Bloomberg adds BQuant Assistant, a conversational AI coding tool, to its quant platform

What BQuant Assistant does

According to Bloomberg, BQuant Assistant sits inside the Python environment where users already build investment strategies, dashboards and quantitative analyses. It can answer questions about BQuant, generate Python code, help query Bloomberg's datasets through Bloomberg Query Language (BQL), debug and iterate on work, and build code for data visualizations.

The assistant can also search the BQuant Help Center and draw on example notebooks, libraries and how-to guides. Bloomberg says this grounding in the BQuant environment allows it to give context-aware answers about a user's projects, workflows and code, and to provide more relevant support for financial data analysis than a general-purpose coding assistant.

It can suggest code and, subject to the user's approval, insert and run that code in the active project within the secure BQuant sandbox. Bloomberg says users keep full control, because the assistant identifies the action it proposes and asks for approval before reading from or writing to a notebook.

Capabilities listed by Bloomberg

Bloomberg lists several tasks users can carry out with the assistant:

• Generate BQL and PyBQL queries to retrieve and analyze Bloomberg data across equities, funds, fixed income, FX, commodities, indices, derivatives and other asset classes, covering more than 22,000 fields.
• Create code for screens and universes across several asset classes, including exchange-traded funds.
• Insert, run, debug and iterate on PyBQL or Python code in an active notebook, subject to user approval.
• Ask about Bloomberg libraries, BQuant workflows and client-facing product documentation.
• Discuss financial concepts and generate code to implement suitable models or techniques.
• Get recommendations for data visualizations and generate code with open source libraries such as Plotly and Jupyter Widgets.
• Select existing code and ask the assistant to explain it, which Bloomberg says helps users build their Python knowledge.

The data fields mentioned include reference, pricing, returns, derived analytics, fundamentals, valuations, sustainable finance data, risk metrics, estimates and economic data.

Availability and the BQuant product line

BQuant Assistant will be generally available in BQuant Enterprise, and in limited beta in BQuant Desktop, at the end of October 2026, according to Bloomberg. The company says both versions of BQuant will include it.

BQuant is a suite of data science tools for financial markets built on a Python stack that combines Bloomberg data and analytics with open source libraries and pre-built example projects. BQuant Desktop is included with a Bloomberg Anywhere subscription and gives enabled Terminal users programmatic access to Bloomberg data in a secure sandbox. BQuant Enterprise is described as a fully managed, cloud-based platform with large-scale compute, internal data integration and collaborative development. Firms can connect proprietary data sources, integrate enterprise Git platforms, reuse internal code through private Conda channels and schedule projects.

The launch follows other recent Bloomberg AI announcements, including ASKB, the Terminal's conversational AI interface, and Enterprise Model Context Protocol (MCP), an AI access layer for Data License Plus (DL+).

What it means for users

Shawn Edwards, Bloomberg's Chief Technology Officer, said that "turning an investment idea into a repeatable analysis can still require significant time and specialized coding knowledge." He said the assistant is meant to help every BQuant user, "from a portfolio manager sketching out a first query to a quant engineering a multi-asset signal", move from a natural-language question to working code, data retrieval and visualization.

For existing BQuant customers, the practical change is that code generation, data querying and explanation are available in the same environment where they already work, with approval steps before the assistant touches a notebook. Bloomberg positions the tool as a way to test ideas and refine analyses faster, though the announcement gives no performance figures or pricing.