How Claude Code Is Transforming Finance—Without Turning You Into a Coder
By: Brooker Belcourt Source: Original URL Type: article
Summary
Fill after reading with your own take. 2-3 sentences: what is this about, what’s the core argument or insight? (The frontmatter summary field has the auto-generated triage summary from ingestion.)
Key Ideas Extracted
Fill during processing. Each idea links to a knowledge entry.
Notes
Your annotations, reactions, questions, disagreements. Written during or after reading.
Raw Content
How Claude Code Is Transforming Finance—Without Turning You Into a Coder With ChatGPT or Claude, you’re only using a fraction of what LLMs can deliver
| By Brooker Belcourt | February 12, 2026 |
TL;DR: As the head of financial services consulting at Every, Brooker Belcourt has helped take top hedge funds, asset managers, and research teams from AI-curious to AI-native.
If any industry was made for AI, it’s finance. The workflows are structured, the tasks easy to map out, the data largely available, and the returns from efficiency huge—exactly the environment where AI performs best.
But working with hedge funds, asset managers, and research teams as part of Every’s consulting team, I’ve learned that investment firms—despite having the talent and resources to adopt AI—often get stuck.
It’s a funny little conundrum that firms in one of the industries best fit for AI struggle to figure out how to start using it effectively. Here’s a primer on how to get started, based on what I have seen from six months of supporting firms.
Start with Claude Code
Financial services teams scour through earnings calls, portfolio reviews, and limited partner updates, all the time. Usually, the first step I take with finance teams is to recommend Claude Code. Unlike alternative LLMs such as Opus 4.6 and GPT-5.3 Codex, Claude Code is a better tool for processing large amounts of data.
It’s also the best tool for large amounts of data and complex tasks. Data is useless unless you can act on it. Claude Code can identify insights and then take action in ways chat-style AI tools cannot. For example, in an earnings preview, which lays out what analysts and investors should expect to see from a company ahead of results, Claude Code can write research, put together a summary table, and take the results to a system prompt. Everything is now ready for analysis at the click of a button.
Define what you’d like to get done
The second step for teams is to clearly define the task they need to complete. These are the most common tasks I’ve helped finance teams deploy:
1. Preparing for meetings
Meetings are important to close deals and make decisions quickly, but preparing for them is a major time sink. The firms we work with that have gotten the most out of Claude Code start here. An analyst defines what they want to achieve from each meeting, specifies the type of company being met, and the relevant context they need to cover. Claude then generates structured prep with the relevant data and context they need to know beforehand.
2. Preparing for and reviewing earnings calls
In the U.S., the world’s largest equity market, public companies are required to report financial results every quarter. But these earnings calls generate copious amounts of material: prepared remarks, a Q&A transcript that can be 30-plus pages, slides, and more. Traditionally, an analyst might read a transcript, pull the key figures, check them against existing models, and then write a summary to share with their team. This process can take 90 minutes to two hours per company.
The hedge fund we work with built an earnings preview and review system using Claude Code that changed this. Their analysts now spend 15 minutes reviewing the output, rather than 90 minutes generating it.
3. Screening companies based on your investment philosophy
Some investors have to screen hundreds of investment targets a month, a process that involves sifting through huge amounts of data. This can take weeks of work. With Claude Code, you can encode your investment philosophy once and run it at scale. It’s easy to get started here. For hedge fund clients, we write the investment philosophy as a Skill in Claude. It can then be applied automatically to any company.
4. Investment analysis
When the price of a company, a cryptocurrency or a commodity moves sharply—up or down—teams scramble to understand why. A large crypto fund we work with uses Claude Code to run this kind of “what happened” analysis automatically. When it detects a sharp move, it gathers data, maps out the key drivers, and delivers a concise summary to the investment team.
Working with Claude
Another blocker for investors adopting LLMs that I’ve consistently heard is that the setup, especially for Claude Code, requires programming knowledge. Most analysts and portfolio managers don’t have this background, and they shouldn’t need to acquire it.
We help financial professionals get over the cold start problem by building everything they manage, including their investment philosophy, as Skills and plugins. We have built plugins—bundled packages of skills and commands that can be shared and installed—that get teams running in hours, not weeks.
Beat the competition
The workflows that feel cutting-edge today will be table stakes in two or three years, and the gap between the firms using these tools effectively and those that aren’t will only grow.