Systematic checks
Every formula reconstructed from source. Every dependency mapped. Structural clarity before AI adds context.
Now accepting beta applications
Rigorous model analysis, inside Excel.
Every formula checked. Every assumption surfaced. Every dependency mapped. Systematic analysis and AI-assisted insights — at a fraction of the cost of a manual review, in minutes.
2,847
Formulas checked
81
Assurance score
50–70×
Faster than manual review
How it works
Three layers of intelligence. One clearer picture.
Kalc applies systematic checks first, AI-assisted insights second — so every finding is traceable to a cell, not a guess.
AI-assisted insights
Sector-aware logic checks on verified data — DSCR, IRR, NPV, and covenant patterns — explained with cell-level references.
Actionable output
Assurance score, severity-ranked findings, and an exportable analysis report — ready for your working papers and presentations.
The analysis flow
From raw model to informed next step
Understand
Structure mapped. Dependencies traced.
Validate
Formulas checked. References flagged.
Interpret
Logic assessed for purpose.
Prioritise
Findings ranked by severity.
Share
Exportable report for your review.
The problem
Model completion is not decision confidence
LLMs produce probable answers
Financial models are computation graphs, not text. A language model describes what a formula likely does — it cannot reconstruct every path and prove correctness.
Specialist review is hard to scale
The thorough model review you want before sharing a workbook is slow, expensive, and inconsistently documented — especially when timelines are tight.
Evidence gets buried
Findings scattered across chat transcripts, email threads, and verbal sign-off. Teams need cell-level references, severity scores, and a reproducible analysis record.
What you get
Systematic analysis in one workflow
Structural checks, AI-assisted insights, and exportable findings — applied in sequence inside Excel.
ASSURANCE SCORE
81High confidence
Debt!B12
DSCR covenant breach
Minimum 1.25× violated in years 3–5 · 96% confidence
Sheet3!C42
Hard-coded discount rate
8.5% embedded in formula chain · 94% confidence
Export analysis report ↗
Systematic checks
Every formula reconstructed from source. Every dependency mapped. Every broken reference traced — structural clarity before AI adds context.
AI-assisted insights
Sector-aware logic checks on verified structural data — DSCR, IRR, NPV, covenant patterns — explained with cell-level references.
Assurance scoring
Model-wide assurance score with severity-ranked findings. Critical, high, medium, and low — grouped for remediation, not buried in noise.
Structure mapping
Complete dependency graph across sheets — orphaned cells, broken external links, and fragile points mapped before a single finding is raised.
Version comparison
Side-by-side model versions with cell-level change tracking and impact analysis — built for revision cycles and stakeholder updates.
Exportable report
Analysis report formatted for working papers, presentations, and internal review — timestamped and traceable to source cells.
For AI-built models
The agent builds. Kalc verifies.
AI can build a financial model in minutes — but it can't independently check its own work, and neither can the copilot that helped write it. Kalc is the independent check in the loop: deterministic verification and findings your agent can act on. Kalc identifies issues and suggests remediation; it does not advise on legal, financial, or other matters.
Verify in the loop
Call Kalc from your agent over API or MCP. Every formula, dependency, and financial-logic rule checked deterministically — not guessed. Findings anchored to the exact cell.
Findings your agent can act on
A remediation brief written for a build agent to read: what to change, where, and why — grouped by severity. Your agent fixes and resubmits; Kalc reports what resolved, what's still open, and what regressed.
Built for agent workflows
POST /sessions— submit a version, get findings, deltas, and a gate status your orchestrator can branch on.GET /audit/{id}/brief.md— an agent-ready remediation brief, ready to paste into your build agent.
Available over REST and as an MCP server. Kalc verifies; it never builds. Findings identify and suggest — they are not legal, financial, or professional advice.
Built for trust
Confidential by architecture — not by policy
🇪🇺
EU-hosted data
All model analysis processed and stored within EU infrastructure. No transatlantic transfers of your deal data.
🔒
Zero AI retention
Zero data retention on AI inference. Your formulas are analysed to produce findings — not stored or used for training.
⚖️
GDPR Article 28
Data processing agreement available. You remain the controller; Kalc acts as your processor.
◆
Separate from authorship
Kalc did not build your model and cannot edit it. It identifies issues and suggests remediation — analytical support only, not legal, financial, or professional advice. You decide how findings are used.
Beta program
Shape the product from day one
Full analysis access during beta
All analysis layers included at no cost. Project Finance, M&A, Infrastructure, and Real Estate cohorts now onboarding.
Direct line to the team
Report bugs, request features, and get timely responses from the people building Kalc — not a support queue.
Influence the roadmap
We are looking for analysts who will run Kalc on real models and tell us, candidly, what they find within fourteen days.
Early-adopter pricing at launch
Beta participants receive locked early-adopter pricing when Kalc launches commercially.
Get early access
Apply for beta access
We are onboarding a limited number of analysts in this cohort. Tell us about your work and we will respond within 48 hours.
- Full analysis layers at no cost during beta
- Direct access to the Kalc team
- Early-adopter pricing locked at commercial launch
Application received!
We will review your application and respond within 48 hours. Keep an eye on your inbox — or reach us at hello@kalc.tech.
Already have an invite? Install the add-in →
Questions
Frequently asked
What does Kalc analyse?
Excel financial models — formulas, dependencies, assumptions, and financial logic. Kalc reconstructs every calculation path, applies sector-specific checks, and returns severity-ranked findings with cell-level evidence directly inside Excel.
How is this different from ChatGPT or Copilot?
Language models produce probable descriptions of formulas. Kalc applies systematic checks first, then AI-assisted insights — with cell-level references you can review. Kalc did not build your model.
Where is my data processed?
On EU infrastructure. Zero data retention on AI inference is available. Self-hosted and air-gapped deployments are supported for regulated environments.
What is included during beta?
Full access to all analysis layers at no cost. Direct support from the Kalc team. We request first impressions within fourteen days of your first analysis.
Which sectors are supported?
Project Finance, M&A, Infrastructure, and Real Estate templates are in active beta. General financial logic checks apply to all models regardless of sector.
Every model deserves a second look.
Systematic analysis at machine speed — a fraction of the cost of a manual review.
Request an analysis →