Lending is two decisions. The industry only measures one.

The first decision is a filter, and fifty years of credit infrastructure has been built to automate it. The second decision sets both the revenue and the loss on every loan written — and it is still made by policy. A flat ticket. A multiple of income. A number a credit committee agreed on and nobody has revisited.

This is not an oversight. It is a measurement problem, and a genuinely hard one.

A lender’s own book contains almost no variation in loan amount that is independent of risk — because the lender’s own policy chose the amounts. Safer applicants got more. So if you fit a model of default against amount on your historical book, you do not learn how risk moves with the amount. You recover the policy you already had, with a confidence interval around it. That is why the how much decision has stayed a matter of judgement while the who decision became a science.

It returns an offer-conditioned default probability: not one number per applicant, but a probability for each amount and tenor you could actually offer them. The output is a curve, and your policy ceiling stays exactly where it is. You lend at the furthest point along that curve your own ceiling allows.

It works off the applicant’s repayment sequence rather than the score that summarises it. A bureau score is twelve months of behaviour — who paid, when, how late — compressed into three digits. That compression is good at answering who. It discards precisely the information that answers how much.

Five illustrative borrower profiles on a bullet loan — synthetic, drawn with the same function as the Mentat page, not real applicants. Each row is one profile’s default probability as the amount rises. Note what the shape is: for most borrowers it runs close to flat across a wide range and then bends, sharply, once the repayment crosses what their cashflow carries. The useful information is where that bend sits, and it sits somewhere different for every applicant. Anyone showing you a smooth upward slope is showing you a model, not a borrower.

Take the Intent-strong profile in the chart above — illustrative, not a real borrower. Bureau 745, which clears almost any policy in the market. Income ₹38,000 a month.

A policy engine offers ₹1,14,000 — three times income. At that amount, this profile’s default probability is 15%, because the repayment lands well past what the cashflow carries.

Mentat offers ₹75,000, where the same profile’s default probability is 7.5%.

Same profile. Same bureau report. Same day. Twice the default risk, for half as much again. No score can express that, because the risk is not a property of the borrower. It is a property of the offer.

It runs the other way too. The Capacity-strong profile scores 685, below the 700 cutoff, so the rules engine declines it. Its cashflow carries more than the score suggests: Mentat funds ₹95,000 at 7.8%, inside the same ceiling.

On 400,523 historical leads from a listed lender, scored against that lender’s own live policy as the control:

Those are gains at the same policy ceiling, on the same leads. The lender’s risk appetite did not move. The sizing did.

That is a backtest on their historical book, not a realised result on yours. The model reports 0.84 AUC on held-out Indian retail credit data — an internal evaluation, not independently audited. We publish the population, period, outcome definition and baseline in a methodology note, and we would rather you read it than take the number.

It does not replace your policy. The ceiling, the exclusions and the pricing floor stay yours. Mentat tells you where each applicant and each amount sits beneath them.

It does not claim that risk simply rises with the amount. The curve is mostly flat, then it kinks, and the kink is the whole point.

And it does not pretend the measurement problem away. Mentat is calibrated within amount bands, and we will tell you exactly where the data supports the curve and where it is extrapolating. On a first engagement we run your own declined and approved files and show you, case by case, what a different amount would have changed — because that is the only evidence that should convince you.

In India, more than a billion people are assessed by a system that already holds their repayment history and cannot read the part of it that matters. Most are not turned away. They are handed a number with no relationship to what they could actually carry — and then counted as a credit risk when it breaks.

Pricing the amount is not a feature. It is the half of lending nobody measured.