Chatham Financial uses Codex and GPT-5.6 to cut trade validation to under 4 minutes

Process Zero and the trade validation app

Chatham describes Process Zero as its reengineering consulting service. For each workflow, the firm identifies the minimum inputs and evidence required, determines where human judgment is essential, and decides how AI and AI-built tools should support the work.

Trade validation is an early example. Chatham's Controls and Data Integrity team checks that each system record reflects what the client authorized and what was executed. Using Codex, the firm built an application that gathers supporting transaction evidence, compares key terms, and flags discrepancies for review.

Alex Nordlinger, Co-head of Chatham's AI Advisory practice, said the application cut review time from approximately 30 minutes to under 4 minutes in early measurement. He added that the firm is validating performance against real transactions and experienced reviewers before it expands automation. Chatham is comparing the app's results with those of experienced reviewers, and plans to extend the application to additional trade types and automate more of the workflow while maintaining appropriate controls and professional oversight.

Employee-built applications on Chatham Vibes

Chatham's employees use ChatGPT and Codex in research, analysis, drafting, software development, and other daily activities. Staff can also build their own tools through Chatham Vibes, an internal platform for creating applications tailored to their work.

Employees build with a range of models. The AI features inside Vibes applications run on GPT-5.6 Terra by default, with GPT-5.6 Sol as an optional upgrade based on per-app configuration.

These applications increasingly support client-facing workflows:

• One helps teams review maturing-cap trades and prepare pricing workbooks and client communications.
• Others support producing fixed-income rate sheets, preparing hedging dashboards, and reviewing trade confirmations.

According to the company, Chatham professionals supply the market context, client understanding and judgment to evaluate the work, refine it, and decide what reaches the client.

Chatham Onyx and its model mix

Chatham Onyx is described as the firm's next-generation capital markets operating system. It brings assets, debt, and derivatives into one environment where clients and advisors can work from connected, governed data and use AI without losing traceability to the underlying source.

Chatham uses Codex across the Onyx development lifecycle, to help plan, build, test, document, and review software. John DeGuenther, Chief Technology Officer, said Codex is helping teams turn product vision into working capabilities more quickly, while standards for accuracy, security, and accountability remain the same.

The platform uses GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.4, and GPT-4.1. Simple analysis and non-production testing are routed to the most cost-effective models, while GPT-5.6 handles complex tasks that need to maximize accuracy and value.

One Onyx feature is ChatFIN, which summarizes patterns in historical market data, helps users understand their portfolios, and locates and links to legal documents for debt, derivative, and lease terms.

What it means for Chatham's experts

Chatham says it uses OpenAI to perform structured comparisons, organize evidence, identify exceptions, and help teams explore information more efficiently. The intended result is that advisors spend less time assembling information and more time interpreting it, managing difficult cases, and advising clients.

Mike Noonan, Co-Chief Operating Officer, put it this way: "Our constraint has never been expertise. It is the hours our experts spend getting to the point where they can apply it."

Next, Chatham plans to expand trade validation across additional products, continue refining employee-built applications, and use Codex to help develop new capabilities for Onyx. The 30-minute-to-under-4 figure comes from early measurement, and the firm stresses that it is still checking the tool against real transactions and experienced reviewers.