Home / Prompts / Metrics and the team

Prompt to build a metrics tree for a UPI or lending app

What you get: A north star, input metrics with definitions and an 8-number weekly dashboard. Copy it, fill in the parts in [BRACKETS], and run it in Kriyā or any AI assistant.

The prompt

You are a product analytics lead at an Indian fintech. Build the metrics tree for my app.

App: [APP]
Business model: [MODEL]
Stage: [STAGE]

Give:
1. The north star metric and why
2. The tree: 3 to 5 input metrics and the drivers under each
3. Definitions: the exact event and time window for each metric
4. Benchmarks, using the India figures below where they apply
5. The weekly dashboard: 8 numbers, in order
6. Counter-metrics so we do not grow the wrong way (fraud, defaults, complaints)

Rules:
- Use the India figures listed below and name the source and month next to each one you use.
- If you need a figure that is not listed, write "Assumption:" and give your reasoning instead of a number you cannot source.
- Plain words. Short sections with headings. No filler.

India figures to use (from productgrowth.in/numbers):
- UPI processed 24.07 billion transactions worth ₹29.37 lakh crore in September 2026, according to NPCI data. Source: https://productgrowth.in/numbers/upi-transactions-per-month-india/
- Indians spent ₹2.02 lakh crore on credit cards in August 2026, according to RBI card statistics: ₹79,355 crore at shops and ₹1,22,980 crore online. Source: https://productgrowth.in/numbers/credit-card-spends-india/
- India had 124.05 million credit cards in circulation in August 2026 (RBI). Source: https://productgrowth.in/numbers/credit-cards-india/
Run this in Kriyā → Kriyā opens with this prompt in its box; nothing is sent until you press send. Replace the [BRACKETS] first.

What to fill in

ReplaceWithExample (used for the sample answer)
[APP]Your appA credit card bill payment app with rewards
[MODEL]How you earnInterchange share and partner offers
[STAGE]Stage1 lakh monthly active users

The numbers this prompt uses

The prompt carries these figures so the answer starts from dated, sourced numbers instead of guesses. Each page shows the source, the month and the history.

Sample answer

Sample answer from Kriyā, 26 October 2026, for the example inputs above. Kept as it came back; links added beside each figure.

1. North star

Rewarded Bills Paid per MAU, per month (a bill counts only if the rewards/offer layer was used or credited). Pay-and-leave users earn you nothing. Interchange share and partner offers both need repeat bill volume and reward engagement.

Note: you earn interchange only if your flow generates card-network volume. Confirm what your bank/PA contract actually pays on a bill payment. Assumption: it is a small bps share, so frequency matters more than ticket size.

2. The tree

  • Activation: KYC/card-link done → first bill paid. Drivers: card-link success, OTP/bank-redirect drop-off, time from link to first pay. This is where "zombie KYC" shows up [3].
  • Payment success: Drivers: UPI vs card vs net-banking mix, bank-wise failure rate, retries. See [6].
  • Repeat: Cards with a bill paid in 2 consecutive cycles. Drivers: due-date reminders, autopay opt-in, number of cards per user.
  • Reward engagement: Drivers: reward visibility at pay screen, redemption rate, partner-offer click-to-claim.
  • Monetisable volume: Drivers: spend per bill, share of bills on revenue-sharing rails, offer-partner payout per user.

3. Definitions

  • Activated: card linked and first successful bill within 7 days of signup.
  • Payment success rate: successful ÷ initiated bill payments, same day, excluding user cancels.
  • Repeat rate: cards paid in cycle N that are paid again in N+1, 45-day window.
  • Reward engagement: users with ≥1 reward viewed or claimed ÷ users who paid, 30 days.
  • North star: rewarded bills ÷ MAU, calendar month.
  • MAU: user with ≥1 session or payment in 30 days.

4. Benchmarks

  • Market context: 124.05M credit cards in circulation (RBI, Aug 2026) [4]. Card spend was ₹2.02 lakh crore in Aug 2026 (RBI, per productgrowth.in/numbers).
  • UPI context: 22.7B transactions in June 2026 (NPCI) [5]. The September 2026 figure you supplied, 24.07B and ₹29.37 lakh crore (NPCI), is newer, so use that for current scale.
  • Activation: investment apps see 35–45% D7, lending 20–30%, neo-banking 40–55% (Product Growth knowledge base) [3]. Assumption: a bill-pay app should target the neo-banking range, since first pay is a habitual action. Kriyā's estimate
  • Payment success, repeat rate, reward engagement: I have no sourced India benchmark. Assumption: set your own baseline in the first 4 weeks and improve against it.

5. Weekly dashboard (in order)

  1. Rewarded bills per MAU (north star)
  2. Weekly active payers
  3. New-user activation (D7)
  4. Card-link success rate
  5. Payment success rate
  6. Repeat rate (cycle-over-cycle)
  7. Reward engagement rate
  8. Net revenue per payer (interchange + offers)

6. Counter-metrics

  • Fraud: chargeback and dispute rate; share of payments flagged by risk rules.
  • Defaults: missed-due-date rate among your users; late-fee incidents after your reminders. Aim: reminders reduce misses, never nudge overspend.
  • Complaints: tickets per 1,000 payments, "paid but not credited" cases, and time to resolve. Kriyā's estimate
  • Reward abuse: share of rewards from self-transfers or looping.
  • Compliance: card-data handling under RBI tokenisation rules; DPDP consent for card and contact data. Verify the current rules with your PA.

Next action: Instrument the card-link → first-pay funnel this week, since activation is where the biggest drop usually sits.

Beside each figure: source links the number page it comes from, your input means it came from the example inputs, and Kriyā's estimate marks a figure Kriyā worked out or assumed with no source given; check those before you use them. Your own run will differ.

More prompts for this job