusion, so the record remains additional.
Validate exclusions, then rank in code
A hard exclusion is accepted only with an exact quote from that record and a closed objective reason, including an active rule for a topic-specific mismatch. Code orders main candidates by selection priority, evidence label, publication year, and PMID. There is no score floor: an edition may contain up to 15 Cards, plus up to 10 separately labelled Additional studies that are never promoted merely to fill the Card list.
Write one abstract-grounded signal per card
Each Card is generated in isolation from one supplied PubMed abstract, not from an assumed full text. Code checks the signal's support excerpts and numbers against that same abstract. Unsafe optional fields are removed; a still-invalid Card is skipped after one corrective retry without destroying otherwise valid Cards. Citation details and the PubMed link remain attached.
Build a source-marked synthesis
Selected titles, abstracts, and signals are used to write short topic sections. Every clinical claim must carry an inline marker, and every marker maps to one PMID in that edition. Code strips markers tied to out-of-edition PMIDs, removes unused source declarations, and fails sections that contain undeclared markers or no valid cited source.
Verify with code and an independent model family
Programmatic checks cover PMID integrity, marker completeness, and numeric marker-to-abstract binding. Google Gemini then checks the section against the supplied source abstracts for statistical semantics, unsupported claims, attribution, and qualitative marker binding. A separate Anthropic judge adjudicates two subjective flag types; if that judge is unavailable or uncertain, the flag stays in place.
Regenerate or repair, then check again
Structural or deterministic failures trigger a fresh generation rather than an in-place edit. Confirmed subjective issues can enter a narrow repair pass using the relevant source abstracts. Repaired text does not clear itself: it must be verified again.
Apply the honesty gate
A synthesis is displayed only when every section is cleared by its latest verification, or has been explicitly accepted by a human reviewer. Current verification records are bound to the exact section content; if the text changes afterward, the prior result no longer clears it. A still-flagged topic remains hidden for manual review.
Transparency
What the labels do—and do not—mean
Evidence label
A controlled description of the study design reported in the abstract, such as systematic review, randomised trial, cohort study, or case series.
Quality tier
A simple 1–5 hierarchy derived mainly from study design. It is not a full critical appraisal, risk-of-bias assessment, certainty rating, or GRADE judgment.
Selection priority
An automated reading-order estimate led by topic centrality and clinical usefulness. It ranks direct candidates; it is neither an inclusion threshold nor a claim about scientific truth.
Considered studies
The pipeline retains the selection funnel and versioned decision ledger: how many records matched, which were assessed, why an objective exclusion was accepted, which item-level technical failures occurred, and which candidates did not become Cards. Up to 10 close candidates appear directly in the Additional studies area.
Cadence
What “monthly” means in practice
The scheduled curation run begins on the first day of each month in the Europe/Zurich time zone. It uses a rolling 30-day PubMed entry-date window, so it is not a claim that every paper carries a publication date in the same calendar month. A first edition may also be requested when a new account chooses a topic; already-prepared topic editions can be reused across readers.
A topic can produce fewer than 15 Cards—or none—when the search is quiet or candidates do not fit the main route or Card validation. Direct studies are not removed by a score floor, while adjacent studies are not promoted merely to meet a quota.
Limitations
What this process cannot guarantee
- PubMed is the search source. Papers outside PubMed, delayed indexing, imperfect topic queries, and records beyond the retrieval cap can be missed.
- Most generated copy is abstract-grounded. An abstract can omit methods, subgroup detail, caveats, adverse events, and results that appear in the full paper.
- Automation can still be wrong. Independent checks and fail-safe gates reduce known error classes; they do not make model output infallible.
- This is not a systematic review. Curata does not claim exhaustive recall, duplicate screening by human reviewers, formal risk-of-bias appraisal, or guideline-grade certainty assessment.
- Clinical context still matters. A short signal cannot account for an individual patient, local guidance, contraindications, or the complete evidence base.