Productivity AutomationVerified

Reviewed and published by trentmaziarz, July 20, 2026. Discovered and drafted by our automated research pipeline.

DataRobot announced syftr in May 2025, an open-source framework that automatically searches through millions of possible AI workflow configurations to identify the combination of components—such as retrievers, language models, and prompt strategies—that best balances accuracy, speed, and cost for a given enterprise use case. The framework is available publicly; an enterprise version was planned for fall 2025.

Details

Syftr uses multi-objective Bayesian Optimization to efficiently search a configuration space of over 10²³ possible agentic workflow combinations without requiring manual testing of each option. It is component-agnostic, meaning it can evaluate any embedding model, LLM, or pipeline module. In testing against six industry RAG benchmarks, the framework increased accuracy by 25 percent overall while reducing costs by 37 percent at baseline accuracy levels. Syftr generates production-ready LlamaIndex pipeline code for the optimal configuration identified. The open-source framework was released on Hugging Face; a DataRobot enterprise-integrated version was announced for fall 2025.

Products affected

syftr

Sources & Evidence

Company Disclosure

syftr | DataRobot

DataRobot·Mar 2026

https://www.datarobot.com/product/syftr/

Company Disclosure

DataRobot Launches the First Open Source Framework 'syftr' for Performant Agentic Workflows

DataRobot·May 2025

https://www.datarobot.com/newsroom/press/datarobot-launches-the-first-open-source-framework-syftr-for-performant-agentic-workflows/

News Article

DataRobot Launches the First Open Source Framework 'syftr' for Performant Agentic Workflows

Business Wire·May 2025

https://www.businesswire.com/news/home/20250528824014/en/DataRobot-Launches-the-First-Open-Source-Framework-syftr-for-Performant-Agentic-Workflows

Cite this record

Trace Foundation. (2026). DataRobot: DataRobot announced syftr in May 2025, an open-source framework that automatically searches through millions of possible AI workflow configurations to identify the combination of components—such as retrievers, language models, and prompt strategies—that best balances accuracy, speed, and cost for a given enterprise use case. The framework is available publicly; an enterprise version was planned for fall 2025 (data as of 2026-07-20) [Data set record]. AI Trace. https://www.aitrace.org/r/practice/13b8383d-150b-4641-aca1-318bc46379c0. Accessed September 4, 2026.

Stable link: https://www.aitrace.org/r/practice/13b8383d-150b-4641-aca1-318bc46379c0
Data as of: July 20, 2026
Last verified: Not recorded

How to cite AI Trace

Other practices by DataRobot

OtherDataRobot offers MLOps tools that allow enterprise organizations to monitor, manage, and govern AI models after they have been deployed to production, regardless of where or how those models were originally built. The system automatically tracks model health, detects data drift, and alerts teams when a model's performance is degrading.OtherDataRobot announced the Agent Workforce Platform in July 2025, co-engineered with NVIDIA, offering enterprise organizations a system to build, deploy, monitor, and govern AI agents that autonomously execute multi-step business workflows. The platform is designed to let organizations manage AI agents as digital workers across cloud, on-premises, and hybrid environments.Data AnalysisDataRobot offers predictive AI tools that enterprise organizations use to analyze historical data and generate forecasts across domains such as fraud detection, demand planning, credit risk, and equipment failure. These tools allow business analysts and data scientists to build, deploy, and monitor predictive models through a unified platform.

Have evidence about DataRobot's AI practices? Submit a report.

Report a Sighting →