Filters
Loading metadata...
Pipeline summary
Therapeutic areas
Trials or candidates can appear in more than one area.
| Area | Candidates | Share | Trials | Median trial age | Recruiting 24+ mo. |
|---|
Recruitment explorer
Result set
Candidates
| Candidate | Lead sponsor | Mechanism / class | Trials | Median trial age |
|---|
Extraction quality
Eligibility extraction eval
| Field | Correct | Errors | Accuracy |
|---|
Material findings
Definitions
Metrics
Backend runs
ClinicalTrials.gov ingestion
| NCT ID | Title | Status | Sponsor |
|---|
LangGraph + OpenRouter
Build walkthrough live census + reviewed AI sample
-
Front end
This page is the viewer. It reads JSON files and turns them into filters, cards, tables, and drill-downs.
-
Raw data
Python fetched every registry record in the current scope from ClinicalTrials.gov. Historical snapshots remain a separate extension.
-
Cleaning
Python standardizes phases, sponsors, conditions, interventions, dates, and current trial statuses.
-
Agent loop
LangGraph extracts structured eligibility fields, validates them against source text, runs an independent model judge, and routes each record to approval or review.
-
Evals
Two independent reviews were reconciled into pilot gold labels. Ambiguous source records are not scored.
-
Export
The builder writes summary, area, candidate, trial, definition, metadata, and evaluation JSON files.
-
Publish
The static files are deployed to the VPS. Readers see the dashboard; they do not trigger live AI calls.