Application Refactoring · Enterprise Knowledge Search · Risk Management
Chatham needed to reduce the routine execution work around capital-markets advisory, trade validation, and internal software delivery while keeping accuracy, auditability, and human judgment central to the workflow.
Reported impact
Chatham cut a key validation workflow from 30 minutes to under four, broadened the number of client and employee applications teams can build, and created more capacity for advisors to focus on interpretation and client needs instead of routine assembly work.
Chatham uses Codex and GPT-5.6 to turn capital-markets expertise into applications, AI features, and workflow redesign rather than isolated productivity wins. Through its Process Zero consulting model, the firm starts from the desired outcome, defines the minimum inputs and evidence needed, and decides where AI-built tools can take over routine comparison and organization steps while professionals keep judgment-intensive work. One early result is a trade-validation application built with Codex that gathers supporting evidence, compares key transaction terms, flags discrepancies, and is being measured against expert reviewers before wider automation. Chatham also built an internal app platform called Chatham Vibes, while Chatham Onyx uses Codex and multiple GPT-5.6 and GPT-4.1 variants to build, test, and power connected client-facing experiences such as ChatFIN. Together, these systems give advisors faster access to evidence and insight while preserving traceability and oversight.
Trade data, transaction evidence, portfolio information, and internal workflow requirements are fed into Codex-built applications and GPT-powered features. Outputs are compared against expert reviewers or surfaced inside Onyx, where advisors interpret results and approve what reaches clients.
"ChatFIN ... helps users understand their portfolios, and locates and links to legal documents"
"Chatham uses Codex across the Onyx development lifecycle"
"Employees have also become builders through Chatham Vibes"
"cutting trade validation from 30 minutes to under 4"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
AWS Sample Sep 7, 2023 Bio-Rad Laboratories Additionally, the team needed Internet of Things (IoT) capabilities to facilitate the automatic and programmatic upload of data—including high-volume instrument data and low-volume system telemetry data—to a centralized… A single ML model might analyze up to 50 GB of data, making it impractical to run on a data scientist’s laptop. AWS Glue · AWS IoT Greengrass · Amazon S3 
MongoDB Sample Aug 31, 2026 LexisNexis Risk Solutions LexisNexis needed an AI retrieval architecture that could preserve relationships and time context across fast-changing financial and commodities data, because standard RAG could not produce reliable answers for… LexisNexis publishes 2,000 articles daily and tracks over 2,200 global commodities. MongoDB Atlas 
OpenAI Sample Jul 7, 2026 Australian Payments Plus AP+ needed a secure way for employees to move faster through complex payment, identity, and reconciliation work while preserving the governance, accuracy, and accountability demanded by a regulated payments environment. 1 day to build working simulations with Codex ChatGPT Enterprise · Codex 