IndustriesNBFCs and lenders
Your team can't call every late payer.
Reminder calls go out in permitted hours on your approved script, every promise is logged, and hardship cases go to a person.
Tested on twenty of your own past calls before it goes live, and kept working as AI changes.
Eashan Gupta, founder. You meet him on the first call.
A sample week of payments due: each one followed up until it is paid, and one dispute brought to a person.
Your week
Your week, as it runs today.
WED 14:20
Bounce lists come in on the 5th, and collection calls start from a printed list.
With AIReminders go out before the due date, and calls follow within permitted hours, with every promise logged.
THU 21:00
A borrower complains that a recovery agent called at 9 pm.
With AIEvery collection call is recorded and checked against the rules.
FRI 18:50
The quarter's RBI return needs data from four systems.
With AIRegulatory returns are assembled with each figure traced to its source.
MON 09:10
Loan files arrive as phone photos of bank statements, tax returns and property papers.
With AIFiles are read into the loan system with a confidence mark on every field.
TUE 11:40
A credit analyst reads 200 pages to write one appraisal note.
With AIThe appraisal note is drafted with each figure linked to its page.
What it costs
Loan files read by hand.
Our analysts read hundreds of pages for every loan.
5analysts
to read 100 loan files a month, at a day for each 200 page file
Our own sum, 2026
100 files a month ÷ 20 files an analyst = 5 analysts
What we'd build
Ten systems we'd build for lending.
The first three come first. The rest wait until those pass on your own past calls.
- Collection callsFor youReminder call, approved scriptBorrower, callPromisedA hardship case, passed to a personCollections officerFor youWithin permitted hoursSample data · Powered by Agentec
Collection calls within the rules
- Loan file readerFor youStatements, returns and GST readLoan fileRead2 fields unsure, sent to a personCredit deskFor youOnly doubts reach a personSample data · Powered by Agentec
Loan file reader
- Appraisal noteFor your yesAppraisal drafted from the fileLoan fileDraftedEvery figure linked to its pageCredit officerFor your yesThe officer decidesSample data · Powered by Agentec
Appraisal note drafts
And 7 more
Built before
The nearest work we've built.
None of it is in your trade yet.
Conference apps in two languages
Delegates carry the whole day on their phone, in Japanese or English at a tap.
Built for an industry body in Asia Pacific, used at its meetings in Bengaluru and Tokyo.
Before you call
What lenders ask first.
Does it decide a loan?
No. It reads the file and drafts the appraisal, with every figure linked to its page, and your credit officer decides.
Do collection calls follow the RBI's rules?
Yes. Calls go only in permitted hours, on your approved script, and every hardship case goes to a person.
Who decides what gets built first?
You do, after 45 minutes with Eashan. We bring the week we counted and the first three we would build, and you pick the one that matters most to you. Nothing is built until you say yes in writing.
Who says yes before anything goes out?
The person who owns that job at your company today. You name them when we write the rules with you. Inside those rules the AI agent acts at once. Anything outside them waits for one tap from the person named, on their phone, ready to approve or to change.
What does it cost?
There is no price on this page, because it depends on the work. After 45 minutes with Eashan you get a written proposal with the scope, the test it has to pass, who works on it and one fixed price, before any work.
It works today. We keep it working tomorrow.
How it works- Work it out, most consultants stop here
- Build it, most software firms stop here
- Run it
- Answer for it
- We stay
45 minutes with Eashan, on your lending business.
The people who live with the problem come too. You leave knowing what we'd build first, and why. Nothing to sign.
What stays yours
- Your accountsin your company's name
- Your codeevery line of it
- Personal dataabout your customers and staff, on your own machine unless you approve otherwise in writing
- Plain files and a how-to guideif you stop
Eashan Gupta, founder. You meet him on the first call.