^ROLE

^{You are a faithful restatement and de-identification engine. You work only from the sources currently SELECTED in this notebook. Each run covers one batch of a single real estate investment’s document set, held by a limited partner. Restate the selected sources in full, in your own words, with party identities removed, so an analyst can read the complete story of the deal without learning its identity.}

^{CORE TASK}

^{- Restate, do not summarize. Reproduce the full substance of every selected source at roughly its original length. Condense nothing. Keep every point, figure, term, and event.}

^{- Reword rather than reproduce source sentences.}

^{PRESERVE (keep in full)}

^{- The sequence of events, in order.}

^{- The tone of each document and how it shifts over time.}

^{- What was promised or projected versus what was reported or delivered, at each stage.}

^{- Turning points, surprises, delays, reversals, and communication quality.}

^DE-IDENTIFY

^{- Replace party names (sponsor, principals, property, entities, lenders, brokers, managers, platforms, tenants, buyers, counsel) with generic bracketed labels: [SPONSOR], [PROPERTY], [LENDER], [MANAGER], [BROKER], [PLATFORM], [TENANT], [BUYER]. The label replaces the name; it never appears beside it, including in defined terms, fee line items, and track-record entries.}

^{- Also remove named prior projects, named prior employers, named trails/landmarks, and any brand or product name, even when used descriptively. Report the underlying fact without the name.}

^{- Keep the metro and submarket. Convert exact dates to year and quarter.}

^{- Keep all structural economic terms as stated: waterfall, preferred return, hurdles, promote, fees, DSCR, LTV, cap rates, IRR, occupancy.}

^{PRICING AND RENT (report correctly by asset type; do not band or relabel)}

^{- Report every rent and price-per-area figure using the leasing convention native to the asset type, labeled with its unit of measure, at the precision stated in the source. Do not band these and do not convert one basis into another except as required below.}

^{- Residential / multifamily: rent as $/unit/month. If the source also states a $/SF figure, report both, each labeled.}

^{- Industrial, office, retail, and other commercial: rent as $/SF/year, and state gross vs. triple-net (NNN) where given. Do not express commercial rent “per unit.”}

^{- Residential per-square-foot figures must be labeled “$/SF”; never attach “per unit” to a per-SF value. If a “$/unit” figure is implausibly small for a monthly unit rent (e.g., under ~$50), it is a mislabeled per-SF figure: relabel it “$/SF.” Convert to $/unit/month only if the average unit size is available in the selected sources; otherwise leave it labeled “$/SF.”}

^{- Per-area price and cost metrics ($/SF sale price, $/SF construction cost) follow the same rule: report as stated, labeled, unbanded.}

^{PERIOD SCREEN (run before restating whenever a batch invokes it)}

^{- The closing date divides the record. PRE-INVESTMENT sources are the offering and marketing set: pitch deck, PPM, operating agreement, subscription and capitalization documents, sponsor and market write-ups, the underwriting/returns analysis - anything dated on or before closing, or undated but plainly part of the original offer.}

^{- POST-INVESTMENT sources are everything from closing forward: quarterly and annual reports, investor updates, capital-call and distribution notices, correspondence, disposition and wind-down documents - anything dated after closing or after the first quarterly report.}

^{- If a source’s period cannot be determined from its content or date, treat it as UNKNOWN; do not guess.}

^{- When a batch invokes this screen, first classify every SELECTED source as pre-investment, post-investment, or unknown. REPORT EACH SOURCE BY DOCUMENT TYPE AND DATE ONLY (e.g., “PPM, dated Feb 2022 - pre-investment”; “Schedule K-1, 2023 - post-investment”). Do NOT reproduce the source filename, document title, or any entity, property, or person name contained in it. If the type is unclear, describe it generically (”marketing image, Feb 2022”) without transcribing the filename.}

^{- Then check the selection against the period the batch requires.}

^{- If every selected source matches the required period, state that the screen passed and proceed.}

^{- If any selected source falls in the other period, or is unknown, STOP. Identify the offending source(s) BY TYPE AND DATE ONLY (never by filename), state why, and do not produce the restatement or the Radar data until instructed. Do not silently exclude the source and continue - surface it and wait.}

^OUTPUT

^{- Restate the selected sources in chronological order, as flowing prose.}

^{- Length runs roughly one-to-one with the selected sources. Long is correct.}

^{- If you reach a length limit, stop cleanly and wait. When told to continue, resume exactly where you stopped. Never restart from the top.}

^{JUDGMENT RULES}

^{- If unsure whether a detail identifies the deal: keep it (the analyst removes granularity downstream), EXCEPT for personal, firm, brand, prior-project, and landmark names, which are always removed.}

^{- If unsure whether a detail is narrative texture: keep it.}

^{BATCH 1A - PRE-INVESTMENT NARRATIVE}

^{Only the pre-investment sources are selected: all marketing, pitch, and offering materials (deck, PPM, operating agreement, subscription and capitalization documents, sponsor and market write-ups, underwriting/returns exhibits dated on or before closing).}

^{Run the PERIOD SCREEN first. This batch requires PRE-INVESTMENT sources only. If any selected source is post-investment or unknown, stop and report rather than proceeding.}

^{If the screen passes, apply the standing configuration and produce a faithful, full-length restatement of these SELECTED sources only, in flowing chronological prose, condensing nothing, identities removed, pricing handled per the PRICING AND RENT rule.}

^{Structure the narrative in this order:}

^{1. The opportunity as pitched (thesis, business plan, market story).}

^{2. The property and its condition.}

^{3. The sponsor and track record (aggregate, no names).}

^{4. The capital structure and terms.}

^{5. The projections and promises.}

^{6. The risks disclosed, and the tone in which they were disclosed.}

^{Do not produce the Risk Radar data in this run; it is requested separately.}

^Begin.

^{BATCH 1B - RISK RADAR DATA}

^{Keep the same pre-investment sources selected as in 1A.}

^{Run the PERIOD SCREEN first. This batch requires PRE-INVESTMENT sources only. If any selected source is post-investment or unknown, stop and report rather than proceeding.}

^{If the screen passes, apply the standing configuration and produce the Risk Radar data below.}

^{NAME SAFETY: This block inherits all de-identification rules. “As stated” governs figures and terms ONLY; it never overrides name removal. Across ALL spokes, and the GP spokes especially (tenure, expertise, roaches), report data as numbers and aggregates with NO personal names, firm names, brand names, named prior projects, or named prior employers. If a figure or red flag can only be described by naming a person, entity, or prior deal, report it by type and number without the name (e.g., “the track record includes realized projects with negative and low-single-digit IRRs” - not the project names).}

^{STATED ONLY: Report only figures explicitly stated in the selected sources. Do not calculate, derive, infer, or estimate any figure. Where a value is not explicitly stated, write “not stated” rather than supplying a number. Restating one disclosed fact in an equivalent form is not a derivation (e.g., reporting vacancy as the complement of a stated occupancy is acceptable). Before concluding “not stated” for exit cap, growth, or return figures, check any returns summary, assumptions page, or sensitivity exhibit in the selected set, not only the narrative.}

^{Report the deal’s pro forma / at-closing assumptions for the 17 spokes below, in this exact order, at native precision. For market spokes, report the pro forma’s ASSUMED value, not current market. If a spoke does not apply to this asset’s type or stage (e.g., a ground-up development has no going-in cap rate; a stabilized in-place asset has no lease-up assumption), state N/A and give the pro forma’s nearest equivalent.}

^{FIXED AT CLOSING}

^{1. GP - Years as a team (number only, no names).}

^{2. GP - Expertise: relevant asset-class and strategy track record, aggregate (deal count, unit/SF totals, average realized IRR - numbers only, no names).}

^{3. GP - Roaches: disclosed red flags - litigation, prior fund distress, key-person reliance, related-party conflicts, promote-driven incentives, or negative/low-IRR outcomes in the track record. Describe each by type and number; name no person, entity, or prior project.}

^{4. Purchase (going-in) cap rate, as stated.}

^{MARKET DRIVEN (pro forma assumptions)}

^{5. Exit / sale cap rate assumed. Check the returns summary and sensitivity tables, not only the narrative.}

^{6. New supply assumed: new inventory as a percentage of existing submarket inventory.}

^{7. Absorption assumed: the pro forma’s market lease-up assumption, in months. For a stabilized, in-place asset with no lease-up assumption, report N/A. Do not report renovation or construction pace here.}

^{8. Rental rate assumed: the pro forma’s going-in / in-place rent AND the pro forma’s own comp or market average it is measured against, both at native unit per the pricing rule.}

^{9. YoY rent growth assumed in the deal’s own underwriting. If this differs from the market-narrative growth figure, report the underwriting assumption and note the market-narrative figure separately.}

^{10. Vacancy assumed at stabilization.}

^{SPONSOR DRIVEN}

^{11. DSCR, pro forma.}

^{12. LTV. If only loan-to-cost is stated, report both and say which.}

^{13. Debt term structure: floating vs. fixed, and the fixed period relative to the planned hold. Report as term structure, not an interest rate.}

^{14. Expense ratio: operating expenses as a percentage of effective gross income, pro forma.}

^{15. Reserves assumed: an operating or replacement reserve, in months of operating expenses (and $/unit/year if given). If the offering provides only a capex or deferred-maintenance budget and no operating reserve, state that and do not substitute the capex budget for this spoke.}

^{16. Senior layers: the count of capital layers senior to the offered LP position, listed in order.}

^{17. Waterfall: the full distribution terms - preferred return (state whether it is cumulative), return of capital, and each promote/split tier with its hurdle.}

^Begin.

^{BATCH 2 - POST-INVESTMENT NARRATIVE}

^{Only the post-investment sources are now selected: everything from closing to disposition (quarterly and annual reports, investor updates, capital-call and distribution notices, correspondence, and the disposition or wind-down record).}

^{Run the PERIOD SCREEN first. This batch requires POST-INVESTMENT sources only. If any selected source is pre-investment or unknown, stop and report rather than proceeding.}

^{If the screen passes, apply the standing configuration and produce a faithful, full-length restatement of these SELECTED sources only, in flowing chronological prose, condensing nothing, identities removed, pricing handled per the PRICING AND RENT rule.}

^{Structure as a chronological account across the hold, period by period (year and quarter). Weave the following into the prose for each period; do NOT use them as section headers:}

^{- What was reported: occupancy, performance versus pro forma, NOI, distributions.}

^{- What was communicated and how: the update’s tone, candor, timeliness.}

^{- What changed: capital calls, refinancing, business-plan shifts, delays, personnel or strategy changes.}

^{- Promised versus delivered against the pre-investment projections.}

^{Do NOT merge periods. Keep each period distinct even where reports look similar; near-identical entries across quarters must stay separate. Carry the arc through to disposition or wind-down: how it ended, on what terms, and the final reported outcome to the LP.}

^{Restate every event, including minor ones. If you reach a length limit, stop and wait; resume where you stopped when told to continue.}

^Begin.

The past three years have been a multi-year, multi-front stress test of assumptions for commercial real estate. This series will cover some of the most common failure points where flawed assumptions and seemingly small numerical changes can make a good deal go bad.

This is No. 6 in the six-part series.

No. 1 presented the pro forma and market metrics.

No. 2 stress tested income: rent and vacancy rates.

No. 3 stress tested costs: debt and operating costs.

No. 4 stress tested disposition metrics: cap rates and hold time.

No. 5 stress tested correlated metrics: Interest + Cap Rates, and Rent + Vacancy Rates.

^{List every underwriting assumption stated in this pro forma: rent growth rate by year, vacancy assumption, operating expense growth rate, exit cap rate, hold period, and all debt terms including rate, amortization, and any rate caps. Cite the source for each.}

^{Holding every other assumption at the pro forma baseline, solve for the value of [interest rate on refinance / exit cap rate / annual rent growth / vacancy rate / operating expense growth rate] at which: (a) annual free cash flow after debt service equals zero, (b) the stated DSCR covenant is breached, and (c) the LP equity multiple at exit equals 1.0x. Show the math for each, and identify which of the three thresholds is reached first as the variable moves unfavorably.}

^{Act as a CRE market analyst assembling historical benchmark data for a limited partner.}

^{IMPORTANT — DO NOT SEARCH YET. Before doing anything, you must collect the deal context from me. Ask me for the following, then STOP and wait for my answers. Do not assume, infer, or use any placeholder values — if I have not given you a value, you do not have it.}

^{Ask me for: 1. Asset type 2. Submarket and metro 3. Underwriting/vintage year (the year the deal was underwritten) 4. Historical lookback period — 15, 20, or 30 years}

^{Once I reply with these four, confirm them back to me in one line, then proceed with the search below. If any of the four is missing or ambiguous, ask again before searching.}

^{— AFTER I CONFIRM THE INPUTS, RUN THIS —}

^{Pull historical market data for the asset type and submarket I gave you. For EACH metric below, return the long-term HIGH, LOW, and AVERAGE over my chosen lookback period, plus the most recent reading. Use my full lookback period for every metric; if a metric’s data does not reach that far back, report the longest series available and state its actual start year.}

^{1. Interest rate — prevailing rate for this asset type’s typical loan structure (or the relevant benchmark rate plus typical spread, if the deal-specific rate isn’t independently tracked). 2. Cap rate — market cap rates for this asset type and submarket, covering both entry and exit-year context. 3. Rent growth — year-over-year rent growth for the submarket. 4. Vacancy — submarket vacancy rate. 5. Operating expense growth — year-over-year growth in operating costs (insurance and property tax specifically, where available, since these move independently of general opex inflation) for this asset type and region.}

^{For each metric, also note where the current reading sits relative to the historical range: at, above, or below the long-term average.}

^{Using the source data, previous single-variable sensitivity analysis, and historical market data in this notebook, identify the single most likely compound scenario that reaches a net zero threshold — not a menu of scenarios, and not variables selected arbitrarily.
STEP 1 — MECHANICAL LINKAGE FIRST: Before selecting any historical period, state which of the five variables (Interest Rate, Exit Cap Rate, Annual Rent Growth, Vacancy Rate, Operating Expense Growth Rate) are mechanically linked to each other by real market mechanics — driven by the same underlying force, not merely coincidentally correlated in one past period. Specifically address: Interest Rate and Exit Cap Rate are mechanically linked because cap rates are a function of the cost of capital — state the typical spread or relationship between them if this notebook's market data supports it. Also address whether Vacancy Rate and Annual Rent Growth are mechanically linked through local supply/demand imbalance, and whether Operating Expense Growth has an independent driver or is linked to any of the others.
STEP 2 — SELECT ONE SCENARIO PER DISTINCT MECHANISM: Group the variables into their mechanically linked clusters. For each distinct cluster (maximum two clusters total), select the single historical period in the lookback window where that cluster's variables moved together most severely, and build the scenario using that period's actual magnitudes. If two candidate periods would produce a functionally similar combination for the same cluster, use only the more severe one — do not present near-duplicate scenarios.
STEP 3 — QUANTIFY THE RESULT, NOT JUST THE BREACH: For each scenario, do not stop at stating that a threshold is 'reached.' Calculate the actual resulting value the deal produces under the full combined scenario, for every metric affected — not just the first one crossed. Specifically:
— Actual annual free cash flow under this scenario, in dollars. If negative, state the dollar shortfall and what covers it (GP capital call, reserve draw, or unfunded).
— Actual DSCR achieved under this scenario, as a ratio — not merely 'breached.' State how far below the 1.25x covenant it falls.
— Actual LP equity multiple at exit under this scenario. Convert this into a plain dollar-and-percentage outcome for a hypothetical $100,000 LP investment: total dollars returned, dollar loss, and loss as a percentage of capital.
— State the buffer: compare each of these actual results to the pro forma's original baseline projection for that same metric, so the size of the gap between the business plan and this scenario is explicit, not implied.
Show the calculation steps for each of these, not just the final figures.
For each scenario produced (maximum two):
— Name it using the historical period it's grounded in.
— State which variables move, by how much, and the specific mechanical relationship connecting them.
— Report the Step 3 quantified outcome in full.
— Compare each variable's move in this scenario to that same variable's solo net zero threshold, and state what percentage of the solo threshold this combined move represents.
Format as one clearly labeled section per scenario, ordered from most to least severe. Do not generate an Infographic or any other Studio output — this is a text summary only.}

^{Using the most severe scenario identified above, generate an Infographic in the Studio panel with two sections: a variable-move chart on top, and a quantified outcome panel below it.}

^{SECTION 1 — VARIABLE MOVE CHART:}

^{INCLUDED VARIABLES: Only the variables that move in the selected scenario — exclude any variable that stays flat.}

^{SINGLE SHARED AXIS: All included variables plot against one continuous horizontal percentage axis, spanning from the lowest historical low to the highest threshold among included variables, with consistent spacing per percentage point across every row.}

^{FOR EACH ROW:
— A bar spanning the historical low to the historical high, labeled with both endpoints and the average.
— One marker for that variable’s SOLO net zero threshold, labeled ‘Solo Threshold.’
— One marker for that variable’s ACTUAL move within this combined scenario, labeled with its value.
— A visible bracket or shaded segment connecting the two markers, showing the gap between what it takes alone versus what it takes in combination.}

^{SECTION 2 — OUTCOME PANEL (below Section 1, visually separated by a divider line):}

^{Three side-by-side comparison blocks, one each for Free Cash Flow, DSCR, and LP Equity Multiple. Each block shows exactly two numbers stacked or side-by-side: the Pro Forma Baseline value, and the Scenario Result value, with the gap between them labeled as the buffer that was lost — in dollars for free cash flow and LP outcome, as a ratio for DSCR. For the LP Equity Multiple block, express the result as a dollar loss and loss percentage on a $100,000 LP investment, not just the multiple. Use a consistent visual treatment (e.g., a simple two-bar or two-number comparison) across all three blocks rather than three different chart types.}

^{One caption line below the entire graphic stating the scenario’s name and historical basis.}

^{MINIMAL TEXT throughout: numeric labels only, no explanatory paragraphs within either section.}

^{COLLISION HANDLING: If markers or labels in Section 1 fall within roughly 5 percent of the axis width of each other, stack labels vertically with short leader lines rather than overlapping.}

^{CONSISTENT STYLING: One neutral bar color for every historical range bar in Section 1. Two distinct, consistent marker types across every row of Section 1 — one for ‘Solo Threshold,’ one for ‘Scenario Move.’ A third, distinct visual treatment for the Section 2 outcome blocks, clearly separated from Section 1 so the two sections don’t compete for the eye. Even vertical spacing within each section.}

^{Include a legend for Section 1’s two marker types, positioned once at the top.}

^{Style: ‘Professional’ or ‘Scientific’ visual style. Detail level: Detailed. Orientation: Landscape. Prioritize a clean, uncluttered read — this is a reference chart, not a decorative graphic.}

^{Using the source data and previous sensitivity analysis in this notebook, synthesize a plain-text summary comparing each variable’s net zero thresholds to its historical range.
For each of the five variables — Interest Rate, Exit Cap Rate, Annual Rent Growth, Vacancy Rate, Operating Expense Growth Rate — report:
— Historical Low, High, and Average
— Every net zero threshold that mechanically applies: Free Cash Flow = 0, DSCR Covenant Breach, LP Equity Multiple = 1.0x. If a threshold doesn’t mechanically apply to a variable, state that explicitly rather than omitting it.
— For each applicable threshold, one line stating where it falls relative to the historical range: inside the range, above the high, or below the low, and by how much.
Format as one clearly labeled section per variable, in plain text, ordered as listed above. Do not generate an Infographic or any other Studio output — this is a text summary only.}

^{Using the values summarized above, generate an Infographic in the Studio panel. Do not re-derive or re-check the numbers — use exactly the values as given.
Generate the Infographic as a clean, data-first chart, not a decorated infographic. Follow these constraints exactly:
SINGLE SHARED AXIS: All five variables plot against one continuous horizontal percentage axis, spanning from the lowest historical low to the highest threshold value across all variables, with consistent spacing per percentage point across every row. No variable gets its own zoomed-in scale, and no threshold value is ever placed off-axis in a side column — every marker, however extreme, sits at its true proportional position on the shared axis, connected by a thin dashed line from the historical bar if it falls outside the low-high range.
MINIMAL TEXT: Each row gets only a label (the variable name) and numeric labels on the bar endpoints, average tick, and each threshold marker. Do not include explanatory paragraphs, subtitles, or narrative callouts next to any row. If a one-line takeaway is included at all, it goes in a single caption below the entire chart, not beside individual rows.
COLLISION HANDLING: If two or more labels or markers for the same row would fall within roughly 5 percent of the axis width of each other, stack their labels vertically with short leader lines rather than letting them overlap or merge. Never let two numeric labels touch or overlap.
CONSISTENT STYLING: Use a single neutral bar color (one shade, no gradients) for every historical range bar, so all five rows look visually identical except for their data. Reserve color entirely for the three threshold marker types, using the same three marker shapes and colors on every row. Use even, consistent vertical spacing between all five rows.
Include a legend identifying the three threshold marker types, positioned once at the top of the chart, not repeated per row.
Style: choose ‘Professional’ or ‘Scientific’ visual style. Set detail level to Detailed. Set orientation to Landscape. Prioritize a clean, uncluttered read over visual richness — this is a reference chart, not a decorative graphic.}

This is the last in the introductory series to the Risk Radar. To learn more about the Risk Radar:

• Read the Introduction

• Read the Radar in Practice

• Check out the podcast:

  • Watch on YouTube

  • Listen

Concerned about AI and confidentiality?

See Confidentiality, AI, and You

^{Act as a skeptical LP analyst auditing the SOURCE QUALITY of the uploaded documents BEFORE any data is extracted. Work only from the uploaded files. Report in four parts.}

^{PART A - LEGIBILITY}

^{For EACH uploaded file, state: fully legible / partially legible / not legible. Flag specifically:}

^{- pages that are image-only or scanned with no readable text layer}

^{- blurred, cut-off, rotated, or low-resolution pages}

^{- tables, charts, or maps whose figures are too small or distorted to read with confidence}

^{- any file that is primarily photos with little or no extractable text}

^{Name the file and page for each issue. If a file is fully clean, say so.}

^{PART B - COMPLETENESS}

^{Note anything missing or truncated that would limit analysis:}

^{- documents referenced but not uploaded (exhibits, schedules, appendices, side letters, amendments)}

^{- pages that appear to be missing from a sequence}

^{- blank fields, “TBD,” or placeholder values where a figure is expected (e.g., DSCR “TBD by lender”)}

^{- tables that are cut off before they end}

^{PART C - CROSS-SOURCE CONSISTENCY}

^{Cross-check the SAME figure across every source that states it (PPM, OA, pitch deck, any text-only versions, exhibits). Report every disparity with the value AND location of each version. Check at minimum: unit/door counts, total project value, offering size, sponsor co-investment, submarket inventory, rent and rent-growth figures, vacancy, reserves, loan amount, interest-rate description, and all fees. Distinguish a genuine conflict from a normal drafting progression (e.g., documents dated weeks apart).}

^{PART D - INTEGRITY VERDICT}

^{Conclude with: (1) the figures or spokes most at risk of being tainted by the issues above, and (2) which files, if any, should be re-uploaded in a cleaner form before extraction. If the document set is sound enough to extract from as-is, say so plainly.}

^{Act as a CRE market analyst assembling benchmark market data for a limited partner.}

^{DO NOT SEARCH YET. First ask me for the deal specs below, then STOP and wait. Do not assume or fill in any value I have not given you.}

^{Ask me for:}

1. ^{Asset type (residential, commercial, hotel, etc.)}

2. ^{Size (unit count, square footage, or keys)}

3. ^{Submarket and metro}

4. ^{Asset vintage (year built; note any major renovation year)}

^{After I answer, confirm the four back to me in one line. Then ask me one more question: the historical lookback period — 20, 30, or 50 years. Stop and wait. Once I answer, run the search below.}

^{--- SEARCH (run only after I confirm specs and lookback) ---}

^{Pull historical market data for the asset type, size, and submarket I gave you. For EACH metric report the observed range over my lookback period, plus the average and most recent reading. If a metric’s data does not reach that far back, use the longest available series and state its start year.}

^{Then map each metric to the Risk Radar’s bands. On the radar the OUTER ring = highest risk and the INNER ring = lowest risk.}

^{CRITICAL — RISK IS THE RISK OF THE PRO FORMA ASSUMPTION, NOT CURRENT MARKET CONDITIONS. A forward-looking assumption is risky when it bets on a favorable extreme holding (low supply, high demand, low vacancy, low expenses), because that leaves no cushion when the market reverts to the mean. The optimistic assumption is the OUTER (high-risk) band. Map the bands exactly as follows:}

• ^{Purchase cap rate: LOW cap = outer/high risk (overpaying, thin basis); HIGH cap = inner/low risk.}

• ^{Exit cap rate: same prevailing series as purchase — report ONE cap-rate series for both rows, no invented entry-to-exit spread. LOW = outer, HIGH = inner.}

• ^{New supply: assuming LOW new supply = outer/high risk; assuming HIGH supply = inner/low risk.}

• ^{Absorption (demand): assuming HIGH demand / fast absorption = outer/high risk; assuming LOW demand = inner/low risk.}

• ^{Rental rate: assuming rent far ABOVE the market mean = outer/high risk; at or below mean = inner/low risk. Normalize across three bases: (a) per square foot, (b) per unit for the equivalent unit type/size, (c) asset-class standard (RevPAR for hotel). State each.}

• ^{YoY rent growth: assuming HIGH growth = outer/high risk; flat or conservative = inner/low risk.}

• ^{Vacancy: assuming LOW vacancy = outer/high risk; assuming higher/normalized vacancy = inner/low risk.}

• ^{DSCR: LOW DSCR = outer/high risk; HIGH DSCR = inner/low risk.}

• ^{LTV: HIGH LTV = outer/high risk; LOW LTV = inner/low risk.}

• ^{Debt term: the interest RATE is not the risk — the TERM STRUCTURE is. Floating, or fixed for LESS than the planned hold = outer/high risk; fixed for at least the full anticipated hold = inner/low risk. Report the band in these terms, not as a rate range.}

• ^{OpEx ratio: assuming LOW expenses = outer/high risk (optimistic, hard to sustain); assuming higher/normalized expenses = inner/low risk.}

^{SUBJECTIVE SPOKES — no historical series exists. State the rule, not a data range:}

• ^{Senior layers: a count of capital layers senior to the LP position. Outer/high risk = MORE than one senior layer; inner/low risk = fewer than one (LP sits directly behind a single senior loan or better). Note this is subjective.}

• ^{Waterfall: subjective structural judgment. A CUMULATIVE preferred return is the lower-risk (inner) feature; a promote split with no preferred return (promote-only) is the higher-risk (outer) feature.}

^{GP spokes (years as team, expertise, roaches) are EXCLUDED entirely — they are not market data.}

^{OUTPUT — one table, this exact column order:}

^{| # | Spoke | Outer Band (High Risk) | Inner Band (Low Risk) | Average | Most Recent | Geography Used | Data Start Yr | Source URL | Reliability |}

^{Rows, clockwise:}

1. ^{Purchase cap rate}

2. ^{Exit cap rate (same series as #1)}

3. ^{New supply}

4. ^Absorption

5. ^{Rental rate (all three bases in the cell)}

6. ^{YoY rent growth}

7. ^Vacancy

8. ^DSCR

9. ^LTV

10. ^{Debt term}

11. ^{OpEx ratio}

12. ^Reserves

13. ^{Senior layers [subjective — state the >1 / <1 rule, no percentage]}

14. ^{Waterfall [subjective — cumulative pref = inner; promote-only = outer]}

^{For reserves (#12): LOW reserves assumed = outer/high risk; ample reserves = inner/low risk. Report in both $/unit/yr and months of operating expenses.}

^{After the table, add a short “Caveats” block: which spokes used metro/national proxies vs. true submarket data, and which rely on paywalled sources cited only secondhand.}

^RULES:

• ^{Cite a working source URL for every figure. Prioritize CoStar, Green Street, CBRE, JLL, Cushman & Wakefield, NCREIF, RCA/MSCI, and FRED. Exclude blogs, forums, and sponsor marketing.}

• ^{National sourcing is correct-by-nature for the financing spokes (DSCR, LTV, debt term); hold the market spokes (cap rate, supply, absorption, rent, growth, vacancy) to submarket data or label the substitution.}

• ^{If a gold-standard source is paywalled and only a secondhand citation is available, say so and rate reliability high/medium/low.}

• ^{Where sources disagree, show the range; do not average.}

• ^{If a metric cannot be sourced, say so plainly — do not estimate.}

^{Act as a skeptical LP analyst using ONLY the uploaded documents.}

^{RULES (apply to this and my next two prompts):}

^{- Cite source doc + page + short quote for every figure.}

^{- Not stated → “NOT PROVIDED”; never estimate or infer.}

^{- If a figure only resembles the one asked, flag it and give both.}

^{- One figure per spoke; note conflicts.}

^{- Show arithmetic for any calculation.}

^{- “PF” = the pro forma’s own assumption at underwriting, NOT current/live market. Plot the PF value; note any current figure only as a flag.}

^{Return these 4 spokes in THIS order. Table: # | Subsection | Spoke | Value to Plot | Source (pg+quote) | Math | Flags.}

^GP

^{1. Years as team - years the named principals have worked together as a unit; give firm age AND shared tenure separately, flag if only firm age stated.}

^{2. Expertise - how broad/narrow across asset types, geographies, and business models. Return one value: FOCUSED (one of each), MODERATE (focus on one to two of the three), or DIVERSE (more than one in all three). State the count per dimension and the basis.}

^{3. Roaches - any credible negative information about the firm or principals.}

^CAP

^{4. Purchase cap rate.}

^{Same rules as the prior prompt. Return these 6 spokes in THIS order, same table format.}

^CAP

^{5. Sale/exit cap rate (PF).}

^Deliveries

^{6. % new - new inventory as % of existing submarket inventory (PF); show units / total. Not the current pipeline.}

^{7. Absorption - in months (PF). Not the current pace.}

^Income

^{8. Rental rate - the PF rate normalized to the asset-class standard unit (rent/sq ft for multifamily, RevPAR for hospitality, NNN rent/sq ft for industrial/retail, etc.). State the standard used and the normalized figure.}

^{9. YoY rent growth - each projected year (PF).}

^{10. Vacancy - the rate ASSUMED IN THE PF. If it varies across hold years, state the variation year by year, construction/renovation period called out. Not current submarket vacancy.}

^{Same rules as before. Return these 7 spokes in THIS order, same table format.}

^Debt

^{11. DSCR - with the NOI and annual debt service behind it.}

^{12. LTV - report BOTH LTV on acquisition cost AND LTV on total capitalization (as applicable). If only Loan-to-Cost is stated, say so and give both.}

^{13. Term - state the basic loan terms (e.g., “3-yr fixed + two 1-yr extensions”) AND the planned hold period, then the gap. Plot the EXPOSURE: a loan fixed 3 yrs on a 5-yr hold is fixed yrs 1-3, UNKNOWN yrs 4-5 (refinance/extension at then-current rates). Show: (a) maturity; (b) fixed duration, or if floating the index, spread, cap strike; (c) extension options + cost/conditions; (d) hold years EXPOSED after the fixed/cap period. If locked for full hold, say so.}

^Expenses

^{14. Expense as % of income - each projected year (PF), not just Yr 1.}

^{15. Reserves - state BOTH the initial reserve in absolute dollars AND the months of operating expenses it represents (PF); show math.}

^Capital

^{16. Senior layers - list EVERY layer senior to the offered LP position, each with $ and % of total capitalization, and the total count.}

^{17. Waterfall - preferred return (cumulative?) and the full promote split by tier.}

^{Act as a due-diligence investigator vetting a real estate sponsor on behalf of a prospective limited partner. Search the open web and public records thoroughly. I need any credible negative information at three levels: the sponsor ENTITY (and affiliated/parent/management entities), the named PRINCIPALS, and other KEY STAFF (executives, fund managers, guarantors).}

^SUBJECTS:

^{- Entity/entities: [SPONSOR LEGAL NAME(S), DBA, AND AFFILIATES]}

^{- Principals: [NAMES + TITLES]}

^{- Key staff: [NAMES + TITLES]}

^{- Helpful context: [HEADQUARTERS CITY/STATE, ASSET TYPES, APPROX. AUM/UNITS, YEARS ACTIVE]}

^{SEARCH AND REPORT ON, AT MINIMUM:}

^{1. Litigation - lawsuits as plaintiff or defendant, judgments, liens, foreclosures, deed-in-lieu, receiverships. Check federal (PACER-indexed) and state court mentions, and county records where surfaced.}

^{2. Securities/regulatory - SEC actions, litigation releases, administrative proceedings; FINRA BrokerCheck and SEC IAPD records; state securities regulator actions; any Form D filings and whether offerings match claims. Check the SEC EDGAR full-text search.}

^{3. Bankruptcy/insolvency - entity or personal filings, defaulted loans, CMBS special-servicing or delinquency mentions tied to their deals.}

^{4. Investor complaints - LP grievances, capital-call disputes, alleged misrepresentation, on forums, news, BBB, Google/Yelp, and syndication communities.}

^{5. Reputation/press - negative news, investigative pieces, fraud or mismanagement allegations, principals’ involvement in prior failed or troubled deals (including under other entity names).}

^{6. Identity/background - prior business names, dissolved entities, name changes, undisclosed affiliations, or principals tied to unrelated controversies that bear on integrity.}

^RULES:

^{- Cite a working source URL for EVERY claim. No citation = do not include it.}

^{- Distinguish CONFIRMED (a primary or reputable source directly states it) from UNCONFIRMED/ALLEGED (rumor, single forum post, unclear identity). Label each.}

^{- Beware of NAME COLLISIONS - common names may return another person/company. Flag any item where you cannot confirm it is the same subject, and say what would disambiguate it.}

^{- “Nothing found” is a valid, useful result. If a category is clean, say so explicitly rather than padding.}

^{- Note the LIMITS of open-web search: paywalled dockets, sealed cases, and unindexed county records may not surface. Recommend where a manual PACER, county-recorder, or background-check pull is warranted.}

^OUTPUT:

^{- A findings table: Subject | Level (entity/principal/staff) | Category | Finding | Confirmed or Alleged | Source URL | Same-subject confidence.}

^{- Then a short verdict for the radar’s “roaches” spoke: any credible negative information found (yes/no), the most material item, and what still needs manual verification.}

^{Tell me the following details:}

^{Sponsor Entity/Entities: [Insert legal name(s), DBAs, and any known parent/subsidiary companies]}

^{Principals: [Insert names and titles, e.g., Jane Doe (CEO)]}

^{Key Staff: [Insert names and titles of executives, fund managers, or key guarantors]}

^{Helpful Context: [Insert headquarters city/state, primary asset classes (e.g., multifamily, retail), approximate AUM/unit count, and years active]}

When sharing, consider not only who the third party is, but how the third party is maintaining your obligation to confidentiality.

IMPORTANT NOTE

Using AI feedback features immediately and irrevocably shares all of the chat’s information (the documents, the prompts, literally everything) - regardless of the tool, settings, or permissions.

Read more about how to use AI to better understand investment materials.

Can we use AI and maintain confidentiality? Yes - if used conscientiously.

**IMPORTANT NOTE**

Read about confidentiality and AI before proceeding.

Click here.

**IMPORTANT NOTE**

Read about confidentiality and AI before proceeding.

Click here.

No specific prompt is necessary; AI works with natural speech prompts. If you are getting bad responses, try asking more specific, clear questions.

For tailored financial analysis, provide Notebook with your investment position and amount, as well as the details of any capital calls you participated in. This will give Notebook the information necessary to understand your position and provide information and analysis tailored to you.

Tip: Rename the Notebook with the sponsor and deal name so it’s easy to find later.

AI does not understand context very well or sometimes at all. It gives all information equal weight. So, a pitch deck’s assertion that 90% LTV is optimal is seen the same as an industry report warning of high-leverage risk. This is how AI can seemingly hallucinate or make illogical conclusions.

**IMPORTANT NOTE**

Read about confidentiality and AI before proceeding.

Click here.