Morgan Stanley · Wealth Management Knowledge Assistant + Evals System

A Evidence level

Morgan Stanley: Wealth Management Knowledge Assistant + Evals System

Publisher: OpenAI · Vendors ' official customer information · Direct sources at the case level

Claim origin: Public disclosure by manufacturer or customer · Independent verification: No · Accessed: 2026-09-19

Evidence level measures whether a source can be located and reviewed; it does not mean vendor-reported claims were independently audited.

Deep case | Key delivery chain is substantially documented 10 / 12

Business context1 / 2

Transformation workflow2 / 2

Technical workflow2 / 2

Human roles & governance1 / 2

Measured outcomes2 / 2

Source traceability2 / 2

Remaining gaps: Business context, Human roles & governance

The focus of this case is on transforming the “Foundation Management Knowledge Assistant + Evals System” from a one-time analysis or single-point tool to a production stream that can be embedded into real business, verifiable and sustainable.

Business problem

Wealth advisers need to quickly obtain credible answers from large and highly compliant research and process files.

Solution

Morgan Stanley, in conjunction with OpenAI, optimized search and Evals: expert ratings and regression tests for digests, translations, retrievals, extended to Advisor Assistant and conference Debrief.

Technical architecture & production workflow

Step 01

Enterprise knowledge/documents/data/business systems

→

Step 02

ChatGPT Enterprise/Work access context within permission

→

Step 03

Staff member or custom GPT/Agent completes analysis, generation or automation

→

Step 04

Connector/rules/business governance control data and action boundaries

→

Step 05

Staff review of key outputs and implementation

→

Step 06

HF process sedimentation as template, GPS or Agent and continuous assessment

Key technology & infrastructure components

GPT-4RAG/ResearchEvalsWhisperExpert scoringReturn Test

Human roles & accountability

Consultants assess answers with in-house experts and assume client advice responsibilities.

FDE delivery actions

Select high-frequency and measurable production streams with the wealth management team, rather than simply deploying chat portals
Identifying the business context, system privileges, tools and security boundaries required for the model
Connect models to real software/data/business processes and establish tests, Evals or validation of certainty
Design the Human-in-the-lop and failed upgrade paths to ensure clear boundaries of responsibility
Continuous succession of Prompt, context, tools and processes based on production usage, errors and user feedback

Reusable delivery patterns

Enterprise AI effects depend on context, tools, validation and adoption rates, and not only on model capabilities
Quantifiable workflows first followed by product/platformization of successful models
As far as you can, Agent has access to tests, CI/CDs and security checks to form a closed loop.
High-risk industries must leave professional responsibilities and establish sustainable Evals

Business outcomes & delivery results

Officially, 98 per cent plus the use of a team of consultants; answerable materials expanded from approximately 7,000 questions to 100,000 documents; document accessibility increased from 20 per cent to 80 per cent.

Evidence boundaries & verification notes

The OpenAI official case details changes in Evals, search overlaps, adoption rates and document coverage.
The source can be directly located in the case; the value remains disclosed by the source and does not represent an independent audit.

Primary source: Morgan Stanley: Wealth Management Knowledge Assistant + Evals System ↗