Banking & Lending Repository Health

The AITS Content Tracking System (CTS) gives an executive one number: a composite Repository Health score. At 98.4%, you know your loan files are complete and agree with your loan records, and you can say so with confidence in any room. At 64%, there is work to do, and the breakdown behind the score shows exactly what it is.

BI charts and reports show you the data. CTS uses AI and machine learning to tell you what it means: how healthy the repository is, what is driving the score, and what to do to improve it.

You choose what healthy means. The score is built from the KPIs that you and your managers select and weight. AITS recommends a proven starting set, and you add to it, drop from it or change the weights as your priorities change.

Behind the score is AI trained on your own loan files. It begins with a health check that establishes where the repository stands today, then keeps the score current around the clock, for every loan and every document as it is added.

For example: a loan on the books with no agreement on file, an agreement that names a different country from its loan, or an agreement dated before the loan was approved. CTS flags it, scores its effect on repository health, and recommends action, before the issue is found in an audit, a dispute or a sale of the loan.

What you receive: the score, the breakdown behind it, and a prioritized list of what to fix first. It is evidence you can show a board, an auditor or a regulator.

You do not have to imagine it. The live demo shows CTS measuring real, public loan records.
Open the dashboard and click on the health score to see the composite makeup.

Most lenders cannot say for the portfolio as a whole. That is the problem: not that the files are known to be deficient, but that their condition is not known until someone opens them.

A lender keeps two sets of records. The loan system holds the terms: borrower, amount, dates, status. The document repository holds the evidence: the agreement, its amendments, and the documents behind them. The two are created by different people, in different systems, at different times. A file review samples a few hundred loans a year. Problems usually surface one at a time: a missing agreement, a document filed under the wrong loan, a date that does not match. Until then, nobody could have known how many more there are.

A loan is only as enforceable as the documents behind it. As you know, three things follow from that:

• Enforceable: the agreement on file is the lender's evidence of the terms. A loan with no agreement on file, or the wrong one, is a risk that sits unseen until it is tested.
• Examined: auditors, regulators and buyers of loans all ask the same question: show me the file. The answer should not depend on which loans they happen to pick.
• Long-lived: a loan and its documents are kept for decades, through amendments, restructurings, system migrations and changes of staff.

Each of those rests on the repository: the agreements, the details recorded for each one, and the link between every document and the loan it belongs to. A discrepancy between the file and the loan book does not stay in the back office. It follows the loan into every review, report and transaction that relies on it.

This matters more as lenders adopt AI. An AI assistant that answers questions about a loan is only as reliable as the documents it reads, and the gains come from finding issues early: each one corrected improves the next result, and the improvements compound.

AITS pointed CTS at two sets of public records from the World Bank: its statement of loans, and the loan agreements it publishes. Every loan and every agreement was checked against a set of KPIs, including how well the two sets agree with each other, and the results were rolled up into one composite Repository Health score. Two pages show the result:

• The CTS Dashboard: the score at a glance, with the breakdown behind it and the recommended actions. This is what an executive sees.
• The Health Report: the dimensions, every KPI with how many loans or agreements passed, the actionable recommendations ranked by the gain each would bring, and where the risk sits region by region.
• Two sets of records, compared: loans and agreements are matched by project. That is what shows a loan with no agreement on file, or an agreement that disagrees with its loan.
• Every record, not a sample: each loan and each agreement was checked as it was loaded, the same way CTS assesses each item as it arrives in an engagement.
• Seven of the eight dimensions were measured. Security was left out, because everything here is already public.

Open the CTS Dashboard Read the Health Report

What this is and what this is not. The score is measured from the published loan records and the details recorded for each agreement, not from the World Bank's internal systems, and against KPIs AITS chose for this presentation. The World Bank would choose its own. A check that fails describes the published record; older loans, for example, may have agreements that were never published online. Nothing was edited. The demo is not endorsed by, or connected with, the World Bank.

CTS is not a fixed set of rules applied to every repository. Its AI is trained on your own records, so it learns what a sound record looks like here. The measuring is automated. The standard being measured against is yours.

It learns how you solve problems. When staff confirm, correct or dismiss a finding, that decision trains the model. CTS learns not only to recognize an issue but how your people resolve it, so the alerts get sharper and the number needing review falls.

You decide how much it does. Every type of issue starts with CTS recommending and a person acting. When you are satisfied it handles a type correctly, you can let it prepare the fix for approval, and later give it standing permission to resolve that type itself. Staff check a sample, every action is logged and reversible, and you can withdraw the permission at any time.

The loan stays with the lender. CTS recommends corrections to repository records: filing, links, duplicates, missing details. It never alters an agreement or a loan's terms. Credit and legal decisions remain yours.

People stay in charge. CTS learns from your loan operations and documentation staff, and their judgement is what it cannot replace. It takes the repetitive work off their desks and leaves them the review, the exceptions and the decisions.

The repository improves with it. Every issue corrected raises the score, and the trend shows whether the repository is getting healthier or slipping. Better records make the AI more accurate, and a more accurate AI finds the next issue sooner. The two improvements compound.

CTS does not run against the official repository or the loan system. The environment is replicated in a secure cloud environment hosted in-country, and the AI is trained and run on that replica. It works alongside the systems you already have, with no platform replacement.

Every item is assessed, from the first to the last. The replica starts empty. Your content is loaded into it in bulk, and CTS assesses each item as it arrives. Existing loans, back-scanned files and new originations all go through the same check, so the score covers the whole portfolio and not a sample.

The official repository remains untouched. Nothing CTS does is destructive, and any result or correction can be compared against the original at any time.

Corrections are made and checked in the replica first. Applying them to the official repository remains the lender's decision, through its own change controls.

Health is not one property. CTS scores the repository across eight dimensions, each built from KPIs the lender defines and weights. These eight are the starting set AITS recommends, and the ones used in the live demo; each rolls up into the composite score, and each can be opened to see what is pulling the score down.