LatestAll news

Home / Use cases / PCT-003

Underwrite · PCT-003 · Published note

Who else holds this borrower

A deal team pricing a new loan to a sponsor-backed software company wants to know which BDCs already lend to it and at what marks.

BDCsDirect lendingResearch & ratingsPublic dataVendor + in-house
INPUTBDC schedules of investmentsAI STEPSMatch names across filings · Listholders and marks · Flag mark gapsOUTPUTHolders, marks and mark gaps perborrowerHUMAN CHECKIssuer names are not standardized

Today vs automated

TODAY
  1. Open 10+ 10-QsAssociate · manual
  2. Ctrl-F the borrower nameAssociate · manual
  3. Paste marks into ExcelVP / counsel · manual, re-keying
  4. Email / meeting hand-offAssociate → VP / counsel
AUTOMATED
  1. A new deal enters the pipelineTrigger: starts on its own
  2. Match names across filingsAutomated · Document parser
  3. List holders and marksAutomated · LLM
  4. Flag mark gapsAI draft, human review · Model template
  5. Issuer names are not standardizedApprove / override · VP / counsel

AutomatedAI draft, human reviewHuman onlyTools: Data room, Document parser, LLM, Model template

Verified example

Verified example: one borrower, three public lendersDiagram: Hyland Software, a software first-lien borrower, is held by ARCC, OBDC and GBDC. Edges show each holding and its mark as a percentage of cost; each lender's holding is reported in its June 30, 2026 10-Q.holds 1L · 100.8%holds 1L · 97.0%holds one-stop · 96.3%reported inreported inreported inHyland Software(software, 1L)ARCCOBDCGBDCARCC 10-Qfiled 2026-07-29OBDC 10-Qfiled 2026-08-05GBDC 10-Qfiled 2026-08-03
  • Lender / BDC
  • Borrower
  • Filing
How one borrower links three public lenders and the filings that report it. Verified example: SEC BDC Data Set, period ending 2026-06-30, checked against each filed schedule (ARCC, OBDC, GBDC 10-Qs). Marks are fair value ÷ cost for the position shown in the data set; OBDC and GBDC also list other tranches of the same borrower, not drawn. The borrower is named as each filing reports it; inclusion is not a credit view. Sponsor and agent bank are not disclosed in the schedules, so they are not drawn. Not investment advice.

Before: scattered rows

Where it sitsRow text (as filed)FV ÷ cost
ARCC 10-Q, Schedule of InvestmentsHyland Software, Inc. | First lien senior secured loan100.8%
OBDC 10-Q, Schedule of InvestmentsHyland Software, Inc | First lien senior secured loan | Non-Affiliated97.0%
GBDC 10-Q, Schedule of InvestmentsHyland Software, Inc. | One stop 1 | Non-Affiliated Issuer96.3%

Three filings, name strings that don’t match exactly, two different tranche labels. Nothing in the rows says they are the same company.

Question the graph answers

Which lenders share this borrower, and who marks it lowest?

One hop from Hyland Software: ARCC, OBDC and GBDC. Lowest mark: GBDC at 96.3% of cost. Two hops: the filing behind each mark.

Estimated valueestimate

70–1,160 analyst hours a year
$10k–$290k of time, vs an assumed $20k–$100k tool cost

Net: −$90k to $270k a year net of tool cost; at the low end of the assumptions it does not cover the tool cost.

Manual1–3 h per lookupWith AI0.1–0.3 h per lookup, review included
Assumptions
  • 1–3 analyst hours per lookup today; 0.1–0.3 hours with an agent, including review
  • 100–400 lookups a year for one team
  • $150–250 per hour loaded cost
  • Tool or build cost $20,000–100,000 a year (both)

Estimate, based on the assumptions shown; your numbers will differ. How we estimate

What else it can do for the team

  • Find co-lenders before an amendment call
  • Check your mark against peers each quarter
  • Spot crowded names across managers
  • Support the valuation committee pack
  • Track position size changes by holder
How you get thereFour steps from prompting to an agentic workflow; most teams start at step 4.
1 · PromptingAn analyst asks a chat tool about one lookup.
Needs: an approved AI tool, a confidentiality policy.
Risk: unchecked answers, data pasted outside policy.
2 · WorkflowA fixed pipeline extracts the same fields into your template every time.
Needs: field definitions, a template, document parsing.
Risk: breaks silently when formats change.
3 · AgentIt watches the inbox or data room, runs the checks and drafts the output.
Needs: inbox/doc-store access, system write-back, logging.
Risk: acting on a misread; needs review gates.
The automated lane above
4 · Agentic workflowSeveral agents work across the deal or book; people approve exceptions.
Needs: shared data model, permissions, audit trail, exception queue.
Risk: errors compound across steps; needs monitoring.
Typical starting point
Solution optionsBuy (3 vendors listed), build or hybrid, with the trade-offs of each.
Buy
Octus, The LoanEdge, Canoe Intelligence
Fastest start; you adapt to the product's data model and pricing.
Build
An LLM API, a document parser, a vector or document store, your data warehouse, and a review queue.
Fits your definitions exactly; you own maintenance and controls.
Hybrid
Vendor extraction feeding your own checks, templates and systems.
Common middle path; two things to integrate and govern.

Listing is not endorsement.

What changes for the team1–3 h → 0.1–0.3 h per lookup (estimate); coverage goes from the sections someone had time to read to every clause and schedule checked against the term sheet.
ROLESAssociates move from reading and retyping to checking cited exceptions.
CYCLE TIME1–3 h → 0.1–0.3 h per lookup (estimate)
COVERAGEFrom the sections someone had time to read to every clause and schedule checked against the term sheet.
CONTROLSEvery output cites its source; approvals and overrides are logged.

Who-holds demo →

How it works

Full title: Same loan, different marks: who else holds your borrower, how they value it, and who might sell

“Same loan, several lenders, different marks. Every number links to the 10-Q.”

This card now includes former PCT-015 (Find the forced sellers: which lenders hold a stressed name, and at what mark?).

Scenario

Public: a deal team pricing a new loan to a sponsor-backed software company wants to know which BDCs already lend to it and at what marks.

What the human still decides

Issuer names are not standardized. Treat every match as a possible match and confirm the entity and tranche in each filing before quoting it.

Why it matters

The SEC staff statement asks valuation teams to calibrate to available market information. Other BDCs' marks on the same loan are public evidence your valuation committee will be asked about.

Before and after

Before

  1. Search several 10-Qs by hand for the borrower name
  2. Reconcile different legal-entity names
  3. Copy cost and fair value into a comparison sheet, or pay for a BDC research tool

After (agent first draft)

  1. Agent normalizes issuer names across all SOI rows for a quarter
  2. Returns every BDC holding a matching name with tranche, cost, fair value and FV/cost
  3. Highlights where marks on the same name differ

Agent pattern: normalize names → join across filers → compare marks → label matches 'possible'

Tools

  • SEC BDC SOI data set
  • Fuzzy-match script
  • Static JSON on this site
Try it: prompt and data
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.

Data

Public data. Issuer-name matching is approximate; different tranches and entities can share a name.

Who uses it, vendors and build
Segments
BDCs, Direct lending, Research & ratings
Who uses it
Deal team (pricing a new deal), Credit analyst, LP / credit research
Build
Vendor + in-house
In-house
This site's SOI pipeline + fuzzy name matching. Estimate: 1 week.
Last verified
2026-10-15

Vendors that claim this capability

Tags reflect each vendor's own public claims at the linked page (checked 2026-10-15). Not tested, ranked or endorsed.

Sources and related
In the news.

Next step

Get new walk-throughs

Subscribe to the newsletter

Not investment advice. Names marked SAMPLE are fictional. Found an error? See the corrections log.