First Abu Dhabi Bank's customers get their credit approvals, loans and cheques processed without waiting on paper.
First Abu Dhabi Bank wanted its customers' applications and accounts handled without delays from paper, and its service to keep running even if a data centre failed.
What changed
What stood in the way.
- The document management system ran on Documentum 6.5 and Captiva 6.0, both nearing end of life.
- Scanning and indexing were slow to load, and the system handled only a few document types.
- There was no backup site if the primary data centre failed or its data was corrupted.
- Document-heavy processes and access to sensitive banking records needed to be organised by role.
- 150+document-heavy workflows digitized (as reported)
- 0%system downtime (as reported)
- 10xincrease in productivity (as reported)
What we built.
- An upgrade to Documentum 7.x, with tight control over who can open and edit each document, fast search and standard APIs to other systems.
- Captiva 6.5 and InputAccel to capture, classify and extract over 28 document types into one central repository.
- About 150 document-heavy business processes automated, including credit approval, equities and expenses, loan operations, wealth management, cheque clearing and trust receipts.
- A disaster recovery site designed around agreed recovery point and recovery time objectives.
- Role-based access and a browser-based interface that works across desktop browsers, alongside the bank's T24 core banking system.
- Documentum 7.x
- Captiva 6.5
- InputAccel
- Temenos T24
What this work shows about us.
Credit approval, loan operations, cheque clearing and trust receipts are the document-heavy steps behind a customer's wait, and they were digitized as one system.
A disaster recovery site sized to the bank's own recovery targets keeps service running through an outage.
Want to upgrade your bank's document management system like this? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.
Start your plan ↗If we built it today, with AI.
This work came before today's AI. If First Abu Dhabi Bank (FAB) asked us now, this is what we would add, step by step.
An agent would read each scanned document as it arrives, check it against the checklist for that credit or loan application and tell the officer exactly what is missing. The capture and classification rules still run as configured.
An agent would assemble the credit approval pack from the stored documents and highlight anything inconsistent for the credit officer. The officer still makes every decision.
An agent would find the right document for a customer's query in seconds, within the user's access rights, and draft the reply. Staff check and send it.
Where this work fits.
- LendersYour customers are meant to get the loan they need, without chasing anyone.
- A leading Indian general insurerThe insurer's customers upload their policy documents and get served without the system slowing down.
Facts and figures from the project records; nothing added.
Want this for your business?
Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.
Send us a note instead
An AI agent. This prototype uses prepared answers and sends nothing.
We use essential cookies to run this site. With your consent we also use analytics cookies to see which pages help. Privacy policy