← Back to feed

Anthropic shipped ten production-ready agent templates for financial services on May 5, targeting the workflows that eat the most analyst hours: pitchbook production, KYC screening, and month-end close. Each template ships as a plugin inside Claude Cowork and Claude Code, and as a Claude Managed Agents cookbook for fully autonomous overnight runs.

The timing aligns with Claude Opus 4.7’s lead position on Vals AI’s Finance Agent benchmark — 64.37%, the highest score on the industry’s primary financial task evaluation.

The 10 Templates

Research and client coverage

• Pitch builder — creates target lists, runs comparables, drafts pitchbooks for client meetings
• Meeting preparer — assembles client and counterparty briefs ahead of calls
• Earnings reviewer — reads transcripts and filings, updates models, flags thesis-relevant changes
• Model builder — creates and maintains financial models from filings, data feeds, and analyst inputs
• Market researcher — tracks sector and issuer developments, synthesizes news and broker research

Finance and operations

• Valuation reviewer — checks valuations against comparables, methodology, and review standards
• General ledger reconciler — reconciles GL accounts and runs NAV calculations against books of record
• Month-end closer — runs the close checklist, prepares journal entries, produces close reports
• Statement auditor — reviews financial statements for consistency, completeness, and audit-readiness
• KYC screener — assembles entity files, reviews source documents, packages escalations for compliance

Architecture

Each template packages three components: skills (domain instructions and knowledge), connectors (governed real-time access to provider data), and subagents (additional Claude models called for specific subtasks such as comparables selection or methodology checks). Firms adapt any template to their own modeling conventions, risk policies, and approval flows.

As a Claude Managed Agent, the same template runs autonomously on the Claude Platform — long-running sessions that span multi-hour deal closes, per-tool permissions, managed credential vaults, and a full audit log in the Claude Console. Every tool call and decision is inspectable by compliance and engineering teams.

Microsoft 365 Integration

Claude now works across Excel, PowerPoint, Word, and Outlook (Outlook coming soon) through Claude add-ins for Microsoft 365. Context carries automatically between applications — work started in a financial model can end in a pitchbook deck without re-explaining anything. This closes the application-switching loop that has historically blocked AI adoption in analyst workflows.

Benchmark Position

On Vals AI’s Finance Agent benchmark — the sector’s primary standardised evaluation — Claude Opus 4.7 leads at 64.37%. The benchmark tests agents against real financial tasks including document parsing, cross-entity reconciliation, and compliance workflows under time pressure.

The finance templates are the second vertical-specific agent suite Anthropic has shipped in four weeks, following its cybersecurity agents released in March. The pattern: Anthropic is building sector by sector, using Opus 4.7 as the capability engine and Managed Agents as the deployment substrate.

All plugins and cookbooks are available at the financial services marketplace on GitHub.