Monitor portfolio · PCT-063 · Sourced card

Spot repricings and takeouts

A direct-lending PM wants a quarterly list of portfolio names that were repriced tighter, partially repaid or taken out, cross-checked against public BDC books that hold the same borrower.

Direct lendingBDCsPublic dataBuildable in-house

Today vs automated

TODAY

Open two quartersAnalyst · manual
Line up spreadsAnalyst · manual
Search refi newsPM · manual
Email / meeting hand-offAnalyst → PM

AUTOMATED

Quarter-end: repayment notices and BDC filings arriveTrigger: starts on its own
Diff the schedulesAutomated · Document store
Flag repriced or exitedAutomated · LLM
Attach filing rowsAI draft, human review · Monitoring model
Whether a repricing is worth matching to keep the borrowerApprove / override · PM

AutomatedAI draft, human reviewHuman onlyTools: Inbox / portal, Document store, LLM, Monitoring model, Loan system

Estimated valueestimate

12–90 analyst hours a year
$2k–$22k of time, vs an assumed $10k–$40k tool cost

Net: −$38k to $12k a year net of tool cost; at the low end of the assumptions it does not cover the tool cost.

Manual4–8 h per quarterly reviewWith AI0.5–1 h per quarterly review, review included

Assumptions

4–8 analyst hours per quarterly review today; 0.5–1 hours with an agent, including review
4–12 quarterly reviews a year for one team
$150–250 per hour loaded cost
Tool or build cost $10,000–40,000 a year (in-house)

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

What else it can do for the team

Cross-check against your own book
Rank exposure at risk of takeout
Feed into origination outreach
Draft the market note
Track repricing trend

How you get thereFour steps from prompting to an agentic workflow; most teams start at step 2.

1 · PromptingAn analyst asks a chat tool about one quarterly review.
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.
Typical starting point

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.

Solution optionsBuy (4 vendors listed), build or hybrid, with the trade-offs of each.

Buy
9fin, Debtwire, The LoanEdge, Standd
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 team4–8 h → 0.5–1 h per quarterly review (estimate); coverage goes from a sample of borrowers, quarterly to every borrower, every delivery.

ROLESAnalysts move from re-keying packs to reviewing exceptions and calling borrowers.

CYCLE TIME4–8 h → 0.5–1 h per quarterly review (estimate)

COVERAGEFrom a sample of borrowers, quarterly to every borrower, every delivery.

CONTROLSEvery output cites its source; approvals and overrides are logged.

How it works

Full title: Refi leakage watch: which of your borrowers are repricing or leaving for the syndicated market

“Q3: $16.39bn left direct lending for the syndicated market. The 10-Qs show who repriced to stay.”

Scenario

Public: a direct-lending PM wants a quarterly list of portfolio names that were repriced tighter, partially repaid or taken out, cross-checked against public BDC books that hold the same borrower.

What the human still decides

Whether a repricing is worth matching to keep the borrower. That's a relationship and pricing call the agent can't make.

Why it matters

PitchBook/LCD data reported by Reuters: in Q3 2026, $16.39bn of direct-lending loans were refinanced in the syndicated market versus $2.60bn moving the other way, while estimated Q3 direct-lending volume fell 28% year on year.

What the record shows

Checked 2026-10-16.

Reuters, citing PitchBook/LCD: $16.39bn of direct-lending loans refinanced into the syndicated market in Q3 2026 against $2.60bn the other way. Five of the seven reconciled BDCs (ARCC, BCRED, HTGC, MAIN, OBDC) show the defence: among 1,405 issuers with one spread-bearing row in both their 31 Mar and 30 Jun 2026 SOIs, 98 had their spread cut (77 of them by exactly 25bp) and 45 had it raised. The same borrower was repriced in two books at once: one utility-services borrower's spread went from 4.50% to 4.25% at both BCRED and ARCC, where ARCC's cost also fell from $212.2m to $162.2m. ARCC reported $2.9bn of exited commitments in Q2.

Try it: prompt and data

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.