Loan Term Agreements, AI that reads loan contracts
For Afreximbank, STEPS built an AI platform that reads loan agreements, automatically extracts their covenants and turns them into structured, queryable data.
LOAN AGREEMENT, ART. 12
The Borrower shall maintain a Debt Service Coverage Ratio of not less than 1.25x, tested semi-annually. The Borrower shall deliver audited financial statements within 120 days after the end of each financial year. Any disposal of assets above USD 5 million requires the prior written consent of the Lender.EXTRACTED COVENANTS
Commitments buried in hundreds of pages
Every loan agreement contains covenants: financial ratios to maintain, documents to deliver, operations requiring consent. Tracking them means knowing them, contract by contract.
Long contractsLoan agreements often run to dozens of pages, with schedules and amendments.
Manual readingLawyers and monitoring teams used to record clauses by hand in spreadsheets.
Hard to monitorWithout an overview, a deadline or a threshold can go unnoticed.
A compliance riskAn unmonitored covenant is an undetected credit risk.
From contract to data, in three steps
Dozens of pages per contract, scattered obligations: the platform makes covenants visible and trackable.
Loan agreements are uploaded to the platform, as PDF or Word, with their related facility.
AI identifies covenants, conditions and obligations, and classifies them by type.
Each clause becomes structured data that teams can filter and query.

Upload, extract, review
Lawyers upload a contract, follow the extraction and find each covenant with its original excerpt. Legal review focuses on validation.
All covenants, on a single screen
Each contract produces a results sheet: covenants by category, processing status and direct access to the source text.
What the platform changes for the bank
Covenants become monitored data, no longer text to reread.
The bank has a structured view of all its borrowers' commitments, strengthening credit risk monitoring throughout the life of the loan.
Lawyers validate an extraction instead of rereading everything.
All obligations are identified and classified automatically.
Finding every contract with a DSCR ratio takes seconds.
Each covenant is linked to the contract excerpt it comes from.
Structured data feeds deadline and threshold monitoring.
The same method applies to hundreds of contracts.
12 months, from design to go-live
Covenant typology, contract formats and needs of the legal and credit teams.
Design of generative AI extraction chains and tests on real contracts.
Development of the ingestion, results and search interface.
Validation with the lawyers, adjustments and production deployment.
Under the hood
A document intelligence chain combining file reading, generative AI and a structured database.
- InputPDF and Word contracts, with their related facility
- ReadingText extraction and splitting by clause
- AnalysisGenerative AI that identifies and classifies covenants
- StorageStructured database, filterable and queryable
- InterfaceWeb platform for ingestion, review and search
Frequently asked questions
Which documents does the platform process?
Loan agreements and their amendments, as PDF or Word.
Can what the AI extracted be checked?
Yes. Each covenant is linked to the contract excerpt it comes from, for quick validation by lawyers.
Can it be extended to other contracts?
Yes. The same principle applies to guarantees, financing agreements or supplier contracts.
Do your teams still read contracts line by line? Let's talk about your document AI.
Book a scoping session ↗