Anthropic expands Claude into finance workflows with Microsoft 365 integration

Anthropic launched ten new Claude agent templates for financial services, expanding the AI assistant into some of the sector’s most time-consuming workflows, including pitchbook creation, credit memos, KYC reviews, financial modeling, and month end close.

The templates are available as plugins in Claude Cowork and Claude Code, and as cookbooks for Claude Managed Agents, allowing financial teams to deploy Claude on real work in days rather than months.

Each template combines task specific skills, governed data connectors, and subagents designed to handle specialized work such as comparables selection, methodology checks, and document review.

The new agent lineup includes pitch builder, meeting preparer, earnings reviewer, model builder, market researcher, KYC screener, valuation reviewer, general ledger reconciler, month end closer, and statement auditor. Anthropic said the agents can be adapted to a firm’s internal modeling conventions, risk policies, and approval processes.

The launch also pushes Claude deeper into Microsoft 365. Claude now works directly in Excel, PowerPoint, and Word through add ins, with Outlook support coming soon. In Excel, Claude can build financial models from filings and data feeds, audit formulas, and run sensitivity analyses. In PowerPoint, it can draft decks that update when underlying numbers change. In Word, it can edit credit memos against firm templates.

Anthropic is also expanding Claude’s financial data ecosystem with connectors from Dun & Bradstreet, Fiscal AI, Financial Modeling Prep, Guidepoint, IBISWorld, SS&C IntraLinks, Third Bridge, and Verisk.

Moody’s has also launched an MCP app that brings proprietary credit ratings and data on more than 600 million public and private companies into Claude for credit analysis, compliance, and business development.

The update reflects a broader push to move AI agents from generic chat interfaces into the tools and approval workflows used by financial professionals. Anthropic said Claude Opus 4.7 leads Vals AI’s Finance Agent benchmark with a score of 64.37%, positioning the model as part of its pitch to banks, asset managers, and insurers.