Anthropic’s finance-agent repository is a set of adaptable workflow templates, skills and data connectors—not a fully autonomous financial decision system. Its ten agent templates draft work such as research notes, models and reconciliations for qualified professional review. Teams can use them as Claude Cowork or Claude Code plugins, or deploy cookbooks through the Claude Managed Agents API.
What the repository includes
Anthropic describes the project as reference agents, skills and data connectors for investment banking, equity research, private equity and wealth management. Each template is intended as a starting point for adaptation to a firm’s practices, not a finished system that can be assumed to fit every institution. Anthropic’s repository also groups reusable vertical plugins for financial analysis, investment banking, equity research, private equity, fund administration and operations.
As an Amazon Associate I earn from qualifying purchases.
The ten workflow agents
| Agent | Typical draft work described by Anthropic |
|---|---|
| Pitch Agent | Assemble comparables and pitchbook material. |
| Meeting Prep Agent | Prepare client briefs ahead of meetings. |
| Market Researcher | Gather and synthesize market research. |
| Earnings Reviewer | Review earnings information and filings. |
| Model Builder | Update or build financial models using sources such as transcripts and filings. |
| Valuation Reviewer | Check valuations against a methodology. |
| GL Reconciler | Trace general-ledger reconciliation breaks and support NAV calculations. |
| Month-End Closer | Draft month-end close work and reports. |
| Statement Auditor | Review statements for issues. |
| KYC Screener | Flag onboarding gaps for compliance review. |
The repository’s core financial-analysis plugin includes modeling skills and connectors. Anthropic describes connector servers as a bridge to terminals, research platforms and document stores; the exact data and actions available depend on the connector and the firm’s setup.
How teams can deploy the agents
Anthropic documents two main routes from the same source: use plugins alongside Claude Cowork or Claude Code, or deploy Managed Agents cookbooks through an API behind a firm’s workflow engine. The appropriate route depends on where the work should run and how the institution governs credentials, tools, audit and approvals. The sources do not provide a complete independent comparison of cost, latency or security between the approaches.
#1 Best Overall
- 【High-Performance APU】The MS-S1 MAX features an AMD Ryzen AI Max+ 395 APU, integrating a Zen 5 architecture CPU (up to 5.1GHz, 16C/32T, 64M L3 Cache), an RDNA 3.5 GPU, and an NPU (50 TOPS). The total system output is 126 TOPS. It provides powerful parallel computing capabilities for demanding AI workflows. It is ideal for running local LLMs, multimodal models, and computationally intensive tasks
- 【128GB UMA Memory】Equipped with up to 128GB of LPDDR5x-8000MT/s unified memory, it enables the CPU and GPU to access a shared, high-bandwidth memory pool with extremely low latency. Ideal for large-scale AI inference, 3D workloads, and complex timelines in video editing. It eliminates traditional VRAM bottlenecks, ensuring smoother data transfer during high-intensity computations. The UMA design maximizes performance stability under high loads
- 【Flexible Expansion】The MS-S1 MAX features USB4 V2 (up to 80Gbps), dual 10GbE LAN, HDMI 2.1 (up to 8K60), a full-length PCIe x16 expansion slot, and dual M.2 slots supporting up to 16TB RAID 0/1. Wi-Fi 7 provides stronger signal coverage and a more stable wireless experience. The slide-out design facilitates upgrades and maintenance. It easily adapts to personal, studio, or rack-mount enterprise environments
- 【High-Efficiency Cooling System】Utilizing an aerospace-grade aluminum alloy chassis, copper base plate, six heat pipes, dual turbine fans, and advanced PCM thermal conductive material, it maintains stable cooling performance even under continuous load. This system supports 130W continuous power and 160W peak power operation, with a built-in 320W power supply. It boasts multiple global certifications including CCC, FCC, UL, CE, and UKCA, ensuring stable and reliable operation in various environments
- 【Cluster Design】Two MS-S1 MAX units can be configured as a dual-unit cluster to run a large 235B Q4 model locally, achieving an output speed of 10.87 tok/s. Supporting 2U rack deployment, multiple MS-S1 MAX units can be cascaded into a distributed cluster to create a high-efficiency AI computing center. A cluster of four MS-S1 MAX units successfully ran a DeepSeek-R1 671B Q4 large model. A reserved cluster power-on interface allows for unified start-up and shutdown
| Route | How it runs | Useful considerations |
|---|---|---|
| Cowork or Claude Code plugin | Installed as a plugin in the corresponding Claude environment, following the repository’s README. | Consider the user workflow, local tool permissions, available connectors and the firm’s review process. |
| Managed Agents cookbook | Deployed through the Claude Managed Agents API behind a firm workflow engine; the repository documents a deployment script and API key. | Consider how the workflow engine handles credentials, permissions, audit logs and sign-off, and whether the template matches internal procedures. |
A template can package task skills—domain instructions and knowledge—connectors for governed access to task data, and subagents for bounded tasks such as comparables selection or methodology checks. Anthropic says firms can adapt templates to their modeling conventions, risk policies and approval flows. Callable-agent delegation is described as a research-preview capability, so it should not be treated as a generally established production feature.
The repository also includes partner-built plugins, Managed Agents cookbooks, Microsoft 365 add-in administration tooling and scripts. Deployment documentation and capabilities can change as the repository’s main branch evolves.
Rank #2
- Built for Local AI and Advanced Workflows – The BOSGAME M5 AI Mini PC is powered by AMD Ryzen AI Max+ 395 with 16 cores, 32 threads, up to 5.1GHz, 50 TOPS NPU performance and up to 126 TOPS total AI performance. It is designed for local AI inference, private AI assistants, coding, data analysis, virtualization, content creation and demanding multitasking while keeping sensitive data on the device.
- 128GB Unified Memory for Large Models and Creative Projects – M5 includes 128GB LPDDR5X-8000 unified memory, giving the CPU and Radeon 8060S graphics access to a large shared memory pool. This helps support memory-intensive AI workloads, large project files, multiple virtual machines, 3D work, video editing and complex professional applications without the capacity limits of typical 32GB or 64GB mini computers.
- Radeon 8060S Graphics for Creation, Rendering and Gaming – Integrated Radeon 8060S graphics with 40 RDNA 3.5 compute units delivers high-end visual performance without a separate graphics card. Use the M5 creator workstation for 4K video editing, 3D rendering, CAD, AI image workflows, high-resolution media and modern gaming, while maintaining a compact desktop footprint.
- 2TB PCIe 4.0 SSD and Flexible Expansion – A pre-installed 2TB NVMe PCIe 4.0 SSD provides fast access to models, datasets, media libraries and project files. A second M.2 2280 PCIe 4.0 slot allows additional storage expansion, while the SD 4.0 card reader supports efficient photo and video workflows for creators and production teams.
- Professional Connectivity and Four-Display Support – Dual USB4 ports, HDMI 2.1 and DisplayPort 1.4 support up to four displays and resolutions up to 8K@60Hz. WiFi 7, Bluetooth 5.4 and 2.5GbE deliver fast networking for cloud collaboration, NAS access and business deployment. Windows 11 Pro, performance-mode switching, Wake-on-LAN and auto power-on support flexible workstation use.
What the agents do—and what they do not do
These workflows can prepare analyst work product: for example, assemble a brief, draft a model update, identify a reconciliation break or flag missing onboarding information. Anthropic’s repository explicitly says the agents do not make investment recommendations, execute transactions, bind risk, post to a ledger or approve onboarding. Outputs are staged for human sign-off.
Anthropic’s repository states: “Nothing in this repository constitutes investment, legal, tax, or accounting advice. These agents draft analyst work product — models, memos, research notes, reconciliations — for review by a qualified professional. They do not make investment recommendations, execute transactions, bind risk, post to a ledger, or approve onboarding; every output is staged for human sign-off. You are responsible for verifying outputs and for compliance with the laws and regulations that apply to your firm.”
Rank #3
- FAST RUNS IN THE FAMILY — The 14-inch MacBook Pro with the M5 Pro or M5 Max chip brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. With all-day battery life, double the starting storage,* and a breathtaking Liquid Retina XDR display, it’s pro in every way.*
- BUCKLE UP — Along with a next-generation CPU, faster unified memory, and up to 2x faster SSD storage,* M5 Pro and M5 Max feature a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance and on-device training capabilities. So you can blaze through demanding workloads at mind-bending speeds.
- BUILT FOR AI — Apple silicon, and every major component that powers it, is designed to run demanding on-device AI workloads like LLM inference and training. And Apple Intelligence helps you write, express yourself, and get things done effortlessly with groundbreaking privacy protections at every step.*
- ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.*
- MACOS RUNS APPS FAST — All your go-to apps run lightning fast in macOS, including built-in apps like FaceTime and Messages. Plus, built-in virus protection and free software updates help keep your Mac running smoothly and securely.
Anthropic also describes governed access and audit logs in its Managed Agent cookbooks. Those product descriptions do not, on their own, establish that a particular institution’s deployment meets its regulatory obligations. Firms still need to set permissions, validate outputs, define approval paths and assess their own compliance requirements.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Connectors, data access and entitlements
Anthropic’s May 5, 2026 announcement lists integrations or access paths spanning FactSet, S&P Capital IQ, MSCI, PitchBook, Morningstar, Chronograph, LSEG, Daloopa and firms’ internal data warehouses, research repositories and CRMs. It also names newer connectors from Dun & Bradstreet, Fiscal AI, Financial Modeling Prep, Guidepoint, IBISWorld, SS&C Intralinks, Third Bridge and Verisk, plus a Moody’s MCP app. The finance plugins page describes FactSet and MSCI connectors and partner-built LSEG and S&P Global plugins; it says LSEG capabilities require active LSEG data entitlements.
Rank #4
- 💥【AI 9 HX 470 GAMING PC】The BOSGAME VTA-439 mini pc is powered by AMD Ryzen AI 9 HX 470 (12C/24T, 5.2GHz) with XDNA 2 NPU: 55 TOPS dedicated AI, 86 TOPS total platform performance. Run local LLMs, AI image generation, 8K video, and 3D rendering with zero cloud latency and full privacy. Copilot+ PC certified – the ultimate AI workstation for developers and creators.
- 💥【32GB to 256GB RAM + 1TB to 8TB SSD】The BOSGAME ai mini gaming pc comes with 32GB DDR5 5600MHz RAM (dual slots max 256GB) and 1TB PCIe 4.0 SSD (triple M.2 NVMe slots max 8TB total). Each RAM max 64GB; each SSD slot max 4TB. -Upgrade anytime as your needs grow, multitask working can be performed smoothly.
- 💥【OCULINK eGPU PORT】The Oculink port provides a dedicated PCIe 4.0 x4 connection with up to 64 Gbps bandwidth—significantly higher than Thunderbolt 4's 32 Gbps PCIe data bandwidth. This direct connection delivers better frame rates and lower latency for external GPU setups, giving gamers and content creators the performance edge they need.
- 💥【DUAL 2.5GbE + Wi-Fi 7 + BT 5.4】Dual 2.5GbE LAN ports enable firewall, link aggregation, soft routing, and NAS applications. Built-in Wi-Fi 7 and Bluetooth 5.4 offer stable, high-speed wireless connections for projectors, printers, monitors, speakers, and more—ideal for a versatile, clutter-free workspace.
- 💥【RADEON 890M GPU & QUAD-SCREEN DISPLAY】Integrated with AMD Radeon 890M graphics running at 3100 MHz, the ai pc supports quad display output via HDMI 2.1 (4K@144Hz), DP 1.4 (4K@144Hz), USB4 (8K@60Hz), and Full-Function Type-C. Perfect for AAA gaming, video editing, 3D modeling, and multitasking—deliver stunning visuals across four screens with fluid performance.
Anthropic describes connectors as enabling governed, real-time access, but a listing is not proof that a given firm has access or permission to use a data source. Confirm current provider availability, subscription entitlements, deployment configuration and data permissions with the relevant provider and Anthropic before building a workflow around a connector.
Free tools Windows power users keep installed
One-click scans. No signup required.
What published performance figures show
Anthropic has published several vendor-reported figures, but they describe specific tasks or early customer results—not guaranteed performance for a different model, workflow or institution.
- In its May 5, 2026 announcement, Anthropic reported a 64.37% score for Claude Opus 4.7 on Vals AI’s Finance Agent benchmark. That is a benchmark result, not a forecast of accuracy in a firm’s own process. Read the announcement.
- In its July 15, 2025 product announcement, Anthropic said Claude Opus 4 passed five of seven levels and achieved 83% accuracy on complex Excel tasks when FundamentalLabs used it to build an Excel agent for the Financial Modeling World Cup competition. The result is tied to that agent and task context, not all spreadsheet work. Read the announcement.
- The same 2025 announcement quoted AIG CEO Peter Zaffino reporting an early-rollout outcome of underwriting business reviews being more than five times faster, with accuracy rising from 75% to over 90%. This is a company-reported result, not an independently verified general benchmark.
For a practical evaluation, test the adapted workflow on representative firm data and review the output against the institution’s own standards before relying on it in live work.
Quick Recap
How to assess whether a template fits
- Workflow location: Decide whether the task belongs alongside an individual user’s Cowork or Claude Code workflow or inside an API-driven firm process.
- Data and permissions: Confirm which connectors are available, what provider entitlements apply and how credentials and tool permissions are governed.
- Methodology fit: Check whether the template follows the firm’s modeling conventions, risk policies and approval flows.
- Review and audit: Specify who verifies drafts, records approvals and is accountable for the final work product.
- Boundaries: Keep consequential decisions and actions—such as investment recommendations, transaction execution, ledger posting and onboarding approval—under the required professional and institutional controls.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
