Daloopa

What Daloopa does

Daloopa supplies source-linked public-company financial data and AI tools for investment research. Its product family connects reported figures to spreadsheet modeling, company comparisons and custom research applications. It is aimed at public-equity analysts, investment banks, asset managers and developers building financial research tools. The central use is keeping a financial model connected to the disclosures behind its numbers, rather than repeatedly copying figures from reports.

Data and Excel modeling features

Data Sheets provide downloadable company financial information for starting coverage or adding data to an existing workbook. The Excel Add-In connects models to Daloopa’s fundamental database for subsequent updates. Reported numbers link to their original sources, giving reviewers a route back to the underlying disclosure when a line item needs explanation.

Daloopa Scout is an Excel-native AI modeling assistant. It supports building three-statement models, updating an existing workbook after earnings and comparing metrics across a peer group. Quick-start prompts help specify an initial task; custom skills save reusable prompts. Global instructions capture preferences such as formatting and tie-out logic, while chat history lets an analyst return to earlier conversations. These controls help make a repeated quarterly task more consistent.

For developers, the platform also offers API and cloud delivery. Its MCP service connects compatible AI tools to financial data through an authenticated, read-only connection. That is a way to retrieve research inputs in an AI client; it does not turn the data service into a brokerage or trade execution system.

An earnings update workflow

Consider an analyst maintaining a retailer’s operating model. Start with a copy of the existing workbook and ask Scout to add the latest reported quarter, identify newly disclosed metrics and highlight changed cells. Review the source links for revenue, margins and company-specific operating indicators. Check that the period labels, currency and units match the model, then reconcile the statements before revisiting forecasts.

For a peer comparison, specify the companies, reporting periods and definitions of the metrics to compare. Keep reported actuals separate from your own assumptions. A useful review asks whether two similarly named metrics mean the same thing and whether a restatement changes the historical comparison. Document those checks alongside the assumptions so another analyst can follow the comparison.

Coverage and review limits

Daloopa focuses on covered public companies. Before adopting it, check the tickers, history and industry-specific disclosures needed for your research. A source link makes a number inspectable; it does not establish that a generated formula, forecast or interpretation is appropriate. Analysts still need to review model changes and exercise judgment about assumptions. Teams connecting an external AI client should separately consider that client’s handling of the retrieved data.

Pricing and access

The plans page offers limited free Data Sheets access and sales-led paid packages. Core, Premium and API options differ in included delivery methods and usage allowances. Request the current allowance for Scout, MCP and downloads, and confirm whether API or cloud delivery requires a separate agreement. Do not assume that a free data account includes unrestricted AI modeling.