Scientific due diligence on a claim, inside your assistant. Give Zetesis a claim, an abstract, a paper, a grant or a d…
Scientific due diligence on a claim, inside your assistant. Give Zetesis a claim, an abstract, a paper, a grant or a deck. It routes the claim to its scientific class, then returns the questions a domain reviewer would ask, the failure patterns that caught comparable claims before, and the public evidence bearing on it. Every identifier it returns was retrieved, not generated. **No authentication required.** No account, key or token. ## Tools - `zetesis_scope` routes the claim and returns the diligence apparatus for its class: 314 questions across 11 life-science claim classes, structured by substrate, methods, cohort and risk of bias. A nine-pattern failure taxonomy drawn from studied platform collapses, each carrying the companies it came from, shipped alongside the edge cases where those patterns were wrong. - `zetesis_evidence` runs the searches and returns a deduplicated bundle from Europe PMC, ClinicalTrials.gov, openFDA, NIH RePORTER and SEC EDGAR, every source carrying a PMID, DOI, NCT number, grant number or filing reference. - `evaluate_claim` produces a graded reading server side, when the assessment itself is the deliverable rather than the evidence. - `verify_attestation` re-checks a signed Zetesis record to confirm its claim, evidence and conclusion have not been altered since signing. **The first two call no language model.** They return in under a second, cost nothing to run, and send nothing to a model provider. That is usually the answer a security reviewer is looking for. ## Claim classes Genomics and Mendelian randomisation, single-cell, bulk omics, CRISPR screens, clinical trials, real-world evidence, AI clinical decision support, diagnostics, preclinical models, cell and gene therapy, structural biology. ## The year fence Zetesis can evaluate a claim as it stood in an earlier year, restricting evidence to what existed by then, so a claim is judged on what was knowable at the time rather than on how it turned out. Measured on a control claim: unfenced retrieval missed the pivotal publication entirely and scored 35% evidence coverage. Fenced to the claim's own year, the same query set retrieved it and coverage rose to 79%. The fence is a retrieval precision feature, not only a matter of honesty in retrospect. ## Try it Ask what the published evidence actually supported about aducanumab and cognitive decline at the end of 2019, using only sources available by then. Then ask the same question without the year. The difference is the point.
reutavidan
mcp
free
Others in the same category, ranked by how often they are opened.
