Document Ingestion

EQUIRE accepts catalog-supported file types and runs each document through a processing pipeline. Where source attribution is available, extracted values such as occupancy, rent, NOI, tenant names, and loan terms link to the originating document and an available evidence locator or snippet. These are review aids; an attached locator or excerpt does not itself verify the number against the source.

Supported uploads and limits

Accepted extensions match the upload policy: PDF .pdf; Word and related formats .doc, .docx, .docm, .odt, .rtf, .epub; spreadsheets .xlsx, .xls, .xlsm, .xlsb, .ods, .csv; presentations .ppt, .pptx, .pptm, .pps, .ppsx, .ppsm, .pot, .odp; plain text .txt; and ZIP archives .zip. PDFs can be up to 100 MB; ZIP archives can be up to 500 MB (the container limit; document members use per-type caps: PDF 100 MB, other supported docs 50 MB, 500 MB total extracted documents); other accepted types are capped at 50 MB per file. Images (PNG, JPEG, WebP) dropped on the Documents page or extracted from ZIPs route to Property Photos (up to 12 per deal, 15 MB each). Large multipart payloads may use direct-upload paths when the client exceeds the small form-data threshold (4 MB).

ZIP archives expand to supported CRE formats and property photos; nested zips and unsupported types are skipped per policy. Legacy .ppt presentations are accepted. If they do not yield usable extracted text, convert them to .pptx and upload again.

Document types you can ingest

What gets extracted

Offering memorandum

Property identity (address, asset class, year built, total SF), asking price, in-place NOI, cap rate, occupancy, and tenant or lease abstracts included in the package.

Rent roll

Tenant name, suite or unit, leased square footage, rents, lease commencement and expiration, renewal options, and recovery structure. Summary or aggregate rows (floorplan averages, grand totals) are filtered where the pipeline treats them as non-tenant rows.

Operating statement / T-12

Effective gross revenue, operating expenses by line item, NOI, and occupancy by period.

Debt and loan schedules

Loan amount, rate, IO period, amortization, maturity, and lender where present.

Pipeline flow (orchestration)

After extraction and evidence checks, EQUIRE merges supported data into the deal record and records the resulting review findings. Valuation inputs and the document search index may update in follow-up work after the document reaches a terminal status.

Valuation projection seeds assumption hints from the merged schema with AI inference skipped; full AI-heavy valuation work still happens when you open the Valuation tab and run the model builder. Embedding builds the retrieval index. Either follow-up may be deferred near the processing time budget. A processed or needs_review document status summarizes the extraction and review result; it does not promise that projection or embeddings have finished.

Processing stages you may see

Document processing-stage labels (DocumentProcessingStage) include queued, classification, extraction, verification_deterministic, verification_llm, verification_evidence, reconciliation, projection, and terminal completed or failed. They describe the work recorded for a run, not a guarantee that every optional follow-up finishes before the document becomes terminal. Jobs may record embedding and projection on a separate continuation.

Classification, extraction, and verification

Classification uses filename signals, content keywords, and model-based fallback when needed. Extraction uses native PDF handling or text parsing by format. Verification passes check extracted values against source evidence before reconciliation.

Conflict detection

When two documents disagree on the same field, EQUIRE records a conflict and routes it to the Review tab instead of silently merging. You choose the winning value or enter a manual override.

Source provenance

Field-level attribution

Where source attribution is recorded, Extracted Data can show the originating document and an available evidence locator or snippet. This points to material for review; it does not independently reread or verify the source number.

Manual overrides

User-entered tracked values retain user authority and are marked as user-sourced.

Reviewing conflicts

The Review tab lists open review items: data conflicts, source review, and field checks such as low-confidence values, missing fields, clarifications, diligence confirmations, and financial verification. Available actions depend on the item. A value-changing decision can update the relevant schema and valuation input; evidence-only or supporting findings may be resolved without changing a value. Persisted review status is refreshed as findings and decisions change, including supported auto-heal paths.

The workbench lanes (Blocking Data, Source Review, and Supporting Checks) are a recommended order of operations over the same queue, not a second set of totals.

Worker dispatch and admins

Background workers can invoke processing with x-worker-secret validated against PIPELINE_WORKER_SECRET (and related internal headers). Preview deployments should set this secret if worker dispatch is required; ops details live in internal pipeline documentation, not in this user guide.

Email and intake (optional path)

Inbound email with attachments can create or enrich deals via the intake pipeline (webhook-verified, org-resolved). User-facing surfaces include pending-attach flows (GET /api/intake/pending-attach, PATCH /api/intake/[recordId]/dismiss). Operational email setup is documented for admins in the repo's docs/operations/email-setup.md; it is not duplicated here.

Limits and known gaps

• Non-English documents: extraction targets English.
• Scanned PDFs: low-quality scans may yield partial extraction; higher-quality scans or alternative formats help. Vision-style reading may be attempted when the pipeline classifies a scan.
• Rent roll summary rows: aggregates may be filtered; restore missed real rows manually on Extracted Data.
• Large documents: processing continues in the background; watch the Documents tab for status.

Reclassifying a misclassified document

Reclassify and reprocess from the Documents tab without re-uploading when the type was wrong.

After ingestion

Resolved data feeds Rent roll & financial data cleanup, then Valuation DCF, IC Memo, and Deliverables. For the full workspace tour, see Getting started.