Use cases are assembled from pipelines that already exist.
A builder does not start from a blank canvas. The steps below are published, versioned and tested, and a new use case is mostly a matter of wiring them in the right order and adding the step that is specific to the job.
Retrieval
OCR
Scanned pages and images turned into text with the page kept.
Web search
Public sources searched and fetched with the URL and date kept.
Clinical data retrieval
Locked tables, listings and prior protocols pulled with their version.
Detection and analysis
Classification
Documents or records sorted into the types the pipeline expects.
Molecular modeling
Structure prediction, docking and solvated simulation run per candidate.
Omics analysis
Differential expression and pathway enrichment from count data.
Knowledge graphing
Entities and relations from the literature joined to internal data.
Documents
Document parsing
Sections, tables and fields pulled out of a document with their location kept.
Entity parsing
Genes, compounds, indications and adverse events pulled out of text.
MedDRA coding
Adverse event terms coded to MedDRA with the version kept.
Review
Review agent
A checklist applied to a draft or a record, with each item passed, failed or sent to a person.
Evidence scoring
Each claim scored on source quality and agreement, with the citation kept.
Output
Templates
A company template filled from pipeline output, with each field traced.
HTML reports
A report or brief built from the run, with citations and the run record.