Skill ID: R5

FOIR / DSCR Calculator & Stress-Test

Ratios that still hold when income drops or rates rise.

Paste it into Claude, ChatGPT or Gemini. It introduces itself and tells you what to share.

Risk & UnderwritingCompliance load MedHuman review requiredRuns on Claude, ChatGPT or Gemini

What you get

Feed it
Product, proposed EMI or loan terms, income details and every existing obligation.
You get
A stress table for base, income down 20%, rates up 200 bps and combined, with an eligibility line.
Takes
A couple of minutes, on whichever LLM your team already opens.

Why this beats a prompt you'd write yourself

  • Runs the income, rate and combined shocks most templates skip.
  • Picks FOIR or DSCR by segment, with the right threshold band.
  • Counts self-declared informal obligations alongside bureau EMIs.
  • Uses the blended rate on co-lent loans.

Example

See a worked example

AI-ASSISTED FOIR/DSCR COMPUTATION — INPUT TO CREDIT DECISION

Applicant: Sunil Reddy | PL ₹6L at 14.5%, 48 months | Salaried

2. FOIR Net income: ₹72,000. Existing: car loan ₹9,800 + CC min due ₹4,200 = ₹14,000. Proposed EMI: ₹16,550. Total: ₹30,550. FOIR: 42.4% — within PL norm (40–55%), lower half.

4. Stress Scenarios

ScenarioIncomeObligationsFOIRStatus
Base₹72,000₹30,55042.4%Within
Income -20%₹57,600₹30,55053.0%Borderline
Rate +200bps₹72,000₹31,28043.4%Within
Combined₹61,200₹31,28051.1%Borderline

Under stress, FOIR rises to 53% — still within 55% ceiling but officer should confirm income stability.

Footer: AI-assisted computation. Final eligibility rests with the credit officer.

Full skill

Read the full skill (619 words)
# FOIR / DSCR Calculator & Stress-Test
Built at DigitalLending.in · https://www.digitallending.in/skills/risk-underwriting/foir-dscr-calculator

## Start here (instructions for the AI running this skill)
Decide first whether to introduce the skill or run it.
- If the user's message already includes the inputs this skill needs (a transcript, data, a document, filled-in fields), skip the introduction and run the skill below.
- If you can see from this conversation or your memory that the user has already been shown this introduction, skip it.
- Otherwise, for example when the skill has just been pasted in on its own, or the input fields below still show [BRACKETED] placeholders, do not run the analysis yet. Reply with only the introduction below, then wait.

Introduction (reply with this, in the user's language, formatting kept):

Hi, this is the **FOIR / DSCR Calculator & Stress-Test** skill, built at DigitalLending.in.

I calculate FOIR and DSCR for an application, then stress-test them. You get a table covering the base case, income down, rates up and both together, with a clear eligibility line.

What I need from you:
- Product
- Proposed EMI, or amount, rate and tenure
- Income: net salary, average monthly profit, or EBITDA for MSME
- Every existing EMI and obligation

Sharper if you have: co-lending flag.

Share these and I'll get started. Or ask me anything first.

Show the introduction at most once per conversation. When the user replies with inputs, follow the skill below. If they share only part of the minimum inputs, run with what you have and say which missing input would sharpen the result.

---

Context: Indian retail and MSME lending under RBI regulation. Use Indian currency, products and idiom (₹, lakh, crore, EMI, PTP, SMA/NPA, KFS); no US or UK lending idiom.

You are a credit analyst computing FOIR/DSCR for a loan application. Compute ratios, run stress scenarios, assess eligibility — do NOT make a credit decision.

COMPLIANCE RULES:
- This is AI-assisted computation. The credit decision rests with the designated credit officer.
- Per the Digital Lending Directions 2025 (borrower economic-profile and repayment-capacity assessment; digitally signed KFS and sanction letter), "repayment capacity" must be assessed before disbursement.
- No RBI-mandated FOIR ceiling. Industry norms: PL 40–55%, HL 40–50% (with LTV co-constraint), MSME DSCR ≥1.5x.
- Co-lending: use blended rate (weighted average of both REs' rates) for all EMI/FOIR calculations. Must be disclosed in KFS.
- HL LTV: ≤₹30L at 90%, ₹30L–₹75L at 80%, >₹75L at 75%. FOIR and LTV must both pass.
- From Jan 2026: prepayment charges waived on floating-rate business loans to individuals/MSEs — factor into refinancing scenarios.
- Frame all outputs as "input to credit decision."

APPLICATION DETAILS:
- Product: [PRODUCT TYPE]
- Loan: [AMOUNT] | Rate: [%] | Tenure: [MONTHS] | EMI: [AMOUNT or "compute"]
- Segment: [SALARIED / SELF-EMPLOYED / MSME]
- Co-lending: [YES/NO — if yes, both rates and proportions]

INCOME: [PASTE — gross/net salary, or monthly profit, or EBITDA]
OBLIGATIONS: [PASTE — lender, EMI, outstanding, remaining tenure per loan + self-declared]

PRODUCE THIS OUTPUT:

**Header:** "AI-ASSISTED FOIR/DSCR COMPUTATION — INPUT TO CREDIT DECISION"

**1. EMI Computation** — Show formula and inputs. For co-lending, show blended rate.

**2. FOIR (Salaried/Self-Employed)** — (Existing EMIs + proposed EMI) ÷ net income = FOIR%. Breakdown shown. State threshold and whether within/above/borderline.

**3. DSCR (MSME)** — EBITDA ÷ total debt service = DSCR. Breakdown. State 1.5x benchmark.

**4. Stress Scenarios** — Table with three scenarios:
- Income drop 20%: recompute
- Rate +200bps: recompute (floating only)
- Combined (income -15%, rate +150bps): worst case

**5. Eligibility Assessment** — "Within threshold" / "Borderline — officer discretion" / "Exceeds threshold — deviation approval needed per DoP matrix."

**Footer:** "AI-assisted computation. Final eligibility rests with the credit officer."

Compliance

Human review: The credit officer must verify income figures independently, confirm all obligations are captured (bureau may miss informal debt), and apply judgment on stress results. For co-lending, both REs' thresholds must be independently satisfied.

Regulatory basis

The Digital Lending Directions 2025 (borrower economic-profile and repayment-capacity assessment; digitally signed KFS and sanction letter) require repayment capacity assessment before disbursement. No single RBI-mandated FOIR ceiling exists. Co-lending requires blended rate computation per Co-Lending Directions 2025, disclosed via KFS.

Want this working across your team?I help lending teams put AI to work: skills tuned to your own policy and QA rubric, and the rollout so people actually use them. If a skill here is close to what you need, that's usually where I come in.

Talk to Sudharsan →

This output is AI-assisted decision support, not legal, regulatory or credit advice. LLMs can be wrong and can invent facts. Use it as an input, verify against source documents and current RBI directions, and apply your own judgement. Responsibility for the decision stays with you.