Asset enquiry
- Accounts
- 1 with a positive balance
- AEAT · Annual income
- €18,000 / year
- Cadastre
- 1 property
Document intelligence specialised in your industry.
MestrIA is the platform for processing documents at scale, with ready-to-use solutions for debt collection and real estate assets. It classifies, extracts and cross-checks data to deliver structured results with source evidence. Less manual work. Faster operations.
Ready-to-use solutions
Less manual work
EU processing
For debt recovery teams, servicers, law firms and asset managers.
Teams that work with MestrIA
8
▪ ready-to-use solutions
1M+
▪ documents processed per month
5
▪ proprietary extraction and validation engines
EU
▪ guaranteed EU data residency
What is MestrIA
The platform to accelerate your document workflows.
Process thousands of documents with solutions ready for your industry. Classify, extract and check information using the fields and criteria each workflow needs.
Less manual work. Fewer errors. Faster processes.
YOUR DOCUMENTSOAP AGREEMENT REGISTRY EXTRACT LEXNET
Loan agreement
- Principal
- €8,000
- Date
- 15/03/2025
- Parties
- Party A · Party B
Registry information
- Property
- 001 · Example
- Owner
- Owner A
- Charges
- Mortgage
Court notice
- Court
- Court A
- Proceedings
- Case A
- Decision
- Procedural decision
DOCUMENT INTELLIGENCE
ClassifyExtractCross-checkAudit
Extraction engines, proprietary models and solution-specific rules.
STRUCTURED RESULTS
Case-file data
| Document | Field | Value |
|---|---|---|
| OAP | Annual income | €18,000 |
| Agreement | Principal | €8,000 |
| Registry extract | Property | 001 |
| LexNET | Decision | Procedural decision |
DataIssuesSource evidence
Review, export to Excel or connect delivery to your management system.
Fields and checks depend on the solution. Delivery formats and connections are agreed for your team. Storage and processing in the EU.
▪ From documents to your operations ▪
From agreements to the data you need.
MestrIA extracts parties, amounts and financial terms from an agreement and organises them into structured data. Select an agreement type to explore the source document and its output as JSON or a table. Field names and codes in the sample outputs remain in Spanish, following the original schema.
Input documentcontrato_prestamo_47829153K.pdf
PERSONAL LOAN AGREEMENT
Borrower
MARTÍNEZ SOLÉ, ELENA · NIF 47829153K
C/ Marina 142, 4º 2ª, 08013 Barcelona Financial terms Principal advanced €7,490.00 · 60 monthly payments of €158.42
Nominal rate 8.25% · APR 9.14% · arrangement fee 1.5% Clause 10.2 · default interest Two points above the ordinary rate Signature 12 March 2019 · electronic signature with qualified seal
C/ Marina 142, 4º 2ª, 08013 Barcelona Financial terms Principal advanced €7,490.00 · 60 monthly payments of €158.42
Nominal rate 8.25% · APR 9.14% · arrangement fee 1.5% Clause 10.2 · default interest Two points above the ordinary rate Signature 12 March 2019 · electronic signature with qualified seal
REVOLVING CREDIT CARD AGREEMENT
Holder
FERRER OLIVA, ANDRÉS · NIF 53921487M
Av. Diagonal 305, 4º 1ª, 08013 Barcelona Product Visa Classic Revolving · agreement 504128-77
Credit limit €3,000.00 Financial terms Deferred nominal rate 22.08% · APR 24.51%
Minimum monthly payment 3.00% of the drawn balance Signature 4 October 2021 · electronic signature with qualified seal
Av. Diagonal 305, 4º 1ª, 08013 Barcelona Product Visa Classic Revolving · agreement 504128-77
Credit limit €3,000.00 Financial terms Deferred nominal rate 22.08% · APR 24.51%
Minimum monthly payment 3.00% of the drawn balance Signature 4 October 2021 · electronic signature with qualified seal
Structured outputsalida.json
// Select “View example result”
ReadClassifyExtractValidate
Example table with simulated data
portfolio_2026Q3.xlsx · 2,140 rows
| A | B | C | D | E | F | G | H | I | |
|---|---|---|---|---|---|---|---|---|---|
| 1 | nif KEY | titular | producto | capital_eur | tin | tae | firma | confianza | estado |
| 2 | 47829153K | Martínez Solé, Elena | personal loan | 7,490.00 | 8.25 | 9.14 | 2019-03-12 | 0.98 | complete |
| 3 | 53921487M | Ferrer Oliva, Andrés | revolving card | 3,000.00 | 22.08 | 24.51 | 2021-10-04 | 0.97 | not in the data tape |
| 4 | 00000000X | Rovira Munt, Clara | personal loan | 12,000.00 | 7.90 | 8.71 | 2020-06-30 | 0.99 | complete |
| 5 | X4471629T | Novak, Petar | consumer finance | 4,318.22 | n/a | n/a | n/a | 0.41 | agreement missing |
| 6 | B62144809 | Distribuciones Berga SL | credit facility | 45,000.00 | 6.40 | 7.02 | 2018-11-15 | 0.96 | complete |
filesissuessummary
Illustrative example with fictional data. The identifiers are not valid.
From scattered files to organised case files.
MestrIA identifies each document and groups it into its case file. It checks information across sources and flags missing documents so your team can focus its review on issues.
Batch of 12,480 files · 4 documents per file · 2 to exceptions
File MC-3744408
Martínez Solé, E.
Agreement
personal loan · 9 pp.
✓
Balance certificate
as at 30/06/2024 · €4,812.44
✓
Transaction statement
04/2019 to 06/2024 · 63 entries
✓
Signature evidence
qualified seal · 12/03/2019
✓
Cross-checks
✓
borrower · agreement = certificate
Martínez Solé, Elena
✓
certified balance = sum of transactions
€4,812.44
✓
signature · seal and timestamp recorded
12/03/2019
File complete
Ready for professional review
4 of 4 documents · 3 cross-checks · traceable per field
1,847 files ready · 293 waiting on a document
Every field, linked to its source document.
From the result back to its source: each field retains a reference to the document and page it came from. Your team can check the data in context and review discrepancies before using it in your operations.
Extracted data · Source evidence
Personal loan agreement
p. 1 / 9
Borrower
MARTÍNEZ SOLÉ, ELENANIF 47829153K · address C/ Marina 142, 4º 2ª, Barcelona
Signature date 12 March 2019
Principal advanced €7,490.00
Term 60 monthly payments · instalment €158.42
Nominal rate 8.25% · APR 9.14%
Clause 10.2 · default interest
Two points above the ordinary rate
Co-borrower FERRER OLIVA, ANDRÉS
MestrIA Engine v3
evidence per field
titular0.99
Martínez Solé, Elena
nif1.00
47829153K
capital_inicial0.99
€7,490.00
tae0.98
9.14%
cotitularreview
Ferrer Oliva, A. · not in the data tape
5 of 34 fields
p. 1 · entry 4
▪ Solutions
Solutions built for your workflows.
Portfolio due diligence and boarding, contract and land registry extraction, judicial document preparation and management, and property document auditing. Choose your workflow to see the documents you provide, what MestrIA checks and what your team receives.
Choose your workflow
Asset tracing
Debt recovery 01 / 09
OAP reading and classification
Reads PNJ reports, identifies balances, income and assets, and automatically classifies results by debtor. Prioritise cases with identified assets and distinguish no findings from cases needing more information.
01 · Input documents
PDFAsset enquiryPNJ · Debtor ABalance: €250.001 property identified
PDFAgency responsesAEAT · SEPE · CatastroReference dates and response status
02 · Output
Debtor classification
Debtor A€250.00 · 1 property
FindingsDebtor BIn the responses received
No findingsDebtor CSome institutions have not replied
IncompleteFindings and coverage kept separate. Each value retains its date and source.
Illustrative example · Fictional data
For your team
Prioritise recovery: identify balances, income and assets for seizure review without reading every report manually.
The appropriate action and eligibility for seizure are validated in professional review.
Explore solution
Format based on a real report · Fictional identities, amounts and dates
INPUT · PDF / ATTACHMENTS
One PDF, several documents
7 pagesComprehensive asset enquiryResponses from authorities and institutions
2 pagesProcedural orderAttached court document
1 pageLexNET receiptSending and delivery record
COMPREHENSIVE ASSET ENQUIRYEnquiry details · Debtor A
Services consulted
- AEAT · Extended account informationLast-quarter balance: €250.00Balance at 31 December: €450.00
- AEAT · Annual incomeAnnual remuneration: €18,000.00Example tax year: 2024
- Catastro · Cadastral data1 property · Cadastral value: €32,000.00
- SEPE · BenefitsStatus: BAJA (discontinued) · Monthly amount: €0.00
- Financial institutionsSome institutions have not yet responded
This view follows the supplied PDF: asset enquiry and attachments. The sample workbook summarises the asset information; court attachments are kept separate.
OUTPUT · STRUCTURED EXCEL
One row per debtor, with dates and statuses kept distinct.
resumen_patrimonial.xlsx
| Name | Tax year | Annual income € | Monthly income € | Accounts with balance>0 | Total positive balance € | Properties | Property value € | Vehicles |
|---|---|---|---|---|---|---|---|---|
| Debtor A | 2024 | 18.000,00 | 0,00 | 1 | 250,00 | 1 | 32.000,00 | 0 |
Detail sheets
SummaryCoverageAccountsRecurring incomePropertiesVehicles
A summary that preserves context
Identified assets
One account with a reported balance and one property. Details retain ownership, date and source.
Historical income
Income for tax year 2024 is not current monthly income. The SEPE benefit is recorded as discontinued.
Pending response
Some financial institutions have not replied. A missing response does not mean a zero balance.
The output shows the documentary record to support review of possible enforcement. A professional determines whether assets can be seized and what action is appropriate.
AUTOMATIC CLASSIFICATION
From the report to the cases worth reviewing first.
MestrIA classifies findings by debtor and keeps coverage in a separate column. Prioritise possible enforcement opportunities and locate missing information.
| Debtor | Classification | What was identified | Coverage and next step |
|---|---|---|---|
| Debtor A | Assets identified | Reported balance: €250.00 · last quarter. One property identified. | Responses outstanding. Check dates and possible enforcement using available evidence. |
| Debtor B | No assets identified | No positive balances or assets in the responses reviewed. | Expected responses received. Record the result and enquiry date. |
| Debtor C | Information pending | Insufficient responses to classify the findings. | Review coverage and complete information through the team’s channels. |
A reported amount is not automatically the amount available for seizure. A professional checks ownership, dates and the appropriate action.
See the difference between “no data” and “pending”
| Name | Service | Status | Context |
|---|---|---|---|
| Debtor A | AEAT · Accounts | OK | Reported balance with reference date |
| Debtor A | AEAT · Funds | SIN_DATOS | Response received with no data |
| Debtor A | SEPE | OK | The response records a benefit as BAJA (discontinued) |
| Debtor A | INSS | ERROR | The service returned an error message |
| Debtor A | Financial institutions | PENDIENTE | The cover sheet says OK, but the response page says some institutions have not replied |
Excel for review and analysis; structured JSON for integrations such as Kmaleon, according to the contracted solution. Processes supplied reports without external queries.
Land registry extracts
Real Estate 02 / 09
Land registry extracts
Converts land registry extracts into structured property, ownership and charge data. Supports asset analysis and flags ambiguities and normalisation issues.
01 · Input documents
PDFRegistry extract · Property AProperty descriptionOwnership and charges
PDFBatch of registry extractsOne or more properties per document
02 · Output
Structured property record
- Property / CRU
- A · 00000000000000
- Ownership
- Owner A · 50% / Owner B · 50%
- Charges
- 1 mortgage · Lender A
Cadastral referenceIncomplete reference in the extract
ReviewOwners, rights and charges linked to their property and source document.
Illustrative example · Fictional data
For your team
Analyse batches of properties without transcribing each extract. Reduce errors linking owners and charges.
Contract extraction
Credit portfolios 03 / 09
Bulk contract extraction
Transforms batches of agreements into structured data on parties, amounts, dates and financial terms. Organises results for analysis, review and use in your processes.
01 · Input documents
PDFLoan agreementBorrowers and guarantorsAmounts, dates and rates
PDFCards and vehicle financeTerms by product
02 · Output
Data ready for analysis
- Product
- Vehicle finance
- Main borrower
- Person A
- Co-borrower / Guarantor
- Person B / Person C
- Principal / Nominal rate
- €12,000.00 / 8%
Agreement A · Pages 1–3. Card terms remain separate for each payment mode.
Illustrative example · Fictional data
For your team
Avoid copying fields from thousands of contracts. Reuse the data in due diligence, boarding and claim preparation.
Due diligence
Credit portfolios 04 / 09
Portfolio document due diligence
Cross-checks portfolio data against the available documentation. Identifies differences, information without documentary support and missing documents to guide the review of each transaction.
01 · Input documents
PDFSeller documentsConsumer · Cards · AutoAgreement · Terms · Signature
XLSXData tape + requirementsPortfolio dataAgreed delivery / SLA
02 · Output
Coverage by account
Account A · Consumer loan
AgreementBorrower and amount cross-checked
ReceivedGeneral termsRequired in the agreed delivery
MissingSignature evidenceLinked to account A
ReceivedReceived documents, missing items and differences against the data tape.
Illustrative example · Fictional data
For your team
Check whether you received what was agreed. Focus the team on missing items and discrepancies instead of reviewing every PDF.
Portfolio boarding
Credit portfolios 05 / 09
NPL portfolio document boarding
Prepares the document inventory and data needed to bring a portfolio into your operations. Organises documentation by transaction and defines checks and delivery format according to your management system.
01 · Input documents
PDFIncoming portfolioDocuments by accountLoans · Cards · Auto
MAPTarget schemaAgreed fields and formats
02 · Output
Delivery mapped to your system
Extracted fieldTarget field
Account number
account_idMain borrower
borrower_nameOriginal principal
original_amountAccount BRequired certificate not provided
ReviewProject-specific scope: inventory, validation and delivery format.
Illustrative example · Fictional data
For your team
Speed up portfolio onboarding with normalised data and a separate exception list before loading your system.
Claim preparation
Legal operations 06 / 09
Document preparation for legal claims
Brings together data from agreements, certificates and other case documents. Cross-checks information and flags inconsistencies and missing documentation before legal review.
01 · Input documents
PDFAgreement and signing recordParty A · Account A
PDFBalance certificateAmount: €3,000.00
XLSXAssignment listAmount: €3,100.00
02 · Output
Case file ready for review
Party and accountAgreement · Certificate · Signing record
MatchClaim amount€3,000.00 vs. €3,100.00
MismatchClaim dataIssuesMissing docsSummary
Each value retains its document and page. Legal review before proceeding.
Illustrative example · Fictional data
For your team
Reduce manual preparation and spot inconsistencies before assembling the claim.
Explore solution MestrIA
Illustrative example · Fictional documents and data
01 · Upload the case file
Different documents. One operation.
PDF · 01
Agreement
Particular conditionsParty A · Operation A
Nominal rate 8%
Fictional example · 1 / 1PDF · 02
Certificate
Operation balanceOverdue instalments · €600
Outstanding principal · €2,400
Fictional example · 1 / 1PDF · 03
Signing record
Evidence of executionParty A · Operation A
Signature and date
Fictional example · 1 / 1PDF · 04
Statement
Drawdowns and transactionsDate · Description · Amount
Operation references
Fictional example · 1 / 1XLSX · 05
Assignment
Operation listOperation A
Reported amount · €3,100
Fictional example · 1 / 1Data is read from the documents. The list provides a comparison; a discrepancy does not overwrite the documentary value.
MestrIAClassify
Extract
Cross-check and verify
02 · MestrIA extracts and cross-checks
Structured data. Visible differences.
XLSX · expediente-operacion-a.xlsx
| Check | Document source | Comparison | Result |
|---|---|---|---|
| Party and operation | Agreement: Party A · Operation A | Certificate and signing record: match | Match |
| Claim amount | Certificate: 600 + 2,400 = €3,000 | Assignment: €3,100 | Review · €100 difference |
| Default interest · Loan | Agreement: nominal rate 8% + 2 percentage points | Certificate: 10% | Match · 10% |
Every field retains its document and page. Cut-off dates and amount definitions are checked before drawing conclusions about differences.
CLAIM DATA
One row per case with data for the law firm’s template.
ISSUES
Differences and readings requiring review, with supporting evidence.
MISSING DOCUMENTS
Outstanding documentation. If a required source is missing, the case remains on hold.
SUMMARY
Batch overview by status: ready, review, on hold or defective.
03 · Receive a four-tab workbook for claim preparation and legal review. The law firm prepares the claim in its own tool; MestrIA does not file it.
- Input
- Agreement, balance certificate, signing record, statement and assignment list.
- Result
- Workbook with claim data, issues, missing documents and batch summary.
- Scope and review
- Legal review determines document sufficiency and the appropriate action. This example does not draft or file a claim.
Case reconstruction
Legal operations 07 / 09
Judicial case reconstruction
Classifies documentation and orders the milestones needed to reconstruct the history of proceedings. Links each milestone to its source and makes gaps in the available documentation visible.
01 · Input documents
PDFLegal case folderClaim · Orders · Procedural noticesCopies and receipts
PDFUnordered documentsDifferent dates and senders
02 · Output
Case history
- 10/02/2026Claim filedClaim + filing receipt
- 18/02/2026Claim admittedDecision · Page 1
- Not providedReferenced noticeReferenced in a later decision
- 20/03/2026Subsequent actionProcedural notice · Page 2
Milestones linked to source documents. Missing items are flagged when supported by evidence.
Illustrative example · Fictional data
For your team
Understand the case history without rereading the entire folder. Simplify handovers and avoid repeated reviews.
Court notices
Legal operations 08 / 09
Court notice classification
Identifies the type of decision, court, proceedings, parties and time limits stated in each notice. Prepares the information for review and transfer to your daily operations.
01 · Input documents
PDFIncoming noticeLexNET · Court representativeDecision and attachments
PDFDaily document intakeMultiple proceedings
02 · Output
Notice identified
- Case / Court
- A-2026 · Court A
- Document type
- Procedural order
- Effect / Recipient
- Request to remedy a defect · Party A
- Stated time limit
- “Ten days”
Review queueA-2026
Action requiredTime limit extracted from the document; calculation and action subject to review.
Illustrative example · Fictional data
For your team
Reduce manual sorting of the daily intake. Identify what arrived, which case it belongs to and what needs attention.
Property documentation
Real Estate 09 / 09
Property document audit
Bring registry extracts, permits, certificates and technical documents together by asset. Check statuses and consistency against agreed criteria, cross-check with external public data and prepare an asset record with issues for review.
01 · Input documents
PDFAsset documentsRegistry extract · CertificatesPermits · Reports
DATAExternal public dataCadastral informationProperty identity and data
02 · Output
Cross-checked asset record
Property identificationDocument ↔ Public source
MatchBuilt areaDocument: 90 m² · Public source: 95 m²
MismatchRequired permitAccording to asset requirements
MissingBoth values and their sources are retained for review.
Illustrative example · Fictional data
For your team
Reduce manual searching and comparison. Locate missing documents and differences to review each asset’s document file.
Need a connection or an additional solution? We review the scope with you.
Book a demoBetween 60% and 90% less time compared with manual processing.
Industries
Solutions specialised in your industry.
01 · NPL
NPL & debt collection
For funds, servicers and debt recovery teams, including law firms and court representatives working with NPLs. From portfolio analysis to judicial case-file documentation.
Explore NPL solutions →02 · REAL ESTATEReal Estate, Property & Facility Management
For owners and Real Estate, Property and Facility Management teams. Bring registry extracts, permits, certificates and reports into each asset’s document file, with structured data and missing documents flagged for review.
Explore the industry →
▪ How it works ▪
A shared foundation for your document solutions.
MestrIA turns unstructured documentation into structured data, cross-checks information and flags issues. Each result keeps its source reference for review and use in your operations.
01
OCR and document reading
Extract printed and handwritten text and interpret drawings, maps and other visual elements to prepare the document’s information.
02
Identification and classification
Recognises what each file contains: an agreement, deed, registry extract, resolution or communication. Identifies the case or asset it belongs to from the available data. Ambiguous or unreadable files are flagged for review.
03
Variable extraction
Extract the variables your operations need: borrowers, amounts, dates, security and the fields agreed for each project.
04
Reconciliation and review
Cross-check variables across documents and against your data tape. Flag discrepancies and data requiring review, with field-level traceability.
Integration
Document intelligence for the system you already use.
Connect MestrIA to your management system —your own, Kmaleon or another solution— and bring structured data, checks and issues directly into your operations.
Portfolio of case files
Case files · PDF documents
- Classify
- Extract
- Cross-check
Management systemYour own · Kmaleon · Another solution
Connect email, SFTP, API or a shared drive. We adapt intake rules, field mapping and delivery formats to your team; ambiguous cases go to professional review.
Technology and trust
Sector knowledge. Control over your information.
Advanced OCR and extraction engines, our own document models and source evidence for your team’s review. Storage and processing in the EU, with deployment, access and retention defined for each project.
How the platform worksIllustrative example · Fictional data
01 Your documents
PDF / 01Loan agreementA. García
Case file 0042
Case file 0042
PDF / 02Account statementBalance: €3,200.00
30 Sep 2026
30 Sep 2026
Folders, PDFs and scans. Every document retains its source.
02 Document reading
Illustrative route
Docling
DoclingText · Tables · Structure
One or more engines, depending on the document and deployment.
03 Sector intelligence
Criteria for each solution
Document types · Fields to extract · Agreed requirements · Reference datatape
Document engineering and processes
Classification
Identifies each document and assigns it to its case file.
Extraction
Captures borrowers, products, dates and amounts.
Audit
Cross-checks documents, data and requirements; flags exceptions.
Our own specialised models, such as MestrIA-v3-2B.
04 Your result
Structured data / 0042
Excel · JSON · API- Borrower
- A. García
- Product
- Consumer loan
- Balance
- €3,200.00
Balance discrepancy
Source: statement · p. 2Datatape: €3,150.00.
Same field and date: 30 Sep 2026.
Integrated engines
The route is configured for each solution; not every engine is used on every document.
- Mistral OCR
- LlamaParse
- Amazon Textract
- Azure AI Document Intelligence
- Docling
- MinerU
- Google Document AI
Data and processing in the EU
Deployment options on your own servers.
Access, retention and deployment conditions defined for each project.
- Controlled access
- Document traceability
- Contractual confidentiality
Available solutions
Impact on your operations
Explore results and try your own batch →
▪ FAQ ▪
Frequently asked questions
MestrIA is the document intelligence platform with specialised solutions for debt collection and real estate assets. Choose the solution, upload your documents and review data and exceptions with source evidence. Email, API and management-tool connections are configured when you need them.
Extracting means reading a value from a document. Reconciling means comparing it with other documents
and the data tape to flag differences. The results support professional review of the file.
The main offer is the MestrIA platform managed in the European Union. Deployment in your cloud, on your
servers or on-premise can be agreed as part of the contractual scope and is validated for each project.
Available modules already include the fields and checks for their use case. You can upload documents to the module enabled for your team. Connections, deployments and additional solutions have their own timeline depending on scope.
Evaluation must state the document type, fields, sample, method and limits. Review criteria are agreed
for each project. An accuracy figure is comparable only when what was measured and under which
conditions are known.
▪ Contact
See how it fits your operations.
Tell us which documents your team handles. See how MestrIA can simplify the work.
Try it with a batch of your documents We agree the sample, expected output and confidentiality with you.
The calendar opens with Calendly.