# D2B — Data-to-Business Agent

> D2B takes spreadsheets made for people to read — several tables on one sheet, subtotal rows, decorative headers, inconsistent spellings — as they are, and delivers reconciliations, summaries and reports with every number traceable line by line. For AI agents it is a data plane with typed tables, lineage, versions and diffs, reachable over API, MCP, CLI and SDKs.

## Read these first

- Developer documentation (static, full text): https://docs.d2b.dev/llms.txt
- Everything in one file: https://docs.d2b.dev/llms-full.txt
- Quickstart: https://docs.d2b.dev/en/quickstart/
- MCP server (tools, connection): https://docs.d2b.dev/en/mcp/
- Concepts (workbook, table, sheet, version): https://docs.d2b.dev/en/concepts/

## Pages on this site

- https://d2b.dev/ — for people who work with spreadsheets
- https://d2b.dev/developers — for people building agents
- https://d2b.dev/pricing
- https://d2b.dev/privacy — privacy policy (includes the Google API Limited Use disclosure)
- https://d2b.dev/terms

## Blog

- https://d2b.dev/blog — articles on AI data analysis, spreadsheets made for people, lineage and provenance, agents and MCP. Every article is also available as Markdown at the same URL with `.md` appended (for example https://d2b.dev/blog/ai-data-analysis-sends-you-back-to-excel.md), and per-language feeds at /rss.xml and /<locale>/rss.xml.