Templates and recipes to build with Reducto
Browse ready-to-use, copy-pastable examples for parsing, extracting, splitting, and more.
CP2000 Notice Processing: Reconcile Payer and Tax-Return Income
Extract CP2000 notice items and payer records, reconcile payer-level reported income, and preserve the response date for a reviewed tax response.
Carbon Project Document Extraction: Reconcile Verification Totals
Extract carbon monitoring and verification quantities, align project and metric scope, and preserve differences for a documented adjustment review.
Hospital Financial Assistance: Reconcile Declared and Documented Income
Extract hospital financial-assistance income records, check case and gross-or-net basis, and reconcile reviewed annualized evidence with declarations.
Construction Submittal Review: Check Revisions and Approval Records
Extract construction submittal identifiers, revisions, and approval dispositions, then compare them with the reviewed procurement requirement.
Festival Artist Invoice Reconciliation: Check Guarantee Balances
Extract festival guarantees, paid deposits, and reviewed deductions, then recalculate the remaining artist balance and compare it with the invoice.
Warehouse Pickup Verification: Reconcile Dispatch and Vehicle Changes
Extract pickup, dispatch, and vehicle-change records, then check shipment identity and field-specific authorization before warehouse release review.
Event Evidence Checks: Verify Duration and Witness Records
Extract event timestamps and witness statements, then compare duration and distinct evidence counts with reviewed verification requirements.
Clean Energy Payroll Review: Reconcile Cash Wages and Fringe Benefits
Extract clean energy payroll wages, fringe amounts, and hours, then compare them with reviewed project requirements and calculate a scoped shortfall.
Legal Memo Review: Verify Rubric Coverage and Source Quotations
Extract legal memo assessment records, verify coverage of an approved rubric, and check that each recorded quotation appears in the memo text.
Legal Due Diligence: Reconcile Loan Schedules with Lender Statements
Extract loan disclosure and lender-statement balances, then compare the instrument, as-of date, currency, and principal basis for due diligence.
Customs Document Extraction: Reconcile Origin and Metal-Content Weights
Extract shipment origin and metal-content evidence, match invoice items, and check declared origins and metal weights without merging country fields.
Interconnection Study Extraction: Reconcile Upgrade Cost Allocations
Extract interconnection upgrade tables with Reducto, then reconcile study revisions, project shares, allocated costs, and the complete dollar total.
Concert Settlement Reconciliation: Check Guarantees and Revenue Shares
Extract concert deal and settlement figures, then reconcile guarantees, permitted expenses, advances, and net revenue shares with a stated formula.
Residual Payment Reconciliation: Match Usage Events to Contract Rates
Extract contract rates and usage events with Reducto, detect duplicate uses, and reconcile a flat-per-use residual calculation with proposed payment.
Immigration Document Extraction: Reconcile Identity and Arrival Records
Extract names, birth dates, and arrival dates from immigration application records, then generate source-linked discrepancies for packet review.
Disaster Reimbursement: Reconcile Invoices and Payment Evidence
Reconcile disaster reimbursement requests with invoice totals and allocated payment evidence, preserving project identifiers and source amounts.
Coffee Supply Chain Traceability: Link Invoices to Producer Plots
Link coffee invoices to producer-plot schedules with Reducto and check lot identifiers, declared origins, and geographic evidence references.
Aerospace Certificate of Conformance Checks for Receiving Inspection
Extract aerospace receiving certificates and compare part numbers, lots, revisions, and approved processors with purchase-order requirements.
Find Missing Tender Requirements in Bidder Evidence Indexes
Extract tender requirements and bidder evidence indexes, detect missing mandatory mappings or unknown IDs, and prepare cited procurement review tasks.
Match Temporary Import Manifests with Carnet Equipment Lists
Extract serial-numbered equipment from temporary import manifests and carnet lists, then detect missing, swapped, or duplicated shipment items.
Convert Handwritten Exam Responses into Question-Level JSON
Extract handwritten exam responses into question-level JSON, preserve equations, and detect missing or duplicate answer parts before human grading.
Compare Employment Verification Letters with Declared Work History
Compare employment verification letters with declared work history, preserve exact source dates, and flag mismatched periods for screening review.
Reconcile Scholarship Award Letters with Financial Aid Ledgers
Extract scholarship award letters and reconcile student, academic year, and amounts against aid ledgers, flagging duplicates and missing awards.
Reconcile Housing Income Declarations with Pay and Benefit Records
Extract recurring income from pay and benefit records, annualize gross amounts, and compare housing income declarations without double-counting.
Reconcile Scouting Measurements Across Player Reports
Extract objective measurements from scouting reports and testing sheets, match player and event details, and surface cited discrepancies for review.
Reconcile Payroll Exposure in Contractor Insurance Submissions
Extract contractor liability application and payroll schedule data, reconcile exposure totals, and flag mismatched periods or duplicate classes.
Reconcile Acquisition Loan Sources and Uses with the Purchase Agreement
Extract acquisition agreement and financing schedule amounts, compare purchase prices, and detect duplicate lines or funding gaps with citations.
Convert Handwritten Registers into Searchable JSON Records
Convert handwritten register entries into structured JSON while preserving source names, dates, and places for search and transcription review.
Match Commercial Invoice and Packing List Quantities
Extract item quantities from commercial invoices and packing lists, match shipment IDs and SKUs, and flag missing lines or unit differences.
Extract Prior Authorization Denial Reasons and Response Deadlines
Extract denial reasons and response deadlines, match the notice to its authorization request, and create a cited brief for appeal preparation.
Handwritten Legal Intake: Extract an Attributed Case Chronology
Extract attributed events from handwritten legal intake letters, preserve uncertain dates and source quotations, and prepare a chronology for review.
Sports Transfer Fee Reconciliation: Check Installment Payments
Extract sports transfer installments and settlement records, match counterparties, and compare recorded payment amounts and dates with the agreement.
Schedule-Change Premium Reconciliation: Match Approved Events to Payroll
Extract approved schedule-change premiums and payroll records, then reconcile event coverage and paid amounts for the same employee and pay period.
Warranty Claim Processing: Check Labor Hours by Repair Operation
Compare claimed labor hours with a selected guide, match operation and vehicle model/year, and surface cited quantity discrepancies for review.
Grant Matching Funds: Reconcile Awards and Contribution Records
Extract grant award and contribution records, identify duplicated contributions, and reconcile documented matching funds with the approved requirement.
Inspection Report Extraction: Track Corrective-Action Evidence
Extract inspection findings and corrective-action responses, then check finding coverage, stated completion, and linked evidence for closeout review.
Aircraft Lease Redelivery: Check Serialized Component Life Records
Extract serialized component life records for aircraft lease redelivery and compare documented remaining cycles with a reviewed return requirement.
Packaging Quality Data Extraction: Compare Inspections Across Sites
Extract packaging inspection results across receiving sites, join the supplier lot and specification, and list measurements outside the allowed range.
NIL Contract Extraction: Reconcile Agreement Terms with Disclosures
Extract NIL agreement terms and disclosure fields, then compare parties, dates, and cash compensation while preserving the source of each value.
Construction Pay Application Reconciliation: Verify the Current Amount Due
Extract construction pay application totals and recalculate current amounts due from earned work, stored materials, retainage, and prior certificates.
Home Health Referral Processing: Reconcile Services and Signed Orders
Extract home health referral and order fields, then compare patient references, services, visible signatures, and timing before intake review.
Crew Credential Checks: Compare Certificate Validity with Assignment Dates
Extract crew credential dates and compare them with assignment windows and reviewed document requirements to find expiry gaps or missing records.
SOC 2 Report Extraction: Build a Vendor Exception Register
Extract selected SOC 2 control results, preserve auditor exceptions and untested procedures, and check report scope against a reviewed checklist.
Textile Lab Report Extraction: Compare Results with Product Specifications
Extract fabric test results from textile lab reports and compare style, lot, method, direction, units, and signed values with product specifications.
Handwriting OCR for Equipment Logs: Extract Timestamped Readings
Turn handwritten equipment logs into timestamped readings with Reducto, then check equipment tags, units, duplicate times, and monitoring ranges.
Art Loan Insurance Review: Check Coverage Dates and Scheduled Values
Extract art loan agreements and insurance schedules, then check that coverage dates and scheduled values match the requirements for each object.
FDA Form 483 Extraction: Build a Supplier Observation Register
Extract FDA Form 483 observations into a supplier register, match the correct facility and inspection, and identify records needing review.
Clinical Research Data Extraction: Align Study Results for Comparison
Extract study populations, endpoints, timepoints, and effect estimates with Reducto, then align research results before comparing their values.
Mortgage Closing Document Checks: Reconcile Loan Amounts and Borrower Names
Extract loan and borrower fields from mortgage closing documents, then reconcile note principal, disclosed amounts, and gross loan proceeds.
International Athlete Registration: Reconcile Identity Documents
Use Reducto to compare names and birth dates across athlete registration and identity documents while preserving source-language evidence.
Engineering Interface Documents: Compare Revisions, Units, and Tolerances
Extract interface nominal values, tolerances, and governing references, then compare full tolerance intervals against a selected baseline in Python.
Chargeback Evidence Extraction: Reconcile Receipts and Delivery Records
Extract chargeback receipts and delivery records with Reducto, then compare order references, amounts, currency, and shipping addresses with citations.
Check Auto Finance Deal Jackets for VIN and Amount Mismatches
Extract VINs and financed amounts from auto deal jackets, compare order, contract, and insurance records, and flag cited funding-packet discrepancies.
Extract Medicaid Activity Logs for Caseworker Review
Extract dated Medicaid activity logs, detect duplicate or implausible hours, and prepare cited totals for caseworkers using reviewed program rules.
Reconcile Bankruptcy Proofs of Claim with Schedules and Invoices
Extract bankruptcy proofs of claim, schedules, and invoice support, match creditors and obligations, and compare cited amounts for claims review.
Reconcile Music Royalty Catalogue Transfers by Work and Share
Extract music catalogue transfer and relinquishment schedules, compare work IDs and shares, and flag mismatched parties, dates, or percentages.
Calculate Revenue Guarantee Shortfalls from Contracts and Statements
Extract contract guarantee rates and settlement statements, match partner and period, and calculate cited revenue shortfalls for finance review.
Extract Drawing Tolerances and Compare Supplier Inspection Results
Extract drawing dimensions and asymmetric tolerances, match supplier inspection records, and flag out-of-range results with cited source values.
Reconcile Bank Statement Balances for Benefit Redetermination
Extract bank statement and declared balances, verify the reviewed account and reporting date, and surface cited differences for benefit caseworkers.
Compare Artwork Appraisals with Scheduled Insurance Values
Extract artwork appraisal and scheduled insurance values, match object IDs and currencies, and compare the amounts with a reviewed value rule.
Compare Submitted Diagnosis Codes with Chart Evidence
Compare submitted diagnosis codes with explicit chart codes for the same member and encounter, creating cited documentation gaps for coding review.
Check Clinical Trial Consent Versions, Signatures, and Dates
Extract consent versions and signature dates, compare them with a selected site approval letter, and surface cited document discrepancies for review.
Automate KYC Document Refresh Checks for Identity and Expiry
Compare identity-document names and numbers with customer profiles, check printed expiry dates, and create cited KYC refresh tasks for analysts.
Check Hotel Group Billing Against Contracted Room Rates
Extract hotel agreement rates and final folio charges, recompute room charges, and flag billing discrepancies with source citations for finance.
Extract Schedule K-1 Income and Flag Duplicate Tax Forms
Extract partnership Schedule K-1 income, detect duplicate or amended forms, and withhold totals until taxpayer and tax-year scope is resolved.
Extract Material Test Reports and Check Specification Limits
Extract material test report values and specification limits, match revisions and units, and flag measurements outside the stated numeric range.
Build a Seller Disclosure Review Checklist from PDFs
Extract seller disclosure answers and explanations from PDFs, then apply question-specific review rules with cited property and form checks.
Automate Prior Authorization Intake with Cited Document Checks
Extract member IDs, service codes, signatures, and encounter dates to build a cited prior authorization intake checklist for clinical reviewers.
Reconcile Player Trade Proposals with Season Payroll
Compare player trade proposals with season payroll, flag salary discrepancies, and calculate proposed net movement from cited source values.
Reconcile Mortgage Pay Stubs with Loan Application Income
Extract mortgage pay stub and application income with Reducto, annualize base pay, and flag borrower, employer, or income mismatches with citations.
.png&w=3840&q=75)
Build a Grounded Chat Agent over 10-K Filings with r-1
Build a grounded chat agent over Apple’s 10-K filings with r-1. Add history-aware retrieval, source citations, follow-up handling, and page-level evidence.
.png&w=3840&q=75)
Build a Citation-Ready Knowledge Base with r-1
Build a citation-ready knowledge base from Apple’s 10-K filings with r-1. Parse tables, create searchable records, filter retrieval, and refresh documents.
Turn a Complex 10-K into Grounded RAG with r-1
Build a grounded RAG pipeline for Apple’s 10-K with r-1. Learn table-aware document parsing, embedding-ready chunking, retrieval, and page-level citations.
-3.png&w=3840&q=75)
Turn loss runs and insurance submissions into underwriting-ready data
Loss run reports are how carriers report claims history, and every one is laid out differently across dozens of pages of dense tables. This cookbook covers how you can create an end-to-end pipeline in Reducto that turns the whole report in one call into clean, structured tables you can load straight into code.
-4.png&w=3840&q=75)
Split a law review article into sections and extract any part
A law review article is long and highly structured: an abstract, a table of contents, and dozens of numbered sections, often across a hundred or more pages. Pulling one piece, say the abstract, first means finding where it lives before you can read it. With Reducto you parse the whole article once, split it into its constituent parts, and then run a targeted extract against only the pages that hold what you want. Three endpoints, one pipeline: Parse turns the PDF into clean structured text, Split maps the article into its sections, and Extract pulls the exact field you asked for with citations back to the source.
-1.png&w=3840&q=75)
Parse any healthcare document into clean, structured text
Healthcare documents are some of the messiest inputs in any pipeline. A single patient's file might include a handwritten intake form, a scanned chart with checkboxes and body diagrams, a casualty card filled out under pressure, and a lab report full of dense tables, each laid out differently and often photographed or faxed. Retyping that by hand is slow, error prone, and does not scale. Reducto parses the entire document in one call and returns it as clean, structured text, handwriting transcribed and tables preserved, so your code or your model works with the data instead of the scan.
-2.png&w=3840&q=75)
Pull every field from a handwritten property loss form
First notice of loss forms come in handwritten, dozens of fields packed into a tight grid with corrections scribbled over the originals. Reducto reads the handwriting, skips the crossed-out edits, and returns every field as structured JSON with a citation on each value.
-1.png&w=3840&q=75)
Turn a brokerage statement into structured account data
Brokerage statements bury account numbers, types, and balances in dense, multi-account tables that look different at every firm. Reducto parses those tables cleanly, then returns every account as structured JSON with a citation on each value.
.png&w=3840&q=75)
Reconcile every transaction on a bank statement
Bank and brokerage statements arrive as PDFs and scans that spreadsheets can't read. Reducto's Extract turns one into a clean, typed list of every transaction, ready to load into a ledger, dashboard, or audit trail.
.png&w=3840&q=75)
Extract structured data from patient intake forms
Patient intake forms arrive as scans, faxes, and phone photos, every one laid out differently. Reducto's Extract reads them the way a nurse would, pulling demographics, insurance, and medication history into clean JSON with a source citation on every field.
Reducto + Databricks: a friendly parsing comparison
Nine real cases where Reducto's parsing and Databricks ai_parse_document diverge, from spreadsheets and charts to signatures, tracked changes, and handwriting, and why those last-mile details decide whether downstream AI lands the right answer.
.png&w=3840&q=75)
Pull every redline from a contract
Redlined contracts are exactly the long-tail complexity that breaks template-based pipelines. Reducto reads every strikethrough, underline, and annotation as structured tags, so your team surfaces all 500+ revisions in code instead of page by page.
