OpenAI case study: Chatham Financial cut trade-review time from ~30 minutes to under 4 with Codex

#What happened

OpenAI published a customer case study on October 2, 2026, describing how Chatham Financial uses ChatGPT, Codex, and the OpenAI API across its advisory workflows — including a Codex-built trade validation app that cut review time from about 30 minutes to under four.

#What OpenAI published

OpenAI published a customer case study on October 2, 2026, describing how Chatham Financial — a capital markets advisory firm listed as a small and medium-sized business in the finance industry in North America — uses ChatGPT, Codex, and the OpenAI API across its advisory workflows.

#Trade validation under "Process Zero"

Chatham's Controls and Data Integrity team built a trade validation application with Codex. The app assembles supporting evidence on each transaction, checks the key terms, and marks discrepancies for review. In early measurement, the application reduced review from approximately 30 minutes to under 4 minutes. "In early measurement, the application reduced review from approximately 30 minutes to under 4 minutes. Just as important, we are validating its performance against real transactions and experienced reviewers before we expand automation." — Alex Nordlinger, Co-head of Chatham's AI Advisory practice. Chatham plans to extend the application to additional trade types.

#Employee-built apps: "Chatham Vibes"

Employees apply ChatGPT and Codex across research, analysis, drafting, and software development, and build their own applications on Chatham Vibes, an internal platform. AI features in Vibes applications run on GPT-5.6 Terra by default, and individual apps can be configured to upgrade to GPT-5.6 Sol.

#Chatham Onyx and model routing

Chatham Onyx, the firm's next-generation capital markets operating system, places assets, debt, and derivatives in a single environment where clients and advisors work from connected, governed data. Codex is used throughout the Onyx development lifecycle, helping teams plan, build, test, document, and review software. "Codex is helping our teams turn product vision into working capabilities more quickly, while our standards for accuracy, security, and accountability remain the same," said Chief Technology Officer John DeGuenther. The Onyx platform runs on GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.4, and GPT-4.1, with simple analysis and non-production testing routed to the most cost-effective models. One Onyx capability, ChatFIN, surfaces patterns in historical market data, gives users a view of their portfolios, and finds and links the legal documents covering debt, derivative, and lease terms.

#Why it matters

Co-Chief Operating Officer Mike Noonan said the limiting factor for the firm has been the time experts spend reaching the point where they can apply their expertise, and that OpenAI is helping recover that time — shifting advisors from assembling information to interpreting it.

#Source links

• https://www.unite.ai/chatham-financial-builds-capital-markets-tools-with-openai-codex/

Verified October 2, 2026.