Automated README summary
Automatically summarized from the README on 30 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
TrialScout is a demo that reads a patient's plain-language profile and checks it against eligibility criteria of recruiting solid-tumour oncology trials on ClinicalTrials.gov, showing which trials are worth raising with a doctor.
How it uses Jev
For each eligibility rule split from a trial's text, Jev answers one typed question using the patient's cancer type, stage, age, sex and notes. Its verdicts (likely meets, likely fails, ask your doctor) are shown next to the quoted rule and used to rank trials.
Primitives:choice
Technique worth stealing
Hard filters (condition, status, age, sex, distance) run before Jev, and each search is capped at 300 questions.
Try it
npm install; make db-local; echo 'TYPESAFE_API_KEY=your-key' > apps/worker/.dev.vars; make -j2 dev
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.74
- Shows a System One patternunclear0.54
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolunclear0.60
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale0.77 / 2
- About JevFound in material0.95
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 30 Sept 2026.