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.
Historian retrieval
Tags pulled from the process historian for a unit and a window.
Work order retrieval
Open and closed work orders for an asset from the maintenance system.
Spec lookup
Rated points and limits pulled from the asset registry and vendor datasheets.
Detection and analysis
Classification
Documents or records sorted into the types the pipeline expects.
Rate-residual detection
A signal fitted against rate so a change in the machine is separated from a change in flow.
Fleet rollup
A check run on every asset, scored and rolled up by site.
RSM optimizer
A response surface fitted to the unit’s data and searched inside the operating limits.
Constrained ranking
Items ranked under limits such as rig count, capital or schedule.
Lane scoring
Locations or lanes scored on economics and risk from their own terms.
Engineering calculators
Emission factors, margins and machine comparisons computed as code.
Documents
Document parsing
Sections, tables and fields pulled out of a document with their location kept.
Review
Review agent
A checklist applied to a draft or a record, with each item passed, failed or sent to a person.
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.
Interactive boards
The board a shift lead sees, with the trend, the list and the record.
Monitoring and alerts
A check scheduled on a unit or a fleet, with an alert when it trips.