Loan Underwriting Assistant · Banking & Compliance
Give underwriters an organized file, not a stack of numbers
Each application gets a missing-document list, ratios with formulas shown and every policy rule checked. Not a credit decision: your underwriter decides.
Free account to start. Buying and running live need a paid plan.
- Starts when your form or app sends it something
- 1 AI step
- A person approves before it acts
- About 25 min to set up
Sound familiar?
The job, before and after this agent.
What it feels like today
- “Underwriters spend hours calculating ratios before they can start judging a file.”
- “Files reach underwriting with documents still missing.”
- “Policy checks get applied a little differently by each person.”
What you get with the agent
- Documents still missing under your policy, listed so loan operations can chase them
- DTI, DSCR, LTV and your other ratios calculated only from the figures sent, with each formula shown
- Every policy rule marked meets, doesn't meet or can't assess
- Strengths, risk notes, conditions to consider and neutral applicant questions
- Complete files queued for an underwriter and logged in your Google Sheets pipeline; incomplete ones sent to loan ops in Slack
Before
An underwriter picks up a file, finds the YTD P&L is missing, emails ops, then rebuilds the ratios in a spreadsheet.
After
Incomplete files go back to ops before they reach underwriting. Complete ones arrive with ratios, policy checks and questions ready, and the underwriter makes the decision.
How it works
The whole workflow, step by step.
Receives each loan application with its figures and the list of documents received from your origination system or form through a webhook. AI lists documents still missing under your policy, works out DTI, DSCR, LTV and your other ratios only from the figures sent (showing each formula; every ratio is recalculated in code, never by the AI), checks every policy rule and writes strengths, risk notes, conditions to consider and questions for the applicant. Incomplete files go to loan operations in Slack; complete files wait in Reviews for an underwriter, who makes the credit decision in your own system, and are logged in a Google Sheet. It never approves, declines or prices a loan, doesn't pull credit reports, and ignores and flags protected characteristics.
- TriggerNew loan application
- AI stepPrepare the underwriting summary
- LogicCheck the math
- LogicFile complete?
- Incomplete:Ask loan ops for missing items in Slack
- Complete:Underwriter reviews
- App callAsk loan ops for missing items in Slack
- OutputWaiting for documents
- Human approvalUnderwriter reviews
- Reviewed:Log the reviewed file
- App callLog the reviewed file
This is the workflow that opens in your workspace when you set the agent up. Every step can be edited.
- Step 1New loan applicationYour loan origination system or application form posts the application with its figures and the documents received to the webhook URL.
- Step 2Prepare the underwriting summaryAI checks documents against your policy, picks the figures for each ratio from the data (showing the formula), checks each policy rule and writes risk notes and questions for the underwriter. The ratios are then recalculated in code.
- Step 3Check the mathRecalculates each ratio (numerator ÷ denominator) in code — not by AI — writes the correct values into the summary and flags any ratio the AI got wrong for the underwriter.
- Step 4File complete?Incomplete files go to loan operations in Slack to collect what's missing; complete files go to an underwriter.
- Step 5Ask loan ops for missing items in SlackPosts the application, the missing documents and the questions for the applicant to your loan operations channel.
- Step 6Waiting for documentsThe run history keeps the partial summary.
- Step 7Underwriter reviewsAn underwriter reads the summary, ratios and policy checks in Reviews and makes the credit decision in your own system; approving logs the reviewed file.
- Step 8Log the reviewed fileAppends the application, ratios, policy-check results and summary to your underwriting pipeline sheet.
Example run
What goes in, and what comes out.
Example with fictional data
Comes in
A fictional $240,000 equipment loan for Riverside Machine Works: EBITDA $214,000, existing debt service $61,000, proposed annual payment $56,400, collateral appraised at $285,000.
The agent produces
DSCR = 214,000 ÷ (61,000 + 56,400) ≈ 1.82; LTV = 240,000 ÷ 285,000 ≈ 84%. Each policy rule checked, revenue decline noted as a risk, two applicant questions listed. Queued for an underwriter.
What you need
Everything it takes to run it.
About 25 minutes from purchase to live. A checklist above the canvas takes you through each step.
Plan
Included in Enterprise; on other paid plans it's $159 once. Agents run live on paid plans, from Basic ($39/mo).
Your AI key
Connect any of 14 AI providers on your own key. Your provider bills usage directly, at cost; we add no markup.
Apps
- SlackLive
- Google SheetsLive
Checklist
- A paid plan (agents run live on paid plans).
- An AI provider key (Settings → AI Providers).
- Slack and Google Sheets, connected in Settings → Integrations.
- An origination system or form that can send the application's figures to a webhook URL.
Setup, about 25 minutes
- Connect your AI provider. The AI steps run on your own key (OpenAI, Anthropic, Google and more). Add one in Settings → AI Providers.
- Connect Slack. Connect the Slack workspace your lending team uses (Settings → Integrations → Slack).
- Connect Google Sheets. Connect the Google account that can edit your underwriting pipeline sheet (Settings → Integrations → Google Sheets).
- Paste your underwriting policy. Open “Prepare the underwriting summary” and replace the placeholder with your policy.
- Pick the Slack account and loan ops channel. Open “Ask loan ops for missing items in Slack” and pick your account and channel. Invite the app to private channels first (/invite @Fluxo Flow).
- Pick your underwriting pipeline sheet. Open “Log the reviewed file” and pick your account, spreadsheet and tab. Header row: Application, Applicant, Product, Amount, Term, Ratios, Policy checks, Risk notes, Summary, Status.
- Test it with Dry Run. Press Dry Run: the agent runs on sample data with no messages sent and nothing written to your apps.
- Switch the trigger on. Open the trigger, switch the webhook on and have your origination system or form send each application to its URL.
Is it a fit?
Who it's for, and what it won't do.
Built for
- Community banks and credit unions doing SMB lending
- Equipment finance and specialty lenders
- Loan operations and credit analyst teams
What it doesn't do
- It is not a credit decision: it never approves, declines, prices or recommends a decision. An underwriter decides in your own system.
- It doesn't pull credit-bureau data or read scanned documents (PDF or image): it works from the figures and extracted text you send.
- It never estimates a missing figure: a ratio without its inputs is left blank and flagged.
- It doesn't send adverse-action or decision notices, and never uses protected characteristics.
We list the limits up front so you can decide before you buy.
Price
$159 one-time
Per workspace. It never renews.
- Included at no extra cost on Enterprise.
- Buying and running it live need a paid plan, from Basic ($39/mo).
- Dry Run costs nothing: simulated AI and app calls, nothing sent.
- AI usage is billed by your own provider, at cost. No AI credits to buy from us.
One-time agent purchases aren't covered by the 30-day money-back guarantee. Refund policy
FAQ
Questions about Loan Underwriting Assistant.
Does it approve, decline or price loans?
No. It's not a credit decision and says so in every summary. It never approves, declines, prices or recommends; an underwriter decides and records the decision in your own system.
What about fair lending?
It's instructed never to use or infer protected characteristics or proxies such as names or ZIP codes. If they appear in the data, it ignores them and flags the fields for removal.
Can it pull credit reports or read PDFs?
No. It works from the figures and extracted text your origination system or form sends, and leaves any ratio blank and flagged when an input is missing rather than estimating.
What does it take, and is it worth it?
About 25 minutes of setup with Slack and Google Sheets. It's a one-time purchase that never renews that takes ratio calculation and policy checking off every file. Live runs need a paid plan and your own AI key; Dry Run is free.
Does it approve or decline loans?
No. It prepares a summary for an underwriter and says so in every summary. The underwriter makes and records the credit decision in your own system.
Does it pull credit reports or read PDFs?
No. There's no credit-bureau connection. Send the figures (income, debts, credit data your system already pulled, financial statement totals) in the application data.
How does it handle fair lending?
It's told never to use or infer protected characteristics or proxies such as names or ZIP codes; if they're in the data it ignores them and flags the fields so you can remove them from the feed.
Is this a subscription?
No. Loan Underwriting Assistant is a one-time purchase of $159 per workspace and never renews. The Enterprise plan includes it at no extra cost. Running it live needs a paid plan (from Basic ($39/mo)), and your AI provider bills you directly for usage.
Can I test it before it touches real data?
Yes. Once it's set up in your workspace, Dry Run plays every step on sample data with simulated AI and app calls: nothing is sent and nothing in your apps changes. Switch the trigger on only when you're happy.
Put Loan Underwriting Assistant to work.
Free account, no credit card. Your Agents page opens with Loan Underwriting Assistant ready to buy and set up, then Dry Run it before it goes live.