How Nevis Uses Claude to Save Advisors 5+ Hours Per Week

Nevis is an AI platform for wealth management that automates the administrative burden crushing independent financial advisors—from CRM data entry to meeting notes and client emails. Built on Claude Opus 4.5 and Claude Haiku 4.5, the platform serves firms collectively managing more than $50 billion in client assets and saves each advisor more than five hours per week on routine tasks. The result is a clear path for advisors to double their client capacity while maintaining service quality.

Impact

5+

Hours saved per advisor per week on administrative tasks

$50B+

Client assets managed by firms using Nevis

2x

Projected increase in clients per advisor

Challenge

Financial advisors spent up to 80% of their time on administrative tasks like CRM data entry, meeting documentation, and client email drafting, severely limiting client capacity and creating costly operational overhead that could consume 2-5 staff hours per day per team member.

Solution

Nevis deployed Claude Opus 4.5 and Haiku 4.5 to power automated meeting notes, task creation, and context-aware client emails through an agentic pipeline built with Pydantic AI and the Anthropic API, with n8n extending these capabilities to the operations team without additional engineering overhead.

Tools & Technologies

What Leaders Say

The type of work our AI agents perform requires a combination of strong logical reasoning capabilities and deep finance domain expertise. Anthropic’s models excel at both, so we were not surprised to see them outperform other models on our internal, tailor-made evaluations. We have developed and are using a targeted set of synthetic evaluation datasets that closely approximate financial advisers’ day-to-day tasks and processes. We use Claude models in our production agentic pipelines and are very satisfied with the quality of work they deliver for our users.

Philipp Burda, CPO, Nevis

Each of our advisors spends 1-2 hours each day managing data input into our CRM. Then each member of our ops team spends 2-3 hours each day inputting that information into our custodial platform. Nevis is fixing that. It’s a strategic step forward for our growth.

Michael Dodds, President and Financial Advisor, Dodds Wealth

Wrapping up a meeting at 7pm used to mean I’d not be home before 8pm, as my wife will testify. Now, I can close my laptop and know that Nevis has my back: all my notes are there, my to-do list is up to date and there’s a recap email ready for me to review and send to my client.

Financial Advisor, United Capital
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

Independent financial advisors in the United States spend an estimated 80% of their time on administrative tasks—pulling data between disconnected platforms, drafting follow-up emails, updating CRM entries, and documenting meeting notes. This overhead limits how many clients any one advisor can serve and keeps talented professionals from focusing on the strategic work that actually creates value for clients.

The founding team at Nevis identified this gap from direct experience. Mark Swan, Philipp Burda, and Ivan Chalov came from Revolut, where Burda led AI initiatives and saw firsthand how language models could automate middle- and back-office operations in financial services. They built Nevis around the premise that AI could remove the administrative ceiling constraining advisor productivity—and chose Claude as the foundation because of its accuracy on complex, multi-step financial tasks.

The Nevis platform deploys Claude Opus 4.5 and Claude Haiku 4.5 across several core workflows. An AI Meeting Agent transcribes sessions, corrects speech-to-text errors, and generates structured client meeting summaries. Smart Tasks automatically builds complete task items with subtasks, descriptions, and assigned owners. Smart Emails drafts context-aware follow-up communications tailored to each advisor’s writing style and meeting history. For document retrieval, the platform uses a RAG architecture built directly on the Anthropic API via Python, with Pydantic AI handling the meeting intelligence pipeline. Integration across the advisor’s toolchain—including n8n for operations team workflows—extends Claude’s capabilities to staff who would otherwise need custom engineering work to access the same APIs.

In evaluation, Claude demonstrated materially lower hallucination rates and stricter adherence to complex multi-step instructions than competing models. Its ability to process entire meeting transcripts in a single request—without the error-prone chunking required elsewhere—was critical for a product handling sensitive client financial data. Claude Code also accelerates Nevis’s internal engineering velocity, powering code generation, refactoring, and first-pass PR reviews.

Advisors using Nevis save more than five hours per week, and Nevis projects this frees capacity to grow from 100 to 200-plus clients per advisor over time. For the wealth management firms it serves—collectively managing more than $50 billion in client assets—Nevis represents a structural shift: the ability to scale assets under management without proportionally growing operations headcount.

Similar Cases

C
Campfire
3 days
reduction in monthly close time

Campfire embedded Claude into its accounting platform to automate monthly closes, bank reconciliation, and financial reporting. Customers now close their books 3 days faster, reconcile bank statements 90% faster, and generate reports 50% faster. Claude powers Ember, Campfire's AI chat interface for natural language financial queries.

Financial ServicesCAClaude API
MF
Money Forward
80%
engineer adoption rate

Money Forward launched its MEPAR program to embed Claude Code across its engineering organization, achieving 80% engineer adoption with 70% using it daily. API endpoint implementation time fell from two days to five hours, and developer onboarding compressed from one week to one day. Early adopters reported saving approximately seven hours per week.

Financial ServicesTechnologyCCClaude Code
A
Airtree
Reduced from 2 days to minutes
market & competitor research time

Airtree, a $2 billion Australian venture capital firm, deployed Claude Cowork as shared firm-wide infrastructure to unify fragmented data across tools like Notion, Slack, Google Drive, and Affinity. The team built custom Skills to automate board meeting prep, market research, and portfolio reporting — cutting multi-hour tasks down to minutes. What began as individual productivity gains quickly scaled into a collaborative system where Skills built by one person benefit the entire firm.

Financial ServicesWWebflowTTypeform
S
Stripe
1,370
engineers deployed

Stripe collaborated with Anthropic to create a signed enterprise binary of Claude Code, deploying it to 1,370 engineers with zero configuration. One team migrated 10,000 lines of Scala to Java in 4 days instead of 10 weeks.

Financial ServicesCCClaude Code
LF
LB Finance
Hours to minutes
dashboard refresh time

LB Finance, the Sri Lanka financial services company managing over $1 billion in assets and serving more than 1 million customers, deployed Snowflake AI Data Cloud with Cortex AI to modernize its data and analytics infrastructure. The migration eliminated manual paperwork in reporting, reduced dashboard refresh times from hours to minutes, accelerated loan approvals through AI-driven processing, and nearly eliminated IT maintenance costs — enabling real-time data visibility across the organization.

Financial ServicesSSnowflakeSCSnowflake Cortex AI
K
Klarna
80%
reduction in average customer query resolution time

Klarna is a global fintech company serving over 85 million active users with payment and shopping solutions, processing 2.5 million transactions daily across more than 45 markets. Facing mounting pressure to scale customer support across global markets without proportional headcount increases, Klarna deployed an AI assistant built on LangGraph and refined with LangSmith that now handles the work equivalent of 700 full-time staff. The result is 80% faster customer query resolution and 70% automation of repetitive support tasks.

Financial ServicesLLangSmithLLangGraph
B
Block
75% saving 8-10+ hours
engineers saving time weekly

Block, the financial technology company behind Square, Cash App, and Afterpay, deployed Claude as the default model in its open-source AI agent, codename goose, running through the Databricks Data Intelligence Platform. The system gives approximately 4,000 employees across 15 job profiles direct access to internal data, automated SQL generation, and AI-assisted code writing. Engineers report saving 8 to 10-plus hours per week, with goose adoption doubling within a single month.

Financial ServicesCGcodename gooseDDatabricks
BL
Bank Leumi
-60%
log detection and analysis time

Bank Leumi, Israel’s leading bank with more than 7,000 employees and $195 billion in assets, replaced its aging SIEM with Elastic Security to gain unified visibility across a cloud-and-on-premises infrastructure generating vast volumes of semi-structured data. By deploying Elastic Security alongside Kibana dashboards and MITRE ATT&CK-aligned detection rules, the bank cut log detection and analysis time by 60%, reduced security incident resolution time by 50%, and lowered total cost of ownership by 40%.

Financial ServicesESElastic SecurityEElasticsearch