GitHub Repos intermediate 3 min read May 7, 2026
Public Preview Sign in free for the full digest →

Anthropic's financial-service AI stack

“FIS cut AML investigation time from days to minutes using these 10 markdown files — and the repo is Apache 2.0.”

Anthropic's financial-service AI stack
1 Views
0 Likes
0 Bookmarks
Source · github.com

“"I'm not paying $125k/year/seat to get locked into a black box ecosystem that might change." — OldfieldFund, HN thread https://news.ycombinator.com/item?id=44576312 (accessed 2026-05-07)”

You know that feeling when you spend four hours building a comparable company analysis in Excel, pulling multiples from Bloomberg, formatting slides, and then the deal dies anyway? Financial analysts at banks, PE firms, and hedge funds repeat that cycle daily — comps, DCF models, earnings recaps, GL reconciliations, KYC reviews — each a multi-hour template task that requires domain knowledge but follows a predictable structure. Existing tools automate narrow slices: a Bloomberg terminal for data, PitchBook for deal history. None of them draft the actual work product end-to-end. This repo treats each workflow as a composable Claude agent: give it the right data connectors and domain prompts, and it drafts the output for a human to approve.

ai-agentsfinancial-servicesllmclaudemcppythonopen-source

Each agent is a markdown file telling Claude how to behave for a specific finance workflow — think of it as a detailed job description in plain text. When you install an agent via Claude Code with one command, it also wires up MCP connectors to financial data providers like FactSet or PitchBook, so Claude can pull live market data when you run /comps or /dcf. A Python script called sync-agent-skills.py keeps skills synchronized across agents automatically, and check.py validates all manifest links before you deploy. You run the same agent two ways: as a plugin in the Claude Cowork web UI for interactive use, or as a headless Managed Agent via /v1/agents for automated pipelines. Every output is staged for human review — the agent drafts, a qualified professional approves.

01
10 named agents covering the full financial workflow — pitch builder through KYC screener — each pre-wired to MCP connectors for FactSet, PitchBook, Moody's, LSEG, and 7 other data providers, so you skip building data integrations from scr...
02
Single-source system prompts: one markdown file per agent deploys identically to both the Claude Cowork plugin and the headless Managed Agents API, preventing the prompt drift that silently breaks enterprise AI deployments when interactive...
03
Slash commands for financial tasks — /comps, /dcf, /lbo, /earnings, /ic-memo, /dd-checklist — callable from Claude Code or the web UI, each triggering a structured multi-step workflow with live data.
04
Swappable MCP connectors via .mcp.json edits: point agents at your firm's existing data sources instead of the defaults, no changes to agent logic required.
05
Validation tooling included: check.py lints manifests and verifies cross-file references before deployment; sync-agent-skills.py propagates skill edits automatically, so a change to one skill file does not silently break the five agents th...
06
Microsoft 365 integration: Claude add-ins for Excel, PowerPoint, and Word are generally available as of May 2026; Outlook is in beta — agents can read from and write to the Office documents your team already uses.
07
Apache 2.0 license: fork the repo, edit the markdown prompts for your firm's terminology and process standards, swap data connectors, and deploy — no royalties or vendor permission required.
Who it’s for

If you are an engineer at a bank, asset manager, insurance firm, or fintech building internal AI workflows, this is months of prompt engineering and MCP connector wiring already done for you — fork it, adapt the markdown files to your firm's terminology, and deploy. Finance professionals who want to use it themselves need Claude Code and Anthropic API access, plus existing data provider subscriptions for the MCP connectors. Not useful if you need agents that execute autonomously — by design, every output requires explicit human sign-off, and the managed-agent architecture caps subagent depth ...

Worth exploring

Yes, if your firm already pays for Anthropic API access and holds subscriptions to FactSet, PitchBook, or similar data providers — the 10 agent templates and 11 pre-built MCP connector definitions alone save significant integration time. The single-source-of-truth architecture is also worth studying for any enterprise AI deployment where consistency between interactive and automated environments matters. Be cautious: Claude Opus 4.7 scores 64.37% on the Vals AI Finance benchmark (roughly a 36% failure rate on benchmark tasks), and HN practitioners reported hallucination in financial document citation workflows — the repo's own disclaimer mandates human sign-off for every output.

Developer playbook
Tech stack, code snippet, sentiment, alternatives.
PM playbook
Adoption angles, user fit, positioning.
CEO playbook
Traction signals, ROI, build vs buy.
Deep-dive insight
Full long-form analysis, no fluff.
Easy mode
Core idea, fast — when you need the gist.
Pro mode
Technical nuance, edge cases, tradeoffs.
Read the full digest
Go beyond the preview

Deep-dive insight, Easy and Pro modes, plus action playbooks — the full breakdown is one tap away.

Underrated tools. Unfiltered takes.

Read the full digest in the Snaplyze app for deep-dive insight, Easy and Pro modes, and the playbooks you can actually use.

Install Snaplyze →