Bloomberg Brings Domain-Grounded AI Coding Into Financial Workflows

Bloomberg introduced BQuant Assistant on October 28, 2026, bringing a conversational AI coding assistant into the company’s BQuant Desktop and BQuant Enterprise products. The assistant is designed for financial professionals who use Bloomberg Terminal services and want to work with financial data through natural-language prompts.

Users can ask BQuant Assistant to write code, build dynamic applications, and speed up financial data analysis workflows. The assistant works inside the BQuant development environment, placing conversational AI in the Python environment where users build investment strategies, dashboards, and quantitative financial analyses.

That setup connects a plain-language request with the tools used to test and develop financial ideas. Bloomberg says the assistant can turn questions into working code, retrieved data, and visualizations, giving users a way to move from an initial idea toward a repeatable analysis inside BQuant.

AI Built Around Bloomberg’s Financial Data

Bloomberg describes BQuant Assistant as domain-grounded, meaning its responses draw on the BQuant environment and resources tied to Bloomberg’s financial data workflows. It can answer questions about BQuant, generate Python code, assist with queries through Bloomberg Query Language (BQL), and help users debug and iterate on their work.

The assistant can also build code for data visualizations and search the BQuant Help Center. When answering questions, it can draw from relevant example notebooks, libraries, and how-to guides. Bloomberg says this grounding lets BQuant Assistant provide context-aware responses about a user’s projects, workflows, and code.

That focus separates the assistant’s role from a general-purpose coding assistant. Its support is aimed at financial data analysis within BQuant, including questions about Bloomberg libraries, BQuant workflows, and client-facing product documentation. Users can also discuss financial concepts while generating code for models or techniques suited to a particular workflow.

Bloomberg’s Chief Technology Officer Shawn Edwards said financial professionals are dealing with datasets that are both larger and more complex. Turning an investment idea into a repeatable analysis can still require significant time and specialized coding knowledge, he said.

“BQuant Assistant brings AI-driven coding that is informed by Bloomberg’s understanding of financial data and quantitative workflows directly into the workflows our clients already use to build investment strategies,” Edwards said.

From Natural-Language Questions to Investment Code

Edwards said the assistant is intended to help every BQuant user, from a portfolio manager drafting an initial query to a quantitative engineer building a multi-asset signal. In both cases, the goal is to help users move from a plain-language question to code, data, and a visual result.

That process can include generating BQL and PyBQL queries to retrieve and analyze Bloomberg financial data. Bloomberg says the data spans equities, funds, fixed income, foreign exchange, commodities, indices, derivatives, and other asset classes, with more than 22,000 fields available.

Those fields cover reference data, pricing, returns, derived analytics, fundamentals, valuations, sustainable finance data, risk metrics, estimates, and economic data. Users can also create code for screens and universes across equities, fixed income, foreign exchange, commodities, indices, exchange-traded funds, and other asset classes.

The assistant’s role does not stop at producing a first draft. Bloomberg says users can use it to debug and iterate on their work, then test and refine ideas while building investment strategies in BQuant. That gives the conversational interface a place inside the development process rather than treating it as a separate question-and-answer tool.

For portfolio managers, the starting point may be a request written in everyday language. For quantitative engineers, it may involve a multi-asset signal, a query across Bloomberg datasets, or code for a dashboard. In each case, BQuant Assistant is built to connect the request with Python, BQL, PyBQL, Bloomberg libraries, and the documentation available through the BQuant Help Center.

Bloomberg’s announcement places the assistant inside BQuant Desktop and BQuant Enterprise, where users already build applications and quantitative analyses. Financial professionals who are Bloomberg Terminal subscribers can use natural-language prompts to write code, build dynamic applications, and work through financial data analysis tasks within that environment.

The result is a Bloomberg-focused conversational layer for coding and analysis. It brings together natural-language questions, financial datasets, query generation, visualizations, debugging, and workflow documentation in one BQuant development environment.

Stay connected via Google News

Follow us for the latest AI News