Every drug program has a breaking point
Conviction isn't evidence.We find what is.
Independent, AI-native scientific scrunity for those who bet on drugs.
Request access →Independent, AI-native scientific scrunity for those who bet on drugs.
Request access →You check Carfax before you buy a car.
When you bet on a drug, you check Prelucis.
Biomedical signal lives across literature, trial registries, and mechanistic biology. You miss things before you have even begun.
Once you are in the deal, you have fallen in love with it. The negative signals are the ones you stop hearing.
We pressure the program to its breaking point until the fault lines show — then hand you the evidence underneath, before consensus has it.
We read the entire evidentiary universe of a program — mechanism, preclinical data, trial design, endpoints, and every comparable program and its fate — then apply adversarial pressure until it tells the truth. The output is not a view. It is a finding, with its confidence stated.
The break is at the endpoint. Sensitivity collapses in the responder subgroup once placebo drift is normalised. Three comparable programs failed on the same axis — and the consensus model has not priced it.
Prelucis is in private release with a small number of funds.