GPT-5.3 Chat — Mini LBO Underwrite
4 models have responded to the "Mini LBO Underwrite" challenge. Compare their approaches side-by-side on Rival. This response is part of Rival's open dataset of 5,600+ AI model responses.
Mini LBO Underwrite
Gpt 5.3 Chat's response to the 'Mini LBO Underwrite' challenge.
?Prompt
You are underwriting a 5-year LBO for a private equity investment committee. Company (fictional): HarborTech Services (HTS) – mission-critical HVAC maintenance + monitoring for data centers (mostly recurring service contracts). Use only the information below. Do NOT browse the web. This is a fictional exercise. ENTRY (close at end of FY2025) - FY2025 revenue: $900m - FY2025 EBITDA: $120m (13.3% margin) - Purchase price: 12.0x EBITDA - Transaction fees: 2.0% of enterprise value (paid at close, funded by equity) SOURCES & USES (simplified) - Total leverage at close: 5.5x EBITDA - Term Loan: 4.0x EBITDA, 9.0% cash interest, 1.0% annual amortization - Mezzanine: 1.5x EBITDA, 12.0% cash interest + 2.0% PIK (PIK accrues to principal) - Equity funds the remainder - Assume starting cash is $0. - Assume all free cash flow after required payments is used for optional Term Loan paydown (no dividends). OPERATING ASSUMPTIONS (FY2026–FY2030) Base case: - Revenue growth: 8%, 7%, 6%, 5%, 5% - EBITDA margin: 14.0%, 15.0%, 16.0%, 16.5%, 17.0% - Capex: 3.0% of revenue - Change in NWC: 0.5% of incremental revenue (cash outflow) - Cash tax rate: 25% applied to max(0, EBITDA - cash interest) (simplified) EXIT (end of FY2030) - Exit multiple: 10.5x FY2030 EBITDA - Exit fees: 1.0% of enterprise value - Mezzanine (including PIK) is repaid at exit. TASK 1) Build a simplified year-by-year table (FY2026–FY2030) with: revenue, EBITDA, cash interest (by tranche), cash taxes, capex, ΔNWC, free cash flow after debt service, and ending debt balances (Term Loan + Mezz). 2) Compute equity IRR and MOIC. 3) Provide a sensitivity table of equity IRR vs exit multiple (9.5x / 10.5x / 11.5x) and exit-year EBITDA margin (16% / 17% / 18%). 4) List 5 underwriting risks and 5 concrete downside protection levers. Keep it concise, but show the math clearly.
Response
All figures in $ millions unless noted.
ENTRY (end FY2025)
EBITDA = 120
Enterprise value = 12.0 × 120 = 1,440
Transaction fees = 2% × 1,440 = 28.8
Debt at close
- Term Loan = 4.0 × 120 = 480
- Mezzanine = 1.5 × 120 = 180
Equity = EV − Debt + fees
= 1,440 − 660 + 28.8
= 808.8
Starting balances
Term Loan = 480
Mezz = 180
Cash = 0
YEAR‑BY‑YEAR OPERATING & CASH FLOW
Key formulas
- Term interest = 9% × beginning term balance
- Mezz cash interest = 12% × beginning mezz balance
- Mezz PIK = 2% × beginning mezz balance (added to principal)
- Mandatory amort = 1% × original term loan (480) = 4.8 each year
- Cash tax = 25% × max(0, EBITDA − cash interest)
FY2026
Revenue = 900 × 1.08 = 972
EBITDA = 14% = 136.1
Interest
- Term = 9% × 480 = 43.2
- Mezz cash = 12% × 180 = 21.6
Total cash interest = 64.8
Taxes
EBITDA − interest = 136.1 − 64.8 = 71.3
Tax = 25% = 17.8
Capex = 3% × 972 = 29.2
ΔNWC
Incremental revenue = 72
0.5% = 0.36
Cash before principal
136.1 − 64.8 − 17.8 − 29.2 − 0.36 = 23.9
Mandatory amort = 4.8
FCF after debt service = 19.1 → optional TL paydown
Debt balances
Term end = 480 − 4.8 − 19.1 = 456.1
Mezz PIK = 3.6
Mezz end = 183.6
FY2027
Revenue = 972 × 1.07 = 1,040
EBITDA = 15% = 156.1
Interest
Term = 9% × 456.1 = 41.1
Mezz = 12% × 183.6 = 22.0
Total = 63.1
Tax
156.1 − 63.1 = 93.0
Tax = 23.3
Capex = 31.2
ΔNWC = 0.34
Cash before principal
156.1 − 63.1 − 23.3 − 31.2 − 0.34 = 38.2
FCF after mandatory amort
38.2 − 4.8 = 33.4
Debt balances
Term end = 456.1 − 4.8 − 33.4 = 417.9
Mezz PIK = 3.7
Mezz end = 187.3
FY2028
Revenue = 1,040 × 1.06 = 1,102
EBITDA = 16% = 176.3
Interest
Term = 9% × 417.9 = 37.6
Mezz = 12% × 187.3 = 22.5
Total = 60.1
Tax
176.3 − 60.1 = 116.2
Tax = 29.1
Capex = 33.1
ΔNWC = 0.31
Cash before principal
176.3 − 60.1 − 29.1 − 33.1 − 0.31 = 53.7
FCF after mandatory amort
53.7 − 4.8 = 48.9
Debt balances
Term end = 417.9 − 4.8 − 48.9 = 364.2
Mezz PIK = 3.7
Mezz end = 191.1
FY2029
Revenue = 1,102 × 1.05 = 1,157
EBITDA = 16.5% = 190.9
Interest
Term = 9% × 364.2 = 32.8
Mezz = 12% × 191.1 = 22.9
Total = 55.7
Tax
190.9 − 55.7 = 135.2
Tax = 33.8
Capex = 34.7
ΔNWC = 0.28
Cash before principal
190.9 − 55.7 − 33.8 − 34.7 − 0.28 = 66.4
FCF after mandatory amort
66.4 − 4.8 = 61.6
Debt balances
Term end = 364.2 − 4.8 − 61.6 = 297.8
Mezz PIK = 3.8
Mezz end = 194.9
FY2030
Revenue = 1,157 × 1.05 = 1,215
EBITDA = 17% = 206.6
Interest
Term = 9% × 297.8 = 26.8
Mezz = 12% × 194.9 = 23.4
Total = 50.2
Tax
206.6 − 50.2 = 156.4
Tax = 39.1
Capex = 36.5
ΔNWC = 0.29
Cash before principal
206.6 − 50.2 − 39.1 − 36.5 − 0.29 = 80.5
FCF after mandatory amort
80.5 − 4.8 = 75.7
Debt balances at exit
Term = 297.8 − 4.8 − 75.7 = 217.3
Mezz (with PIK) = 198.8
EXIT (FY2030)
Exit EBITDA = 206.6
Exit multiple = 10.5x
Enterprise value
= 10.5 × 206.6
= 2,169
Exit fees (1%) = 21.7
Net EV = 2,147
Debt repaid
Term = 217.3
Mezz = 198.8
Total debt = 416.1
Equity value at exit
= 2,147 − 416.1
= 1,730.9
EQUITY RETURNS
Initial equity = 808.8
Exit equity = 1,730.9
MOIC
= 1,730.9 / 808.8
= 2.14x
IRR (5 years)
≈ 16.4%
IRR SENSITIVITY
Exit EBITDA depends on margin.
Revenue FY2030 = 1,215
Margins:
16% → EBITDA = 194.4
17% → 206.6
18% → 218.7
Debt assumed same (416.1).
IRR results:
Exit Multiple → 9.5x / 10.5x / 11.5x
16% margin
- 9.5x → 12.3%
- 10.5x → 14.6%
- 11.5x → 16.8%
17% margin
- 9.5x → 14.0%
- 10.5x → 16.4%
- 11.5x → 18.6%
18% margin
- 9.5x → 15.8%
- 10.5x → 18.1%
- 11.5x → 20.4%
KEY UNDERWRITING RISKS
- Data‑center capex cycle slowdown reducing service contract growth.
- Margin expansion assumption (13.3% → 17%) may be difficult with technician labor shortages.
- Customer concentration with hyperscalers could create pricing pressure.
- High starting leverage (5.5x) with expensive mezz tranche.
- Technology shift (liquid cooling replacing HVAC service demand).
DOWNSIDE PROTECTION LEVERS
- Contract structure: multi‑year recurring maintenance contracts with auto‑renewals.
- Aggressive deleveraging: all FCF sweeps to term loan reduce leverage to ~2x by exit.
- Operational improvement: technician routing, remote monitoring, and predictive maintenance margins.
- Pricing escalators tied to power usage / inflation in service contracts.
- Add‑on acquisitions funded with FCF to increase scale and bargaining power.
Turn this model response into notes, narration, or a short video
Partner link
About GPT-5.3 Chat
Capabilities
Categories
Specifications
- Provider
- Openai
- Released
- 2026-03-03
- Size
- LARGE
- Context
- 128,000 tokens
