Per-record sensitivity propagation. Compounds across multi-client engagement work.
bench · sensitivity →The model layer
your stack is missing.
You've automated the rest — AP, AR, the close — with Claude Code, MCP, and your ERP's API. The financial model is the last thing still living in a spreadsheet. Flatland is the typed, recomputable, audit-trailed layer that fixes that: assumptions with names and types, a real dependency graph, institutional-grade exports your board, investors, diligence partner, or auditor expect.
Largest compiled DAG in the benchmark suite. Whatever your client throws at you fits.
bench · scale-warm →Institutional Excel-export rubric. Six-sheet structure, named ranges, blue inputs / black formulas, every export.
rubric · public →Same IR always produces same outputs. Audit-defensible against any skeptical board.
determinism →A sensitivity sweep across 50 drivers counts as ONE billable compile. Templated multi-client work compounds cleanly inside the metered tier.
metered pricing →Average client model fits in the free tier. Metered overage only on the heavy ones.
pricing detail →Inputs · typed assumptions
Outputs · compiled in topological order
Assertions · guardrails
The automation layer is done.
The model layer is the last frontier.
Intake
Your compile contributes to the live system heartbeat. Anonymized: no model contents, names, or assumptions leave your browser.
Excel export with live formulas available in the Workshop after signing up.
One typed model, four cuts, one afternoon — whether that's four clients, four business units, or four scenarios. The two in signal-orange flagged assertions you'd otherwise hunt by hand. Each cut still gets its own 100/100 Excel and its own audit trail. The leverage is throughput; the moat is that nothing ships unaudited.
Bill the same.
Deliver more.


