Bloomberg Adds Domain-Grounded AI Coding Assistant to BQuant

Bloomberg on October 28, 2026 introduced BQuant Assistant, a conversational AI coding assistant the company describes as domain-grounded, built into its BQuant Desktop and BQuant Enterprise products. According to the announcement, it lets financial professionals who are Bloomberg Terminal subscribers use natural-language prompts to write code, build dynamic applications, and accelerate financial data analysis workflows.

Bloomberg’s Chief Technology Officer Shawn Edwards said financial professionals are contending with increasingly large and complex datasets, and that turning an investment idea into a repeatable analysis can still demand significant time and specialized coding knowledge. “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,” he said.

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 — turn a plain-language question into working code, retrieved data, and a visualization, so clients can more easily test and refine ideas and build investment strategies in BQuant.

What BQuant Assistant Does

The assistant is integrated within the BQuant development environment, placing conversational AI inside the Python environment where users build investment strategies, dashboards, and quantitative financial analyses. Bloomberg says it can answer customers’ questions about BQuant, generate Python code, assist with querying the company’s datasets through Bloomberg Query Language (BQL), help users debug and iterate on their work, and build code for data visualizations.

BQuant Assistant can also search the BQuant Help Center and draw from relevant example notebooks, libraries, and how-to guides when answering questions. Bloomberg says this grounding in the BQuant environment allows the assistant to generate context-aware responses about a user’s projects, workflows, and code. The company says this makes its support more relevant for financial data analysis than what a general-purpose coding assistant offers.

The company says users can generate BQL and PyBQL queries to retrieve and analyze Bloomberg financial data spanning equities, funds, fixed income, foreign exchange, commodities, indices, derivatives, and other asset classes. Those queries can draw on more than 22,000 fields, including 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, according to the announcement. They can ask questions about Bloomberg libraries, BQuant workflows, and client-facing product documentation, and they can discuss financial concepts while generating code to implement models or techniques suited to a particular workflow.

For visualization work, Bloomberg says the assistant can recommend data visualizations and generate code using open source libraries such as Plotly and Jupyter Widgets. Users can also select existing code and ask the assistant to explain it, which the company describes as a way to develop Python knowledge while working.

Approval-Gated Execution in the Sandbox

Beyond suggestions, BQuant Assistant can, subject to the user’s approval, insert and run code directly in the user’s active project within the BQuant sandbox. Bloomberg says this design keeps the work in a single environment rather than forcing users to switch context between posing a question and acting on the answer. The company says users retain full control over these actions because the assistant flags each action it proposes and asks for approval before it reads from or writes to a notebook. Inserting, running, debugging, and iterating on PyBQL or Python code in an active notebook all sit behind that approval step.

Availability and Prior AI Announcements

Bloomberg said the introduction follows a series of recent company announcements of other AI-enabled solutions, which it described as aimed at helping investors and their firms get more value from its financial data. Named examples are ASKB, the conversational AI interface on the Bloomberg Terminal, and Enterprise Model Context Protocol (MCP), which the company describes as an AI access layer for Data License Plus (DL+), its next-generation Data License offering.

General availability in BQuant Enterprise and a limited beta in BQuant Desktop are planned for the end of October 2026, according to the company.