Pegasus AI
Next-Gen Workflows
Funded by the National Science Foundation · Award #2513101
Next-generation workflow management — intelligent automation, real-time monitoring, and LLM-powered tools for large-scale scientific computing.
PegasusAI is the next-generation AI-driven scientific workflow management system developed by a multi-institutional team funded by the U.S. National Science Foundation.
ML models predict resource needs and optimize scheduling before execution.
Real-time anomaly detection and automatic plan adjustment mid-run.
AI-augmented tools keep researchers in control at every step.
Curated datasets to continuously improve AI models and decisions.
ML models that predict task runtime, memory, and resource needs to enable smarter scheduling.
Real-time tracking that detects anomalies, surfaces bottlenecks, and supports live workflow introspection.
LLM-powered tools that help scientists compose, validate, and refine workflows through natural language.
Educational integration into academic curricula, enabling students to engage with real-world scientific computing.
Modular architecture ensuring compatibility with the NSF cyberinfrastructure ecosystem.
Studio is the browser-based interface to Pegasus AI — describe your pipeline in plain language, let the AI build and configure it, then execute it across hundreds or thousands of cores with a single click.
Describe your scientific goal — the AI generates a fully configured Pegasus workflow.
Inspect and monitor your workflow graph as jobs run across the distributed infrastructure.
Submit to OSPool, ACCESS allocations, or your institution's cluster without touching a terminal.
Analyze results, build scripts, and iterate — all within the same AI-assisted environment.
Studio Orientation
Workflow Tutorial