Check a company registration document in seconds: Koncile reads the file and cross checks the registry, then scores the risk from 0 to 100.
Create a free account to run the analysis.
Create a free accountFor document volumes or an API, talk to an expert.
The company document checker used by insurers, banks and large companies
4.8 / 5
A fake company document rarely shows to the eye, and an authentic certificate edited after issue still carries a file number the registry knows. The fake company document detector checks the file, the image, public registries and the consistency of the whole file, on five levels.
Companies are formed state by state, and each Secretary of State issues its own certificates, with its own layout, seal and file number format. We check the document against its stated issuer and flag a PDF rebuilt in Word, Canva or a PDF editor.
An edited PDF often keeps its earlier versions. We rebuild them: a former officer, a former address or an older status date reappears next to the new one. A file number that checks out at the registry does not prove the PDF you hold matches the original.
A scanned or photographed certificate has no metadata left. Our image model, trained on fakes, spots cloned areas, white patches, text laid over the original, seals pasted from another document and pages generated by AI, then checks whether they touch a field that matters.
AI detected82/100Where the formation state offers a public business search, the entity name, file number, status and formation date are compared with the Secretary of State record. A certificate of good standing for an entity the registry shows as dissolved is a strong signal.
The officer who signs must appear on the formation documents and match the ID in the file. The legal name on the IRS EIN letter must match the articles, and the address must match the bank statement and invoices. Koncile extracts these fields from every document and flags the gaps.
Without a tool, these three checks stop clumsy fakes in ten minutes. A tip: ask for the PDF as downloaded from the state or the IRS rather than a scan, to check the metadata as fully as possible.
A certificate of good standing is a snapshot on its issue date: ask for a recent one. The file number must follow the state's format. The EIN shows on the IRS CP 575 notice, sent once when the number is assigned, or on a 147C letter: the legal name must match the articles exactly.
Use the business search of the formation state: name, file number, status, formation date, registered agent, and officers where the state lists them. Delaware warns that its free search is not a statement of good standing. Then check that the signatory is an officer: a real certificate shown by a stranger is the quietest fake.
Use our free PDF metadata viewer and look at Creator, Producer and the timestamps. A certificate comes out of a state filing system, an EIN letter out of the IRS. Word, Canva or a PDF editor are often red flags, and an edit after the issue date deserves a question.
Koncile's fraud detection API gives you a score (0-100) and detailed explanations of manipulation risks, right inside your own tools.
Entity name, state, file number, officers, status and issue date.
High, medium or low level, with a one sentence explanation.
High risk from 80.
A one line summary ready for your information system.
curl -X POST https://api.koncile.ai/v1/upload_file \ -H "Authorization: Bearer $API_KEY" \ -F "files=@certificate-of-good-standing.pdf"requests.post("https://api.koncile.ai/v1/upload_file/", headers={"Authorization": f"Bearer {API_KEY}"}, files=[("files", open("certificate-of-good-standing.pdf", "rb"))]){ "status": "DONE", "General_fields": { "Entity_name": {"value": "Northfield Tooling LLC", "confidence_score": 0.99}, "Issue_date": {"value": "2026-09-14", "confidence_score": 0.98} }, "Fraud_detection": { "risk_score": 79, "summary": "PDF edited after issue: issue date changed", "signals": [ {"name": "Traces of edits", "severity": "high"}, {"name": "Editing software", "severity": "medium"} ] }}Wherever a company document opens an account, a credit line or a vendor record, a fake is costly. Here is where the checker fits in.
Banks and fintechs check formation documents at onboarding, with the officers' IDs. Under FinCEN's customer due diligence rule, they still identify anyone who owns 25% or more of the entity and one person who controls it.
Business documents are checked at the same time as identity and ownership. The detail of every test is kept, for internal audit and for examiners alike.
Before funding, the certificate, the EIN letter and the business bank statements are checked together, at the same legal name and address. A business that claims five years but was formed last month shows in the registry.
Vehicles, machines, IT: the lessee's formation documents are checked with the rest of the file before the asset leaves. A dissolved entity or an edited certificate is stopped before the contract is signed.
At underwriting, company documents prove who the policyholder is and what it does. Anomalies are flagged before the policy is bound, with a score the underwriter can explain.
A fake vendor needs a company document and bank details to get paid. Both are checked together when the vendor is created, before the first invoice reaches accounts payable.
Some edits leave no visible trace: an officer's name swapped, a status date moved forward, an address changed. The fake company document detector relies on signals invisible to the naked eye: traces left by PDF editors and AI tools, the way the file was written, and public registries.
| Document element | What Koncile checks | What gives an edit away |
|---|---|---|
| Issuing software | Creator and Producer compared with what a state filing system or the IRS produces | Word, Canva, a PDF editor or a Python script instead of a government system |
| Dates and timestamps | Creation and modification dates, compared with the certificate's issue date | An edit dated after issue, rewritten or missing dates |
| Saved versions | Versions appended at the end of the file, dormant objects | A former officer, address or status still inside the file |
| File writing style | Object order, cross reference table, the way a version is appended | pypdf, MuPDF or qpdf instead of the issuer's system |
| Image | Scan or photo: cloned areas, white patches, text laid over, AI generation | A name pasted on a scan, a seal copied from another certificate, an AI generated page |
| Issue date and status | Date of the certificate of good standing and the status it states | A date moved forward, good standing claimed for a delinquent entity |
| File number and EIN | State file number format, nine digit EIN on a CP 575 notice or a 147C letter | A number in the wrong format, an EIN letter whose legal name differs from the articles |
| Public registries | Entity name, file number, status and formation date in the Secretary of State business search, where available | A dissolved, forfeited or unknown entity, a formation date that does not match |
| Consistency across the file | Officers and address compared with the ID, bank statement and invoices of the same file | A signatory who is not an officer, an address that differs on the bank statement |
A KYB file brings together formation documents, officers' IDs, beneficial owners and bank details. Founded by a former lawyer, Koncile was built with data protection at the core of its architecture: third party SOC 2 audit, GDPR compliance, secure hosting. Documents are encrypted, deleted after analysis and never used to train a model.
It is a tool that combines several technologies to spot the anomalies that give away an edit or a fraud: machine learning that analyses the image, and analysis of the PDF file, which is written like code. The goal is to stop the few percent of fakes that slip into your business onboarding.
You never know for certain: you measure a risk. It becomes high when one test goes over its threshold, such as a former officer's name found inside the file, or when several tests point the same way: unexpected software, an edit after issue, a retouched image. That body of evidence is what should raise the alarm.
It can help, mainly to spot inconsistencies in context. It lacks three things: models specialised in images edited or generated by AI, knowledge of the traces each editing tool leaves, and a base of how real issuers write their files, which brings the mismatches out. A language model is only one part of the machine.
It depends on your volume. The price combines a base subscription and a cost per page or per document processed. The plans are detailed on the pricing page.
Search the entity on the Secretary of State site of the formation state: status, file number, formation date. A certificate is a snapshot on its issue date, so ask for a recent one, and note that Delaware's free search is not itself a statement of good standing. Then check the PDF for edits after issue.
There is no public EIN lookup. The IRS TIN Matching service is reserved for payers that file information returns. For onboarding, ask for the CP 575 notice, sent once when the EIN is assigned, or a 147C letter, which the IRS issues on request. Compare its legal name with the articles, and check the letter as a file.
Not US companies. An interim final rule of March 2025 exempted domestic entities from Corporate Transparency Act reporting, and FinCEN made the exemption final in August 2026. Foreign companies registered to do business in a state may still have to file. Banks still collect beneficial ownership under the customer due diligence rule.
Yes, when it is used to deceive a lender or anyone else for a gain. 18 U.S.C. § 1014 punishes a knowingly false statement made to influence an FDIC insured bank on a loan or credit application: up to 30 years in prison and a $1,000,000 fine. State forgery laws apply too. Keep the original file and the analysis report.
Yes. Koncile complies with SOC 2 and GDPR, and an independent firm certifies our security and data protection. Your documents are hosted securely with a provider that itself holds SOC 2 and ISO 27001 certifications.
Each document gets its own method: a proprietary ML model for photos, known metadata and forensics for native PDFs, and contextual cross checks.
Inflated balances, deleted lines, a PDF rewritten with software other than the bank's.
See the detection
Net pay changed, contributions that do not match gross pay, a layout that does not match the payroll software.
See the detection
Photo replaced, date of birth or number changed, an MRZ that no longer matches the fields.
See the detection
Edited amounts, wrong VAT, duplicates and made up suppliers.
See the detectionUpload your bank statements, pay stubs or IDs: Koncile extracts the data and flags fakes in seconds.
Talk to an expert
