Armeta parses engineering line lists — whether PDF tables, Excel exports, or scanned tabular documents — into structured line-level records: line numbers, sizes, material specs, insulation, design and operating conditions, from-to connectivity, and P&ID references. Line list data is contextualized against P&ID and isometric data to surface discrepancies and build the complete engineering knowledge graph.
The line list is the structured complement to the graphical record. Armeta preserves your schema and parses each column into queryable fields — including the columns that are usually flattened into free text.
Parsed using your numbering convention. Service codes, size, material class, area, and sequential identifier separated into structured fields.
Captured per row with units normalized — inches, millimeters, mixed-unit imports — so the structured output is queryable across vintages.
Material class assigned per line (e.g. A1A, B2B) extracted and resolved against your pipe specification register.
Insulation type and thickness captured where present, including heat-tracing notes flagged as separate structured attributes.
Captured separately from operating values so any downstream stress, integrity, or compliance workflow has the right column to read.
Operating-condition columns parsed and reconciled against the design columns and the source P&ID where applicable.
Service classification (hydrocarbon, hydrogen, sour, utility, etc.) captured per line and used for downstream regulatory tagging.
Origin and destination equipment tags or off-page references parsed into a structured connectivity column ready for graph assembly.
Source P&ID drawing number per line — the join key used to reconcile the line list against the rest of the engineering archive.
Heat tracing, slope requirements, NDT flags, and other free-text remarks structured as discrete tags rather than dropped on the floor.
A line that exists on a P&ID should appear on the line list. A line on the line list should have a corresponding isometric. Discrepancies between these three sources almost always indicate either a documentation error or an undocumented field modification — both of which matter.
Armeta runs the reconciliation automatically and surfaces the disagreements as structured reports for engineering review.
Each line-list row is parsed against your numbering convention and promoted to a first-class entity. Soft variants (formatting, leading zeros, hyphens) are normalized; hard mismatches are flagged for review rather than silently merged.
Every line on the line list is matched to its appearance on the P&ID. A line on the list with no P&ID presence is surfaced. A line on the P&ID with no list entry is surfaced. The two sources cross-validate each other rather than living in parallel.
Where isometrics exist, the line list is reconciled against the spatial record. Spec, size, and service are cross-checked spool by spool so the line list reflects what was actually fabricated and installed.
Where the P&ID, isometric, and line list disagree, Armeta produces a structured discrepancy report with both values and their source documents. Reconciliation is a decision your engineering team makes with full evidence, not a guess the model makes for you.
Once the line list is structured and reconciled against the graphical record, the workflows that depend on it stop being spreadsheet archaeology.
Surface the lines that meet design-condition thresholds for pipe stress review without manually filtering thousand-row spreadsheets.
Real-world line lists come in every format engineering data has ever lived in: native Excel exports with merged headers, PDF tables with image-baked text, and scanned tabular documents from filing cabinets. Armeta reads them all.
No re-keying. No template forcing. Your line-list schema is what comes out the other side — cleanly structured and joined to the rest of the engineering knowledge graph.
Every parsed line list Armeta delivers is validated against the source document by our engineering team before it reaches you. Accuracy metrics on your own line lists are produced as part of the initial document audit — our ten-document free assessment that establishes baseline performance before any paid engagement.
Every parsed line list is reviewed by an Armeta engineer against the source document before delivery. Not raw model output.
Every structured field links back to the exact cell or region on the source line list — auditable, click-through, defensible.
Differences between the line list, the P&ID, and the isometric are surfaced as structured reports so engineering reconciles them with full evidence.
Your line-list schema is preserved. Columns are not dropped, not renamed, and not silently merged — the structured output round-trips cleanly back to your master.
Three deployment modes, chosen to match the security and governance constraints your engineering records actually live under.
Fastest time to value
Armeta-hosted, isolated per customer. Your engineering documents and extracted data remain segregated from every other customer environment.
Your network, your perimeter
Armeta's contextualization engine runs inside your network. Your documents never leave your environment. Deployed with customers today under data residency and air-gap requirements.
Managed inside your tenant
Armeta-managed deployment inside your own cloud tenant. Cloud operational model, customer-controlled perimeter.
Before any procurement conversation, see Armeta run on your actual line lists — structured row by row and reconciled against your P&IDs and isometrics. Not sample data. Not a generic demo. Your line lists, contextualized, delivered as a structured report in one engagement.
