LatestAll news

Home / Use cases / PCT-077

Report · PCT-077 · Sourced card

ILPA template and DDQ drafts

Maps the fund ledger to ILPA Reporting Template lines and drafts DDQ answers from approved sources, flagging every low-confidence line.

Worked example: The ledger offsets transaction fees but not monitoring fees, which LPA §8.3 also offsets at 100%. The Q2 template would overstate the net management fee by 103,000. See the walk-through ↓

Direct lendingABF / asset-basedCredit secondariesSample data · real docs confidentialVendor + in-house
INPUTFund GL, LPA and approved answersAI STEPSMap to template lines · Draft fromapproved docs · Route for sign-offOUTPUTMapped ILPA template and cited DDQdraftsHUMAN CHECKA person reviews and decides

Today vs automated

TODAY
  1. Map GL accountsAnalyst · manual
  2. Search past DDQsAnalyst · manual
  3. Draft each answerHead of research / IR · manual
  4. Email / meeting hand-offAnalyst → Head of research / IR
AUTOMATED
  1. Quarter-end close, or a new DDQ arrivesTrigger: starts on its own
  2. Map to template linesAutomated · Data store
  3. Draft from approved docsAutomated · LLM
  4. Route for sign-offAI draft, human review · Reporting template
  5. Every classification judgment on fees and expenses, and every answer that goes to an LPApprove / override · Head of research / IR

AutomatedAI draft, human reviewHuman onlyTools: Filing feeds, Data store, LLM, Reporting template

Estimated valuesourced + estimate

160–2,100 analyst hours a year
$24k–$525k of time, vs an assumed $20k–$100k tool cost

Net: −$76k to $505k a year net of tool cost; at the low end of the assumptions it does not cover the tool cost.

Manual8–16 h per DDQWith AI2–4 h per DDQ, review included
Assumptions
  • 8–16 analyst hours per DDQ today; 2–4 hours with an agent, including review
  • 40–150 DDQs a year for one team
  • $150–250 per hour loaded cost
  • Tool or build cost $20,000–100,000 a year (both)

Sourced figures

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

What else it can do for the team

  • Flag answers that changed since the last DDQ to that LP
  • Check consistency across a whole questionnaire
  • Pre-fill the capital call and distribution template
  • Route answers to owners for sign-off
  • Keep an approved answer library current
Worked walk-throughKey catch: The ledger offsets transaction fees but not monitoring fees, which LPA §8.3 also offsets at 100%. The Q2 template would overstate the net management fee by 103,000.

1. The input

The public ILPA Reporting Template guidance sets the target lines. The fund ledger is SAMPLE.

SAMPLE: fictional company, illustrative figures. Not a real borrower, deal or lender group.

GL extract Q2 2026 (SAMPLE): 6110 Management fee 2,450,000 · 6125 Transaction fee offset (310,000) · 6240 Broken-deal legal 185,000 · 6310 Fund administration 140,000 · 6420 GP travel to LPAC 22,000

Adviser ledger, fees received from portfolio companies Q2 2026 (SAMPLE): transaction fees 310,000 · monitoring fees 103,000

LPA §8.3 (SAMPLE): “The Management Fee shall be reduced by 100% of all Transaction Fees, Monitoring Fees and Break-up Fees received by the Manager or its Affiliates.”

2. What the AI produces

GL accountTemplate lineConfidenceFlag
6110 Management feeManagement fees, grossHigh
6125 Fee offset: transaction feesManagement fee offsetsHighUnder-offset by 103,000. LPA §8.3 offsets 100% of transaction and monitoring fees (413,000); the GL offsets transaction fees only (310,000)
6240 Broken-deal legalPartnership expenses: broken dealMediumLPA decides partnership vs GP cost
6310 Fund adminPartnership expenses: administrationHigh
6420 GP travel to LPACInternal chargeback?LowNeeds LPA reading; flagged

DDQ draft (excerpt): “Q: How are broken-deal expenses allocated? A: Per LPA §8.2, broken-deal expenses are partnership expenses… [source: LPA §8.2; 2025 DDQ answer 4.7, approved by CFO]”

3. What a person still checks

  1. The CFO or controller signs off every low and medium confidence mapping against the LPA.
  2. Compliance checks that every DDQ answer still matches current policy and filings.
  3. IR confirms nothing in an answer is a forward-looking claim or inconsistent with what other LPs were told.

4. Where it breaks

  • A ledger built for GAAP doesn’t split expenses the way the template does; some lines need manual allocation.
  • Answer libraries go stale; a confident draft can cite last year’s policy.
  • Side letters can change fee terms for specific LPs.
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 DDQ.
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 (12 vendors listed), build or hybrid, with the trade-offs of each.
Buy
Ontra, V7 Go, Lumonic, Allvue, Chronograph, Cobalt, Indus Valley Partners (IVP for Credit), WhaleBlue, Henon, Acuity Analytics, Ellis, Hypercore
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 team8–16 h → 2–4 h per DDQ (estimate); coverage goes from the names someone had time to pull to the full set, refreshed when sources change.
ROLESAnalysts move from collecting data to writing the view.
CYCLE TIME8–16 h → 2–4 h per DDQ (estimate)
COVERAGEFrom the names someone had time to pull to the full set, refreshed when sources change.
CONTROLSEvery output cites its source; approvals and overrides are logged.
How it works

Full title: LP reporting: map the fund ledger to the ILPA Reporting Template and draft DDQ answers from approved documents

“Broken-deal costs: partnership expense or GP cost? The LPA decides.”

Scenario

A credit fund in its investment period must deliver the updated ILPA Reporting Template and is answering a stream of LP due diligence questionnaires.

What the human still decides

Every classification judgment on fees and expenses, and every answer that goes to an LP.

Why it matters

ILPA's updated template applies from Q1 2026 to funds still investing, and DDQ automation tools now target private markets IR teams directly.

What the record shows

Checked 2026-10-18.

ILPA's guidance sets first delivery of the updated Reporting Template for the Q1 2026 period for funds still in their investment period; Ontra, Intralinks and Tribble each market AI-drafted DDQ answers with review workflows.

Try it: prompt and data
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.

Data

Walk-through uses a SAMPLE deal pack: fictional company, illustrative figures. In practice the inputs are your own confidential borrower or fund documents; keep them inside an approved environment.

Who uses it, vendors and build
Segments
Direct lending, ABF / asset-based, Credit secondaries
Who uses it
Investor relations, Fund CFO, Fund controller
Build
Vendor + in-house
In-house
Mapping is a one-time build per fund; DDQ drafting needs a maintained answer library.
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

Related cards

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.