Financial Model Review Agent
The Financial Model Review Agent reviews project finance models in Excel for formula errors, hard-codes, circularity, inconsistent timing and assumptions that do not match the transaction documents. It reports key ratios such as DSCR, LLCR and equity IRR and explains what drives them, so your team can rely on the model going into credit approval and financial close.
Ideal forModel auditors
The difference
From 30-50 hours per model review to 6-10 hours
Your team gets a trustworthy model into credit approval sooner and spends review time on the assumptions that matter.
Done by hand
30-50 hours per model review
With the Vanine agent
6-10 hours
Time returned to your team
80%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Errors caught early
Model mistakes found at financial close are costly and embarrassing. The agent scans every sheet for common errors while there is still time to fix them.
Assumptions that match the documents
Tariffs, indexation, tax treatment and debt terms change during negotiation. The agent checks the model against the latest PPA, facility and project agreements.
Better use of model auditors
The agent clears routine issues first, so your formal model audit focuses on structure and judgement and runs faster.
Capabilities
Find model errors before they reach the term sheet or the credit committee.
Built for lenders, DFIs, sponsors, transaction advisers, model auditors and project finance teams reviewing infrastructure, energy and PPP financial models.
Formula integrity scan
Identifies inconsistent formulas across rows and columns, broken links, hard-coded values inside calculations and unusual constructs that hide errors.
Circularity and timing checks
Flags circular references, mismatched period flags and timing inconsistencies between construction, operations and debt repayment periods.
Assumptions book reconciliation
Compares tariffs, indexation, operating costs, tax, debt terms and reserve account rules with the PPA, facility agreements and term sheet.
SA tax and accounting treatment
Checks corporate income tax at 27%, VAT cash flows, dividends tax and interest limitation treatment such as section 23M against the model's structure.
Ratio and returns reporting
Reports DSCR, LLCR, gearing and equity IRR by period, with minimums and the drivers behind them.
Review log and query list
Produces a structured review log with cell references, severity and suggested fixes, ready to send to the modeller.
How it works
From your systems to a result you sign off
The modeller makes the corrections, and your financial adviser or model auditor signs off the final model.
Connect the places your financial models already live.
The Excel financial model, term sheet, PPA and facility agreements from SharePoint or the data room. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- Excel financial models
- Virtual data rooms
Runs on request in Teams, Copilot Studio, OpenAI Frontier or your own AI platform, with sensitive models kept on approved infrastructure.
A review log in Excel, a ratio summary and a short findings memo for the deal team.
Step by step
- 01
The deal team uploads the latest model and transaction documents.
- 02
The agent scans formulas, timing and circularity across every sheet.
- 03
It reconciles assumptions to the transaction documents.
- 04
It reports ratios and returns and drafts the review log.
- 05
The modeller resolves findings and the team reviews the updated model.
- 06
Your model auditor or adviser signs off the final version.
Deployment
Runs inside the tools your team already uses
The same agent and the same cited output, delivered three ways: through the AI assistant you have rolled out, on a model you host yourself, or inside your own software.
In the frontier assistant you already pay for
We publish the agent as an MCP server. Add it as a connector and your team calls it from the chat they use every day, with no new tool to learn.
"Trace the inputs to the source documents"
- model
- v23
- project
- Solar IPP
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your financial models never leave your network, which keeps POPIA and data residency straightforward.
- Llama
- Mistral
- Ollama
- or any OpenAI-compatible endpoint
Inside your own software
Trigger a run from your own workflows, and push the finished output into your ERP, GRC or reporting systems. We build the integration with your team.
- REST API
- Webhooks
- Batch jobs
- Embeddable review panel
Governed the same way, every route
Whichever way your team reaches the agent, identity, permissions and audit stay with your existing controls.
- Single sign-on through Entra ID, Okta or Google Workspace
- Reads only the documents each user is already allowed to open
- Every tool call written to an audit log you can export
How we deliver it
One agent, three ways to hold it
Start where your team already works, then take it as far into your systems as the value justifies.
DATA SECURITY & PRIVACY
Your financial models stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your financial models. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR FINANCIAL MODELS NEVER LEAVE YOUR ENVIRONMENT
More agents
More agents we build for South African enterprises
Each one is built on the same foundation: your documents, your rules, and your people signing off.
Precision AI for Institutional Workflows
