Finicast
DemosLog inSign up

The database AI agents use for financial models

Financial models, built by your AI agent.

One prompt in Claude or ChatGPT. A live model your team can steer.

Use Finicast (https://finicast.com/for-agents) to build a five-year forecast for CoreWeave

Works in Claude, ChatGPT, Claude Code, Codex and Cursor. No account, no connector.

finicast.com/w/…/d/overview
The dashboard the prompt produces: an editable drivers table, KPI tiles and charts for a five-year forecast
Here is your model in Finicast:CoreWeave five-year forecastdashboard · editable assumptions · 7 cardsOpen →

Built by Claude from that prompt. Change a driver and every statement follows. Open the live model

Open a demo model.

Each is a live workspace built from a tested document: change a driver, watch every statement follow, download the workbook. The document behind each one is linked, so an agent can start from it.

DCF valuation

Unlevered free cash flow with mid-year discounting, a WACC build-up, perpetuity and exit-multiple terminal values, the equity bridge, and sensitivity tables of price per share.

Open the model → Document

Sales operations

A $55M ARR SaaS sales org: 2,000 opportunities, funnel, BDR scorecards, quotas, accelerators, kickers and SPIFFs, with dashboards for the CRO, VP Sales, sales ops, reps, SDRs and marketing.

Open the model → Document

Ledger to model

A general ledger CSV becomes a monthly operating plan: actuals through August, a driver-based forecast, budget beside outlook, YTD and full-year by entity and department. Click any account to drill into its ledger entries.

Open the model → Document

< 1 msto recalculate a 100,000-row ledger
12 ruleswhere a spreadsheet needs 480 formulas
1 requestfrom document to statements and a link
0 accountsto start: npm install -g finidb

From prompt to model in three steps.

  1. 1

    The agent writes rules, not cells.

    revenue[frame=fcst] = PREV(revenue) * (1 + growth)
gross_profit        = revenue - cogs
cash[frame=fcst]    = PREV(cash) + cash_flow.free_cash_flow
  2. 2

    Finicast calculates every period.

    Income statement, cash flow, balance sheet. One document in, statements and a link out.

  3. 3

    You steer.

    Change a driver. Every dependent cell updates in milliseconds, for everyone with the link.

Operating model · line × period · 8 rules
The Finicast workspace: line items on rows, years on columns, the rule bar below

Charts that carry the story.

This is a live card from a Finicast dashboard, not a screenshot: Intel's month-end close since 2013, with every chief executive appointment marked and the interim periods shaded. The agent wrote the annotations into the model document. Click any month and it drills into that month's daily closes.

INTC month-end close, with each CEO appointment

Click a bar or point → daily
Loading…

Open the model → Document Prices from Financial Modeling Prep, frozen in the document with their as-of date.

Built for agents. Made for people.

Rules, not cells

A rule names a line item and the region it covers. One rule, every forecast period.

A real dependency graph

An edit recomputes only what depends on it. Verified against a reference evaluator.

Dashboards people can edit

Drivers in a table, KPIs and charts that follow. The agent declares them in the same document.

Every interface an agent needs

MCP, REST, a JSON model document, an npm CLI, a skill file. Every error carries a fix.

Why not a spreadsheet, or a script.

SpreadsheetScriptFinicast
A 40-line, 12-period statement480 cell formulasA few hundred lines≈ 12 rules
Forecast vs. actual periodsHand-picked rangesIndex arithmeticframe = fcst
One input changesWhole workbookRe-run the scriptOnly what depends on it
What the person getsA fileA numberA live model to steer

One document in. Statements and a link out.

{
  "periods":  { "start": "2022-01", "count": 9, "grain": "year", "histUntil": "2025-12-31" },
  "pivots": {
    "assumptions":      { "lines": ["revenue_growth", "gross_margin"], "inputs": { "revenue_growth": { "fy2026": 0.6 } } },
    "income_statement": { "lines": ["revenue", "cogs", "gross_profit"],
                          "inputs": { "revenue": { "fy2025": 5131 } },
                          "rules":  "revenue[frame=fcst] = PREV(revenue) * (1 + assumptions.revenue_growth)" }
  },
  "outputs": "all",
  "dashboards": "auto"
}
curl -X POST https://finicast.com/api/build --data @model.json
# → statements as markdown + a link to the live workspace
  • Hosted MCP finicast.com/api/mcp
  • Local npx -y finidb mcp · build offline with finidb build
  • Source-available under PolyForm Noncommercial

Docs for agents → llms.txt

Free to learn on. Licensed for business.

Community

Free

Self-hosted from npm, for noncommercial use.

npm install -g finidb

Commercial

Per organization

A license for the engine in a business or a product.

Talk to us

Ask your assistant for a model.

Copy the promptOpen the live model