Financial Statement Analysis Agent

The agent reads any set of IFRS or IFRS for SMEs annual financial statements, extracts the key line items into your spreading template and calculates standard and custom ratios. It reviews the notes for risk signals and flags anomalies, delivering a structured analysis ready for your credit paper or investment review.

Ideal forCredit teams

The difference

From 4-6 hours to 5-10 minutes

Your analysts move from data capture to credit judgement, handling more applications without adding headcount.

Done by hand

4-6 hours

With the Vanine agent

5-10 minutes

Time returned to your team

98%

Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.

End manual spreading

Banks, DFIs and SME lenders still key AFS figures into spreadsheets by hand for every credit paper. The agent does it consistently in minutes.

Like-for-like comparison

Varied labels and formats are mapped to your standard chart of accounts, so every borrower is assessed on the same basis.

Fewer errors, faster decisions

Integrity checks catch statements that do not balance or add up, and faster turnaround means quicker answers for your clients.

Capabilities

From annual financial statements to a spread credit analysis in minutes.

Built for credit analysts, auditors, investment analysts and lenders at SA banks, DFIs and SME lenders.

Automated financial spreading

Extracts line items from IFRS or IFRS for SMEs statements directly into your spreading templates.

Custom ratio calculation

Calculates standard or proprietary ratios, from liquidity and leverage to profitability, consistently every time.

Trend and variance analysis

Compares years or interim periods to highlight variances and trends in revenue, margins and costs.

Note and disclosure analysis

Reads the notes for accounting policy changes, contingent liabilities, going concern matters and covenant risks.

Statement normalisation

Maps varied labels such as 'Turnover' and 'Revenue' to your standard chart of accounts for like-for-like comparison.

Data integrity checks

Confirms the statement of financial position balances and totals add up, catching errors at source.

How it works

From your systems to a result you sign off

The spread and analysis land ready for the credit analyst to review before they feed the credit paper and any credit decision.

SharePointOutlookTeamsExcel
Any system you use
Connects

Connect the places your client financials already live.

AFS and management accounts from your credit origination system, SharePoint or the applications inbox, with optional bureau data from TransUnion or Experian. 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 spreading templates
  • Credit origination systems
  • Credit bureau data (TransUnion, Experian)
Works in

Microsoft Teams, Copilot Studio or OpenAI Frontier on request, or as a scheduled batch for incoming applications.

Automated financial spreading
Custom ratio calculation
Trend and variance analysis
Note and disclosure analysis
Statement normalisation
Data integrity checks
Delivers to

Your Excel spreading template and a summary of ratios, trends and flags, written back to the credit file or origination system.

Step by step

  1. 01

    Financial statements arrive with a new application or annual review.

  2. 02

    The agent extracts and normalises line items into your template.

  3. 03

    It calculates ratios, trends and integrity checks.

  4. 04

    It reviews the notes and flags anomalies and risks.

  5. 05

    Your analyst reviews the spread and signs off for the credit paper.

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.

Model Context Protocol

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.

Adopting frontier AI across your teams
Called from ClaudeMCP connected

"Spread the FY2023 to FY2025 AFS"

Toolfinancial_statement_analysis.spread_financials
borrower
Borrower (Pty) Ltd
years
FY2023-FY2025
Returned3 years spreadEvery finding linked to its source document
Self-hosted

On a model you host yourself

Run the agent on open-weight models in your data centre or private cloud. Your client financials never leave your network, which keeps POPIA and data residency straightforward.

  • Llama
  • Mistral
  • Ollama
  • or any OpenAI-compatible endpoint
Sovereign AI on your infrastructure
Bespoke systems

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
Custom integrations from our software factory
Governance

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 your data is handled

DATA SECURITY & PRIVACY

Your client financials stay yours.

The agent runs inside your tenancy, reads only what each task needs, and never trains on your client financials. Every step is logged so your auditors can see exactly what it touched.

Built for regulated work.

+
WHAT THE AGENT KEEPSONLY THE OUTPUTENCRYPTED AT REST0 BIT AES0% DELETABLE0 TRAINING RUNS

YOUR CLIENT FINANCIALS 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

Build once.Deploy across teams.Improve over time.