87ns
Per-record sensitivity propagation: 4-arg typed DAG.
bench · commit 46a6328 →Financial Reasoning
Infrastructure.
Every compile produces a signed, re-derivable receipt — anyone holding your model can re-run it and get the same receipt. No trust in us required. That's computation provenance. Flatland is the infrastructure that makes it structural.
Your model, your receipt. We hold neither.
Financial models as code. · Typed IR. · Deterministic compile. · Client-owned custody.
scroll ↓
live · system pulse0 compiles · 0 in last window
4,000drivers
Largest compiled DAG in the benchmark suite. Cold compile, zero errors.
bench · scale-warm →100/ 100
Institutional Excel-export rubric. Three-pass compile, no drift.
rubric · six-sheet test →bit-identical
Same IR always produces the same outputs. Deterministic, recomputable.
determinism test →MCP+ REST
Both protocols, day one. Your agent calls the same engine your CFO can curl.
api reference →50free to start
Then $0.10 per answer. No seat licenses. No proposal.
pricing detail →Not a spreadsheet.
Not a chatbot.
A typed compilation layer.
Spaceland · consumer hardware + subscription · fictitious demo model
compiling the model…
The automation layer is done.
The model layer is the last frontier.
Flatland is that layer.
Specimen · what every compile produces
Three-Statement Modelcompiled · 24 drivers · 4/4 assertions · 1ms
Inputs · typed assumptions
Starting ARR$2.40M
Monthly ARR growth rate8.0%
Monthly gross churn rate1.5%
COGS as % of revenue22.0%
Gross margin target78.0%
Monthly operating expenses (base)$180,000
OpEx growth per quarter4.0%
D&A monthly$8,000
Cash on hand (opening)$4.20M
Accounts receivable days30
Accounts payable days45
Outputs · compiled in topological order
Ending ARR$2.56M
Monthly revenue$213,000
Monthly COGS$46,860
Gross profit$166,140
Gross margin78.0%
EBITDA$-13,860
EBIT$-21,860
Accounts receivable$213,000
Accounts payable$70,290
Cash from operations$-148,570
Ending cash$4.05M
Net monthly burn$13,860
Runway292.3 mo
Assertions · guardrails
✓Gross margin ≥ 45% — SaaS floorgross_margin >= 0.45
✓Cash never goes negativeending_cash >= 0
✓Runway ≥ 12 monthsrunway_months >= 12
✓Net positive growthmonthly_arr > 2400000
content hash 3faa5866a910… · re-derivable from this IR · client-owned
Same IR → same outputs. Deterministic, re-derivable.Fork this in the Workshop →
Every compile produces this. Typed assumptions, an explicit dependency graph, assertions that catch bad structure, and a re-derivable content hash you can recompute independently. This is Financial Reasoning Infrastructure as a visual. The Excel ships too — but this is the source of truth.
See the institutional Excel proof →Four ways inpick the surface that fits the work
01 · Finance Engineers→
The compile layer the category runs on.
Compiled answers across your engagement roster. Typed drivers, recomputable models, audit-trailed exports. Built for the firm that bills as fast as it can defend the work.
100 / 100
institutional Excel rubric, every export
02 · Founders→
Your Series A model, compiled.
Describe your business in natural language. Out comes a typed model with named assumptions, named ranges, and an Excel your investor will read. Thirty minutes, not three weeks.
≤30 min
first compile to investor-ready Excel
03 · AI-Native developers→
A financial modeling MCP your agent can call.
Typed IR. DAG. Sensitivity. Scenarios. Excel. One npx command and your agent harness has a deterministic finance backend. No custom-tool glue, no JSON-pretending-to-be-a-model.
MCP + REST
both protocols, day one
04 · Platforms→
The typed substrate platforms embed.
If you're building a finance product on top of LLMs, Flatland is the deterministic layer underneath. We sit below your agent and behind your UI: IR in, audit-grade artifact out. You keep the customer; we hold the math.
OEM-able
embed the engine, brand the surface
Quantitative reasoning,
compiled.
Flatland · index of everything
For
Learn
Comparisons
Disasters
© 2026 Flatland · Financial Reasoning Infrastructure · live pulse · awaiting first compile