BFSI · AI, Technology
Low code workflows for loan processing that a financial services firm's own teams now run
A mid sized financial services firm wanted to automate loan processing, customer onboarding and compliance reporting, but its small IT team had a backlog measured in months. We set up low code workflows on AksharAI with AI assisted credit checks and automated regulatory reports, and loan approvals became 60% faster with zero compliance errors.
60%Faster loan approvals0Compliance errors40%Lower cost of software development and maintenance- Client
- A mid sized financial services firm offering MSME and personal loans in India
- Region
- India
- Sponsor
- Chief operating officer and head of compliance
- Duration
- 10 weeks to the first live loan workflow, then 3 months of coaching while business teams took over
Engagement model
FDE: Forward Deployed Engineering
Our engineers sat with the credit, operations and compliance teams, built the first workflows alongside them on AksharAI, and then coached their analysts to build and change flows themselves.
How FDE worksThe team
- Engagement lead1
- Forward deployed engineer3
- AI engineer1
- QA engineer (shared)1
The challenge
Where things stood
- Loan files moved between sourcing, credit and operations by email and courier, and a file could sit in someone's inbox for days without anyone knowing.
- Credit officers re-keyed bank statement and bureau data into a spreadsheet for every application before they could start an assessment.
- Monthly regulatory returns were compiled by hand from three systems, and the compliance head checked them line by line before filing.
- Every change to a form or approval rule went into the IT queue, where it competed with core system work and often waited months.
The approach
How we ran it
Weeks 1 to 2
Process mapping with the business
We followed a dozen live applications from sourcing to disbursement with the credit and operations teams, and listed every hand off, check and approval limit.
Weeks 2 to 10
First loan workflow
We built the MSME loan flow on AksharAI's drag and drop builder: application capture, document collection, credit checks, sanction by approval limit and disbursement request, connected to the core lending system.
Weeks 6 to 12
AI assisted credit checks
We added a model that reads bank statements and bureau reports, fills the assessment sheet and flags exceptions for the credit officer. The officer still makes every decision and can see why each flag was raised.
Weeks 10 to 22
Compliance reporting and handover
We automated the regulatory returns from the workflow data with checks before filing, then coached analysts from operations and compliance to build the onboarding and collections flows themselves.
What it looks like
Representative screens
Drawn to show the kind of system we delivered. Client screens and data stay private.
MSME loan pipeline, Ahmedabad branch
Documents pending2
- LN-2026-03318, packaging unit, ₹18,00,000
- LN-2026-03322, dairy unit, ₹6,50,000
Credit review2
- LN-2026-03297, fabrication unit, ₹32,00,000
- LN-2026-03305, organic foods unit, ₹9,75,000
Sanction1
- LN-2026-03284, logistics firm, ₹45,00,000
Ready to disburse2
- LN-2026-03271, garment unit, ₹12,40,000
- LN-2026-03266, electrical contractor, ₹7,20,000
Application LN-2026-03297
- Borrower
- Fabrication unit, Vatva GIDC, Ahmedabad
- GSTIN
- 24AAPFM4821K1Z6
- Amount requested
- ₹32,00,000, term loan, 48 months
- Average bank balance
- ₹4,86,200 over 12 months
- Bureau score
- 762, no overdue accounts
- Flags
- 2 cheque returns in March 2026, review
- Application and KYC complete, 02 Oct
- Statements and bureau read, assessment filled, 03 Oct
- Credit officer review, Ankit Shah
- Sanction by branch credit committee
- Disbursement request to operations
What we delivered
Modules and features
- MSME and personal loan workflows from application to disbursement request
- Customer onboarding with KYC document checklist and status updates by SMS
- AI assisted reading of bank statements and bureau reports into the credit assessment
- Sanction routing by loan amount, product and branch approval limits
- Automated regulatory returns with pre filing validation and an audit trail
- A builder workspace where business analysts design, test and publish their own flows
What changed
Outcomes
- 60%Faster loan approvals
- 0Compliance errors
- 40%Lower cost of software development and maintenance
- Regulatory reports generated straight from the system
- Business teams now build and deploy their own workflows without waiting for IT
Figures as reported by the client.
We no longer need to wait months for IT development.
Looking back
Building the first workflow side by side with the credit team is why their analysts were confident enough to build the next flows on their own. The core lending system was the main constraint: its API covered disbursement but not loan amendments, so for the first two months operations still keyed amendments in twice. We would now test every integration point with real transactions in the first fortnight, before promising which steps the workflow will cover.
Start a conversation
Discuss a similar project
Tell us where your team is today and we will walk you through how a project like this would run for you under FDE. The first conversation is free. Delivery work is paid only after you accept it.
A specialist replies within one working day. The first conversation is free.