Capital Refinery
Private equity underwriting software

Underwriting that survives close.

Most underwriting software is built to get the deal team to IC approval. Capital Refinery is built to keep the underwriting alive across the life of the position — so the assumptions the team relied on at entry remain testable against the operator data the firm is already collecting.

The honest read on the category

What underwriting tools say they do, and what actually happens.

The standard workflow ends at IC approval. The structural problem starts the day after.

What teams think they have
What actually happens
01The model captures the deal team's view of the asset.
The model is a snapshot. Eighteen months later, the operator data has moved and the model is sitting in a folder with the version date in the filename.
02The IC memo documents the thesis and conditions.
The memo is a Word document on a shared drive. The thesis is prose, not a typed object — there is no place in the data model where the assumption lives as a testable clause.
03The diligence pack supports the decision.
The pack lives in the data room. The data room expires at close. The most analytically dense work the firm has done on this asset becomes inaccessible the day the wire clears.
04The team will know if the thesis stops working.
Most firms answer the question by rebuilding the analytical state from scratch every quarterly review. The original underwriting did not stay alive — it stayed in the folder.
05The platform supports the decision over time.
The platform supports the deal team to approval. After approval, the platform vendor walks away. The position is governed by a static artifact and an analyst's memory.
What underwriting software has to do now

Three things the dominant tools do not ship.

01 / 03

A structured investment record at IC

Not a Word document. A typed object.

Thesis, assumptions, conditions, KPIs — bound at IC approval as separate, individually-testable rows. From the moment the wire clears, the platform has a reference point against which every operator update can be tested. Decision validity stops being a memory exercise and starts being a property the platform can compute.

02 / 03

Deterministic-first extraction with provenance

Every figure traces back to the source page.

A regex-and-constructor sweep produces candidate figures from the CIM, the financials, and the credit agreement. A small local LLM adjudicates conflicts. Every number has a candidate ID and a provenance trail. When the assumption gets re-tested in year three, the team can trace it back to the line in the source document — not to the LLM that drafted the model.

03 / 03

A continuous binding from operator data to assumption

Quarter after quarter, for the life of the position.

Each accounting feed and KPI report is mapped to the entry assumption it tests. The connection is structural, not generated. When conditions change enough that the original IC decision is no longer defensible, the platform surfaces it — with the assumption that broke and the time-to-consequence ranking against the rest of the portfolio.

Side by side

Where the lines fall.

CapabilityGeneric underwriting toolsCapital Refinery
Financial extraction from CIMs and statementsLLM-first, citation-style provenanceDeterministic-first with candidate IDs and source-page provenance
Draft model generationYes — strong in the new AI categoryYes — but as input to the structured record
Structured investment record at ICNo — output is a model file or a Word memoYes — bound at approval with thesis, assumptions, conditions
Operator data → entry assumption mappingNo — handoff at ICYes — the data model
Decision validity scoring across the positionNoYes — live across the life of the deal
Covenant + breach probability for credit positionsNo — not in the underwriting layerYes — for credit positions
Time-to-consequence rankingNoYes
Deal workspace · 3 min
The deal workspace, with the underwriting bound to the live data.

A walkthrough of the workspace where the IC memo is a structured object, the assumptions are typed rows, and every figure traces back to the source page in the diligence pack. The same workspace stays alive after close.

Recorded against a real seeded deal. Every figure shown is reproducible from the parsed source documents.
REC · 03:02

Bring us the underwriting from a deal you closed last year.

The fastest way to feel the gap is to compare what your current underwriting tool produced for the IC pack to what a structured investment record looks like in year three. Real document, real position, 60–90 minutes.