LatestAll news

Home / Prompts

35 prompts · by sector

Deal-team prompt library

Every prompt from the catalog in one place. Each says what to cite and what not to opine on. Check the data label before you paste anything: real deal documents belong only in your firm's approved tools.

Direct lending

  1. PCT-004 · Kill the deal in 10 minutes: the agent that screens every CIM against your fund's box

    Here are our fund criteria: {criteria}. Read the attached CIM. For each criterion output pass/fail/unclear, the figure, and the page number. Then list the 5 most important unanswered questions. Do not recommend a decision.
    Sample data · real docs confidential

  2. PCT-002 · Covenants, baskets and add-backs out of a 200-page credit agreement, every line cited to a section

    From this credit agreement, list every financial maintenance covenant with level, test date, and section number. Quote the definition of Consolidated EBITDA add-backs verbatim. If unsure, say 'not found'.
    Public + sample docs

  3. PCT-008 · EBITDA add-back autopsy: how much of this borrower's EBITDA exists only in the credit agreement?

    Quote the Consolidated EBITDA definition verbatim. List every add-back with its cap, lookback, and section. Then build a bridge from reported EBITDA {r} to maximum covenant EBITDA and state the add-back share.
    Public + sample docs

  4. PCT-010 · Lender-on-lender violence radar: scan every credit agreement for J.Crew, Serta, and Chewy trapdoors

    For this credit agreement, state whether it contains (a) a J.Crew blocker, (b) a Serta blocker, (c) a Chewy blocker. Quote the operative language and section, or say 'not found'. Do not give a legal opinion.
    Public data

  5. PCT-007 · Don't trust the compliance cert: re-run the covenant math from the monthly pack, automatically

    Using the covenant definitions in sections {x}, recompute total leverage and fixed charge coverage from the attached monthly packs for the test period. Compare with the certificate. Show each input with its source and flag any difference above 0.1x.
    Sample data · real docs confidential

  6. PCT-034 · The SEC asked how you calibrate your marks. An agent builds the evidence pack for every Level 3 loan

    For each holding below, list every other BDC holding the same borrower in the June 30, 2026 SOI data with cost, fair value and FV/cost, linked to each 10-Q. Flag where our FV/cost is more than 5 points above the median of other holders. Do not opine on the correct value.
    Public data

  7. PCT-063 · Refi leakage watch: which of your borrowers are repricing or leaving for the syndicated market

    Compare the 31 Mar and 30 Jun 2026 Schedules of Investments for {BDC}. For issuers with a single floating-rate debt row in both quarters, list every spread change, cost paydown above 10%, and position that disappeared, with links to both filings. Do not infer why a position changed.
    Public data

  8. PCT-064 · Spread step-ups and new PIK: the amendment trail a quarterly SOI diff leaves behind

    From the 31 Mar and 30 Jun 2026 SOIs for {BDC}, list every single-row issuer whose spread rose or whose PIK component appeared or grew. Show both rates, both marks and both filing links. State 'reason not disclosed' unless a cited source gives one.
    Public data

  9. PCT-066 · AI exposure isn't one number: tag direct compute, infrastructure, enablers and AI-substitution risk separately

    Tag each position in {portfolio} as L1 direct compute, L2 data-centre infrastructure, L3 power/fibre enabler, L4 AI-substitution risk, or none. Quote the sentence that justifies each tag; no quote, no tag. Report exposure by layer, drawn and undrawn.
    Public data

  10. PCT-071 · Every borrower's quarterly pack, spread into one monitoring model: covenant headroom tracked quarter by quarter

    You are a private credit monitoring analyst. Using the attached compliance certificate, monthly financials and the facility's EBITDA definition (with caps), produce one row in our monitoring template: revenue, reported EBITDA, each add-back by category with its cap, net debt, covenant ratio and headroom. Recompute the ratio yourself. List every difference from the certificate with the page it comes from. Do not assess credit quality.
    Sample data · real docs confidential

  11. PCT-073 · Recurring revenue loan: test ARR leverage and minimum liquidity, and check whether the borrower can flip to EBITDA

    Using the credit agreement excerpt and this month's KPI pack, recompute Recurring Revenue under the agreement's definition, then test Total Debt to Recurring Revenue, Minimum Liquidity and the conversion leverage test. Show each figure with its source line. Flag any item counted by the company but excluded by the definition.
    Sample data · real docs confidential

  12. PCT-074 · Amendment or waiver request in: what is being asked, who has to consent, and what it does to the covenant

    Read this amendment request and the facility's amendments clause. Table each ask, the consent class it needs, and the clause. Recompute the projected covenant ratio with and without the asks using the figures provided. List prior amendments. Draft five questions for the sponsor. Do not recommend whether to consent.
    Sample data · real docs confidential

  13. PCT-075 · Agent notices against your book: interest, rate fixings, amortization and fees reconciled before cash lands

    Extract the attached agent interest notice into fields. Recompute our share using our position, the pricing grid and actual/360. Show expected vs noticed for rate, interest, principal and fees, and list each break with both values. Draft a short query to the agent for each break.
    Sample data · real docs confidential

  14. PCT-076 · Early-warning brief across the book: financials, reporting behaviour, requests and news in one cited watchlist draft

    For each borrower, review the attached packs, delivery log, request log and news items. List each soft signal with its date and source. Apply our rules (attached) and draft a half-page brief for any borrower with three or more signals. Do not predict default or assign ratings.
    Sample data · real docs confidential

  15. PCT-077 · LP reporting: map the fund ledger to the ILPA Reporting Template and draft DDQ answers from approved documents

    Map the attached GL extract to the ILPA Reporting Template expense and fee lines. Show account, template line, quarter amount and confidence, and flag any account needing an LPA reading. Then draft answers to the attached DDQ questions only from the approved documents provided, citing each source.
    Sample data · real docs confidential

CLOs

  1. PCT-037 · CLO compliance what-if: if these five loans drop to CCC, which OC test fails first?

    Using the indenture test definitions and the SAMPLE portfolio below, compute CCC %, CCC excess haircut, and each class's OC and IC ratio before and after this scenario: {downgrades/defaults}. Show the formula and indenture section for each test. Flag any test that fails. Do not propose trades unless asked.
    Sample data · real docs confidential

  2. PCT-042 · CLO equity and mezz surveillance: 30 deals, 12 managers, one cushion table the morning reports land

    From these SAMPLE CLO monthly reports, extract junior OC and IC test values and triggers, CCC %, defaulted par, WARF and the last equity distribution, each with a page cite. Put them in one table, compute month-on-month change, and flag any metric whose definition differs between reports.
    Sample data · real docs confidential

  3. PCT-027 · Shadow-rate a borrower on the agency's own grid, then re-score your internal ratings when financials land

    Using the attached published methodology, list each scorecard factor and its thresholds. Map this company's 10-K figures to each factor with cites. Output an indicated range labeled 'illustrative, not a rating'.
    Public data

  4. PCT-075 · Agent notices against your book: interest, rate fixings, amortization and fees reconciled before cash lands

    Extract the attached agent interest notice into fields. Recompute our share using our position, the pricing grid and actual/360. Show expected vs noticed for rate, interest, principal and fees, and list each break with both values. Draft a short query to the agent for each break.
    Sample data · real docs confidential

Credit secondaries

  1. PCT-038 · Credit secondaries: price a 150-loan tape in an afternoon, with every mark benchmarked to public BDC marks

    For each loan on this SAMPLE tape, find matching borrowers in the June 30, 2026 BDC SOI data and list each holder's FV/cost with a link. Flag loans where the tape mark exceeds the max public mark by more than 3 points. Bucket the tape by those flags. Do not recommend a price.
    Public + sample docs

  2. PCT-039 · Continuation vehicle diligence: roll or sell? An agent reads the CV docs and the loan book for LPs

    From this SAMPLE continuation-vehicle election pack, extract the price, NAV date, deadline, default election, fee and carry terms, and the fairness opinion's scope limits, each with page cites. Compare them with the original fund terms. Do not recommend roll or sell.
    Sample data · real docs confidential

  3. PCT-003 · Same loan, different marks: who else holds your borrower, how they value it, and who might sell

    Across all SOI rows for quarter {q}, find holdings whose issuer name matches '{name}' (show match confidence), and table BDC, tranche, cost, fair value, FV/cost. Highlight where marks differ by >5 points.
    Public data

  4. PCT-034 · The SEC asked how you calibrate your marks. An agent builds the evidence pack for every Level 3 loan

    For each holding below, list every other BDC holding the same borrower in the June 30, 2026 SOI data with cost, fair value and FV/cost, linked to each 10-Q. Flag where our FV/cost is more than 5 points above the median of other holders. Do not opine on the correct value.
    Public data

  5. PCT-068 · Pricing a private credit LP stake: reconcile the bid to the advisers' surveys and the underlying marks

    For {fund interest}, tabulate H1 2026 credit secondary pricing from Jefferies, Campbell Lutyens and Evercore with each one's definition. Then place {bid} against each, adjusting for senior/junior mix and software share. Cite every figure.
    Public data

  6. PCT-077 · LP reporting: map the fund ledger to the ILPA Reporting Template and draft DDQ answers from approved documents

    Map the attached GL extract to the ILPA Reporting Template expense and fee lines. Show account, template line, quarter amount and confidence, and flag any account needing an LPA reading. Then draft answers to the attached DDQ questions only from the approved documents provided, citing each source.
    Sample data · real docs confidential

ABF, fund finance, infra & SRT

  1. PCT-035 · Will the new concentration limit bite? Test your portfolio against your back-leverage facility's eligibility limits

    From this credit facility agreement and its amendments, extract every eligibility criterion, concentration limit and advance rate with section cites. Then, for the attached SAMPLE portfolio, compute the borrowing base before and after the latest amendment and list loans whose classification is ambiguous.
    Public data

  2. PCT-040 · SRT reference pool analyzer: what's actually in the pool you're insuring, and what can the bank add later?

    From this SAMPLE SRT term sheet, extract eligibility criteria, replenishment conditions, concentration limits and credit event definitions with cites. Then construct the weakest portfolio permitted by those criteria from the SAMPLE obligor universe and compare its rating and sector mix with the current pool.
    Sample data · real docs confidential

  3. PCT-003 · Same loan, different marks: who else holds your borrower, how they value it, and who might sell

    Across all SOI rows for quarter {q}, find holdings whose issuer name matches '{name}' (show match confidence), and table BDC, tranche, cost, fair value, FV/cost. Highlight where marks differ by >5 points.
    Public data

  4. PCT-069 · ABF data-tape anomaly screen: duplicate collateral, stale borrowing-base assets and impossible loan fields

    Screen {tape} against {facility reports}: list any asset ID, VIN, invoice or obligor ID appearing in more than one active facility; any asset sold or paid off but still in the borrowing base; and any row breaking the eligibility criteria in {agreement section}. Cite the row and rule for each break.
    Public data

  5. PCT-071 · Every borrower's quarterly pack, spread into one monitoring model: covenant headroom tracked quarter by quarter

    You are a private credit monitoring analyst. Using the attached compliance certificate, monthly financials and the facility's EBITDA definition (with caps), produce one row in our monitoring template: revenue, reported EBITDA, each add-back by category with its cap, net debt, covenant ratio and headroom. Recompute the ratio yourself. List every difference from the certificate with the page it comes from. Do not assess credit quality.
    Sample data · real docs confidential

  6. PCT-072 · Borrowing base certificate, re-run from the tape: eligibility, concentration excess and true availability

    Using the facility agreement excerpt (eligibility, concentration limits, advance rate) and the attached receivables tape, rebuild the borrowing base as of the certificate date. Show gross balance, each ineligible category, concentration excess, eligible balance, borrowing base and availability next to the borrower's certificate. Cite the clause and tape rows behind each difference.
    Sample data · real docs confidential

Special situations / distressed

  1. PCT-010 · Lender-on-lender violence radar: scan every credit agreement for J.Crew, Serta, and Chewy trapdoors

    For this credit agreement, state whether it contains (a) a J.Crew blocker, (b) a Serta blocker, (c) a Chewy blocker. Quote the operative language and section, or say 'not found'. Do not give a legal opinion.
    Public data

  2. PCT-003 · Same loan, different marks: who else holds your borrower, how they value it, and who might sell

    Across all SOI rows for quarter {q}, find holdings whose issuer name matches '{name}' (show match confidence), and table BDC, tranche, cost, fair value, FV/cost. Highlight where marks differ by >5 points.
    Public data

  3. PCT-074 · Amendment or waiver request in: what is being asked, who has to consent, and what it does to the covenant

    Read this amendment request and the facility's amendments clause. Table each ask, the consent class it needs, and the clause. Recompute the projected covenant ratio with and without the asks using the figures provided. List prior amendments. Draft five questions for the sponsor. Do not recommend whether to consent.
    Sample data · real docs confidential

BDCs

  1. PCT-001 · Every loan a BDC marks below 90 cents, ranked and linked to the filing

    Using the SOI table from the SEC BDC data set for CIK {cik}, period {date}, compute fair value/cost for every holding, list those under 0.90 sorted ascending, show the inline XBRL URL per row, and summarize in 5 bullets. Do not speculate on causes.
    Public data

  2. PCT-003 · Same loan, different marks: who else holds your borrower, how they value it, and who might sell

    Across all SOI rows for quarter {q}, find holdings whose issuer name matches '{name}' (show match confidence), and table BDC, tranche, cost, fair value, FV/cost. Highlight where marks differ by >5 points.
    Public data

  3. PCT-011 · Cash to PIK, caught in the filing: flag every loan that switched to paying in kind this quarter

    Compare the June 30 and March 31, 2026 Schedules of Investments for {BDC}. List every position whose interest terms moved from all-cash to any PIK component (or back), with both rate descriptions, both marks and links to both filings. If you cannot match a position confidently, say so.
    Public data

  4. PCT-030 · The SaaSpocalypse in the marks: which lenders hold the software loans AI might eat

    From each filer's {quarter} Schedule of Investments, tag holdings with the filer's own industry heading or Industry column (no name matching). Tie tagged subtotals to the filer's industry table within 0.5%. Compute narrow and broad software share of FV per BDC and list software names below 90% of cost.
    Public data

  5. PCT-036 · Who's prorating? A non-traded BDC redemption tracker from tender-offer filings

    For each non-traded BDC in {list}, find the Q3 2026 SC TO-I and final amendment on EDGAR. Extract shares tendered, accepted, the cap and the proration ratio, with links. Do not characterize any fund.
    Public data

  6. PCT-034 · The SEC asked how you calibrate your marks. An agent builds the evidence pack for every Level 3 loan

    For each holding below, list every other BDC holding the same borrower in the June 30, 2026 SOI data with cost, fair value and FV/cost, linked to each 10-Q. Flag where our FV/cost is more than 5 points above the median of other holders. Do not opine on the correct value.
    Public data

  7. PCT-063 · Refi leakage watch: which of your borrowers are repricing or leaving for the syndicated market

    Compare the 31 Mar and 30 Jun 2026 Schedules of Investments for {BDC}. For issuers with a single floating-rate debt row in both quarters, list every spread change, cost paydown above 10%, and position that disappeared, with links to both filings. Do not infer why a position changed.
    Public data

  8. PCT-064 · Spread step-ups and new PIK: the amendment trail a quarterly SOI diff leaves behind

    From the 31 Mar and 30 Jun 2026 SOIs for {BDC}, list every single-row issuer whose spread rose or whose PIK component appeared or grew. Show both rates, both marks and both filing links. State 'reason not disclosed' unless a cited source gives one.
    Public data

  9. PCT-065 · BDC non-accrual watch: reported rates vs what the Schedule of Investments implies

    For {BDC}'s 30 Jun 2026 10-Q: report non-accruals at cost and fair value from the earnings release; compute the cost of SOI rows below 50% of cost as a share of total cost; compute PIK interest income ÷ gross investment income from XBRL. Show each figure with its source link.
    Public data

  10. PCT-067 · Same borrower, different managers: where Ares, Blackstone and Blue Owl books agree and where they don't

    For every borrower held by two or more of ARCC, BCRED, FSK, GBDC, HTGC, MAIN and OBDC at 30 Jun 2026, list each holder's FV/cost, the max–min gap and the filing rows. Sort by gap. Flag where the holders' rows are different tranches.
    Public data

  11. PCT-012 · The 2027–28 maturity wall, BDC by BDC, and which borrowers can't refinance at today's rates

    From the SOI rows for {quarter}, bucket principal by maturity year (≤2026, 2027, 2028, later) per BDC and by sector. Flag PIK and software rows. Output a table and chart with filing links.
    Public data

Insurance, private IG and ratings

  1. PCT-027 · Shadow-rate a borrower on the agency's own grid, then re-score your internal ratings when financials land

    Using the attached published methodology, list each scorecard factor and its thresholds. Map this company's 10-K figures to each factor with cites. Output an indicated range labeled 'illustrative, not a rating'.
    Public data

  2. PCT-034 · The SEC asked how you calibrate your marks. An agent builds the evidence pack for every Level 3 loan

    For each holding below, list every other BDC holding the same borrower in the June 30, 2026 SOI data with cost, fair value and FV/cost, linked to each 10-Q. Flag where our FV/cost is more than 5 points above the median of other holders. Do not opine on the correct value.
    Public data

  3. PCT-037 · CLO compliance what-if: if these five loans drop to CCC, which OC test fails first?

    Using the indenture test definitions and the SAMPLE portfolio below, compute CCC %, CCC excess haircut, and each class's OC and IC ratio before and after this scenario: {downgrades/defaults}. Show the formula and indenture section for each test. Flag any test that fails. Do not propose trades unless asked.
    Sample data · real docs confidential

  4. PCT-042 · CLO equity and mezz surveillance: 30 deals, 12 managers, one cushion table the morning reports land

    From these SAMPLE CLO monthly reports, extract junior OC and IC test values and triggers, CCC %, defaulted par, WARF and the last equity distribution, each with a page cite. Put them in one table, compute month-on-month change, and flag any metric whose definition differs between reports.
    Sample data · real docs confidential

  5. PCT-062 · The private letter rating pack: assemble what the rating agency and the insurer's regulator will ask for, with every figure sourced

    Map this rating agency data request {request} to {closing_set}, {model}, {credit_agreement}. Fill each item with a cited figure or document. Mark items you cannot source. Flag any figure that differs between documents. Do not characterize credit quality.
    Sample data · real docs confidential