Purchasing Guides / Rent Roll & T-12 Underwriting Prep

Rent Roll & T-12 Underwriting Prep

A purchasing guide to buying a workflow that turns a seller's rent roll and trailing operating statement into clean, checked inputs for your underwriting model, with differences listed for your analyst.

Yearly running cost

Assuming 480 deal packages a year

By hand: $48K / year; 960 hours of work
Subscription: $1.2K+ / year
This workflow: $207 / year; Machine usage only; setup, hosting and review are extra.

What should it prepare?

Normalise each deal's rent roll and operating statement into your format. Review the tie-out checks instead of re-keying every line.

One deal package includes up to 500 rent roll units and 12 months of operating statement.

Prepare uploaded deal packagesRent roll and statement in, checked inputs out$1,152 – 3,600 setupFill my underwriting modelChecked inputs written to your model template$1,728 – 5,400 setup

Your analyst owns the assumptions and the investment decision. No valuations, offers or lender submissions.

What is included

Read rent rolls and operating statements in spreadsheet or PDF form, normalise units and lines to your format, check totals against the source and list differences.

Start with rent rolls and trailing operating statements in spreadsheet or PDF form, your chart of accounts and analyst-checked examples. The model option fills the input tab of your own model template; it does not set underwriting assumptions.

How accurate should the prepared inputs be?

Neat columns are not enough. Choose how often unit and account values must be right, whether totals must tie to the source and which differences it must flag.

StandardReliable unit and account values, with unmapped lines held for review.Rent roll fields correct: ≥99%Statement lines mapped correctly: ≥97%IncludedStrictA second check of totals and mappings, with more tests on unusual exports.Rent roll fields correct: ≥99.5%Statement lines mapped correctly: ≥99%Setup +$288 – 840My own targetsAgree your own acceptance requirements with the provider.Quote separately

How these standards are measured

Test on held-out deals your analysts have already prepared, including scanned and differently formatted exports. Totals must tie to the source documents; a silently dropped unit or account line is a failure.

Targets for your selected standard
What is checked	Target
Rent roll fields correctUnit, type, area, rents, lease dates and status must match the source row. A missing or merged unit counts as wrong.	≥99%
Statement lines mapped correctlyCorrectly mapped lines divided by all lines labelled by your analyst; lines with no agreed account must be held, not guessed.	≥97%
Totals that tie to the sourceUnit counts, rent totals and statement totals must equal the source document, or the package is not released.	≥100%
Differences flaggedCorrectly flagged differences, such as occupancy that disagrees with income, divided by all labelled differences.	≥95%

Use exact decimal arithmetic for money. A prepared input is not a valuation; your analyst checks the differences and sets the assumptions.

How quickly do you need each deal package?

Choose how quickly a deal package should be ready for review. Your analyst's checking time is separate.

Within 5 minutesIncludedWithin 2 minutesSetup +$144 – 480Within 60 secondsSetup +$288 – 840

Timing details

Time from accepting both documents to stored normalised inputs, including parsing, mapping, tie-out checks, queueing and retries. Confirm the document sizes and hardware with your provider.

The target applies to at least 95% of agreed test runs, with 2 in progress at a time.

How much do you want to spend per deal package?

Choose the machine budget for reading documents and mapping lines. Tighter budgets may use fewer AI checks on spreadsheet inputs.

Up to $3.00IncludedUp to $1.50Setup +$72 – 360Up to $1.00Setup +$216 – 600

Cost details

Includes model calls, retries and shared hosting allocation. Analyst review, data subscriptions and the calling agent are separate. Failed and repeated runs also consume resources.

Reference machine cost: $0.93 – 1.93 per deal package at 40 deal packages a month. The selected cap is a target to test, not a replacement for this estimate.

Where do you want it to run?

Keep deal documents in your cloud or on your own server. Choose whether document pages may go to an approved AI service.

Run it onAI model access

Data and access details

Runs in a cloud account you control, with access controls and logs.

Only the deal document pages being prepared go to the selected external model. Agree access and retention first.

Restrict access to authorised deal folders and keep tenant names out of model requests where possible. No external calls uses uploaded files and private inference; it cannot use the connected model option.

How do you want to use it?

Use a review page, your current AI agent or a dedicated underwriting agent. You can choose more than one.

A review web pageUpload a rent roll and operating statement, review tie-out checks and export the normalised inputs.IncludedMy existing AI agentAsk your agent to submit deal documents and retrieve the normalised inputs and differences.Setup +$72 – 240A dedicated agentUse a dedicated underwriting agent to prepare deal packages and explain tie-out differences.Setup +$144 – 480

Anything else your provider should know?

Optional. Your choices are included automatically.

Deal packages per monthYour setup budget (USD)

Your documents, chart of accounts or model

Common questions

Do I need this if an extraction add-in already exists?

Not necessarily. A subscription may fit if its formats and output suit your model. Buy a workflow when you need your own chart of accounts, tie-out rules, environment or agent access.

Does it underwrite the deal?

No. It prepares checked inputs. Your analyst sets rent growth, expenses and other assumptions and makes the investment decision.

Can it handle different property systems and scanned documents?

Yes, if you include those formats in the test set. Unreadable pages and unmapped lines are flagged for review rather than guessed.

Can it fill our own Excel model?

Choose the model scope. It writes a new copy of your template's input tabs and leaves formulas and assumptions untouched.

Can I run it without an external AI service?

Yes. Choose private processing and supply your own hardware. Measure accuracy and running cost during the pilot.