
Image: Flickr / Wikimedia Commons
Anthropic Launches Ten AI Agent Templates for Financial Services
Pre-built agents for pitchbooks, credit memos, KYC screening, and month-end close can now be deployed in days via Claude Cowork, Claude Code, or as fully autonomous Managed Agents.
This article was produced by the AETW editorial team.
Anthropic has released ten ready-to-run AI agent templates for financial services work - from building pitchbooks to closing the books at month-end - deployable in days via Claude Cowork, Claude Code, or as autonomous Managed Agents on the Claude Platform.
Ten agents, built to ship in days
Anthropic today released ten ready-to-run agent templates targeting the most time-consuming analyst and operations work in financial services. The templates cover research and client coverage - pitch building, meeting prep, earnings review, and financial model creation - as well as credit, risk, compliance, and back-office finance work including KYC screening, general ledger reconciliation, month-end close, and statement auditing.
Each template bundles three components: skills (domain-specific instructions and knowledge), connectors (governed, real-time access to financial data sources), and subagents (additional Claude models called in for specific subtasks like comparables selection or methodology checks). Firms can adapt any template to their own modeling conventions, risk policies, and approval flows without starting from scratch.
Two deployment tracks
The templates are deployable two ways. As a plugin in Claude Cowork or Claude Code, an agent runs alongside the analyst on their desktop - hand the Pitch Builder a target list and it returns a comps model in Excel, a pitchbook drafted in PowerPoint, and a cover note ready in Outlook. This is the assisted track, where Claude works with the human rather than instead of them.
As a Claude Managed Agent, the same template runs autonomously on the Claude Platform - suited for work that spans a whole book of deals or runs on a nightly schedule. Anthropic provides the infrastructure a firm would otherwise engineer itself: long-running sessions, per-tool permissions, managed credential vaults, and a full audit log in the Claude Console where compliance and engineering teams can inspect every tool call and decision. Both tracks keep the human in the loop; the agent prepares, the professional approves.
Claude now runs across all four Microsoft 365 apps
Alongside the agent templates, Anthropic announced that Claude add-ins for Excel, PowerPoint, and Word are now generally available, with Outlook coming soon. The key addition is cross-application context: an analyst who starts a financial model in Excel does not need to re-explain it when that work moves to PowerPoint or Word. Claude carries the context across all four platforms automatically.
For financial services specifically, this matters because a meaningful portion of analyst time is spent moving information between spreadsheets, slide decks, and email. Claude in Outlook can triage an inbox, arrange meetings, and draft responses in the user's voice. In Excel it builds financial models from filings and data feeds, audits formulas across linked workbooks, and runs sensitivity analyses. In PowerPoint, decks update automatically when the underlying numbers change.
New data partners and the Moody's MCP app
The launch also expands Anthropic's financial data ecosystem. New connectors include Dun and Bradstreet for verified business identity, Third Bridge for expert interview transcripts, Verisk for insurance underwriting data, SS&C IntraLinks for deal room access, Fiscal AI for real-time public equities fundamentals, and IBISWorld for industry-level sector data. These add to an existing roster that already includes S&P Capital IQ, MSCI, PitchBook, Morningstar, LSEG, and Daloopa.
The marquee addition is Moody's, which has launched a full MCP app - going beyond a standard connector by embedding Moody's proprietary interface directly inside Claude. It gives users access to credit ratings and data on more than 600 million public and private companies for compliance, credit analysis, and business development work without leaving the Claude interface.
The underlying model powering all of this is Claude Opus 4.7, which Anthropic says leads Vals AI's Finance Agent benchmark at 64.4%, and tops the GDPval-AA evaluation for economically valuable knowledge work. The agent templates are available at the financial services marketplace on GitHub.
The bigger picture
Today's release is part of a broader Anthropic push into financial services that has accelerated significantly in 2026. Claude is already in production at JPMorganChase, Goldman Sachs, Citi, AIG, Visa, BNY, and Carlyle. Separately, FIS announced a partnership with Anthropic to build an AI agent that compresses anti-money-laundering investigations from days to minutes, with BMO and Amalgamated Bank among the first institutions deploying it.
What Anthropic is building in finance is not just model access. It is an end-to-end stack: purpose-built agents, deployment infrastructure, audit tooling, and a curated data ecosystem tied directly into the systems financial professionals already use. The question for the industry is how quickly firms move from piloting to putting these agents on production workflows - and how much of the traditional analyst stack that displaces over a two-to-three year horizon.
Sources
AI & Technology Researcher
Brian Weerasinhe is the founder and editor of AI Eating The World, where he covers artificial intelligence, tech companies, layoffs, startups, and the future of work. His reporting focuses on how AI is transforming businesses, products, and the global workforce. He writes about major developments across the AI industry, from enterprise adoption and funding trends to the real-world impact of automation and emerging technologies.


