How Balyasny Asset Management built an AI research engine
By combining rigorous model evaluation, full-platform use of OpenAI, and agent workflows, Balyasny is reinventing investment research.
Resultater
95%
Andel af investeringsteamet, der bruger AI-researchsystemet
Resultater
Days to hours
Med agenter, der drives af OpenAI-modeller, kan dybdegående researchopgaver, der tidligere krævede dage, nu færdiggøres på timer
Balyasny Asset Management(åbner i et nyt vindue) (Balyasny) is a global, multi-strategy investment firm with approximately 180 investment teams across diverse asset classes and geographies. The firm operates in a highly competitive and dynamic industry where conviction, precision, and speed are all critical to success. Facing an increasingly complex market environment with surging volumes of financial data, Balyasny saw an opportunity to reimagine the investment research process using AI.
In late 2022, Balyasny established an Applied AI team: a centralized group of 20 researchers, engineers, and domain experts tasked with building AI-native tools that embed directly into team-level workflows. Their flagship product, an AI investment research system, is designed to reason, retrieve, and act like a skilled analyst.
"AI gør det muligt for vores teams at anvende første principper ved at tænke hurtigere på tværs af flere data og mere struktureret."
Investment research is complex, high-stakes, and time-sensitive. Analysts must parse through thousands of documents, from market data and research to regulatory filings. Human expertise remains essential, but traditional methods are time-consuming and difficult to scale.
Off-the-shelf AI tools often can’t handle structured and unstructured data together, lack workflow orchestration, and aren’t built to meet institutional compliance standards. Balyasny needed something purpose-built: an AI system that could think like an analyst, move at the speed of a machine, and work within strict compliance boundaries.
Before any models went into production, Balyasny built one of the most sophisticated evaluation pipelines in finance, measuring models across 12+ dimensions including forecasting accuracy, numerical reasoning, scenario analysis, and robustness to noisy inputs. These evaluations are run against Balyasny’s internal benchmarks, tools, and proprietary financial data.
This rigorous process surfaced strengths in the GPT‑5.4 model family, particularly in multi-step planning, tool execution, and hallucination reduction. Today, Balyasny uses GPT‑5.4 as a reasoning engine within their AI system, alongside internal models, which are selected task-by-task based on empirical performance.
“Vi evaluerer modeller på samme måde, som vi evaluerer investeringer: ud fra fundamentale beviser. GPT-5.4 beviste, at den var i stand til at planlægge, ræsonnere og arbejde med stor præcision.”
Balyasny made a strategic decision to involve OpenAI directly in user-facing workflows. OpenAI teams observed directly how investment teams use their AI system: where it succeeds, where it struggles, and what high performance actually looks like in a commercial context.
That visibility led to faster iterations, tighter product feedback loops, and better model behavior in finance-specific tasks. As a design partner for frontier model releases, Balyasny has influenced the OpenAI roadmap by surfacing insights from actual analysts, not test cases.
“Vi fortalte ikke bare OpenAI, hvad vi havde brug for. Vi viste dem, hvad vi havde brug for. Og det gjorde hele forskellen.”
Because AI is deeply embedded in the day-to-day workflows of investment teams, they can collect structured feedback in real time on everything from user evaluations and outcome audits to tool execution quality. That loop drives rapid improvements to both models and the orchestration layer.
For example, early feedback from merger arbitrage teams revealed that agents needed to continuously re-evaluate deal probabilities as new filings or press releases came in. The Balyasny team quickly extended agent planning capabilities and tool access, replacing a slow, manual workflow with real-time probabilistic monitoring.
While each investment team has a distinct investment strategy, Balyasny took a centralized approach to AI deployment. Their Applied AI team develops core components, including agent frameworks, toolchains, and compliance guardrails, which are then deployed across teams with scoped access to data and tools.
This “federated deployment” model means each investment team can develop and use AI agents tailored to their asset class (for example, macro, commodities, and equities), while the Applied AI team focuses on scaling architecture, research, and model evaluations. It also ensures that compliance and regulatory standards are universally respected—critical in an industry where risk management and data security are non-negotiable.
“Vores tidlige investeringer i AI gav fantastiske resultater. I dag kan hvert af vores investeringsteams beslutte, hvordan de vil anvende den nyeste AI i deres proces, i et sikkert miljø og med ekspertvejledning i realtid.”
Today, ~95% of Balyasny investment teams actively use their AI platform, with measurable impact across velocity, output quality, and analyst experience:
- Deep research tasks that once required days are now completed in hours, with agents synthesizing tens of thousands of documents, including filings, research, and earnings.
- A Central Bank Speech Analyst cut macroeconomic scenario analysis time from 2 days to ~30 minutes.
- A Merger Arbitrage Superforecaster agent now monitors and updates deal probabilities continuously, replacing bespoke spreadsheets and manual alerts.
Just as importantly, analysts at Balyasny report higher confidence in outputs. With scoped tools, traceable reasoning paths, and testable agents, they use AI to deliver structured, explainable insights that increase conviction and inform human decision making.
Balyasny continues to expand its AI roadmap with a focus on:
- Reinforcement Fine-Tuning (RFT) to sharpen model behavior on complex, high-value tasks
- Deeper agent orchestration across financial domains
- Multimodal inputs including financial charts, statements, and filings
Evaluation of future frontier models for domain fit.
“Det er ligesom at tilføje en holdkammerat, der aldrig glemmer, altid citerer kilder korrekt og dobbelttjekker detaljerne, før der sendes noget tilbage.”
