Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

ADEPT: A Pedagogical Framework for Integrating Agentic AI with Deterministic Scientific Workflows (in en)

Technical Report ·
 [1];  [1];  [2];  [2];  [2];  [2];  [2];  [2];  [2];  [2];  [1];  [2]
  1. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)
  2. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
+ Show Author Affiliations

The integration of Large Language Models (LLMs) into scientific research promises to accelerate discovery, yet a significant gap remains between the dynamic reasoning of Artificial Intelligence (AI) agents and the static, deterministic nature of canonical scientific workflows. This paper introduces ADEPT (Agentic Discovery and Exploration Platform for Tools), a reference architecture and pedagogical framework explicitly designed to bridge this gap. ADEPT's primary mission is to provide a transparent, "glass-box" environment where researchers and engineers can learn to effectively wrap established scientific software (e.g., BLAST, Nextflow pipelines) and compose it into reliable, agent-driven workflows. We describe its modular, multi-server architecture, which leverages the Model Context Protocol (MCP) for tool serving, LangGraph for robust agentic orchestration, and a secure nsjail-based sandbox for safe code execution. By prioritizing architectural clarity, safety, and modularity, ADEPT serves as an extensible blueprint for building trustworthy AI-augmented systems and fosters the collaborative development necessary to responsibly employ agentic AI for science. We provide practical examples of how to adapt and extend this framework, highlighting its utility in workforce development and AI-readiness capabilities across research and development projects.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)
Sponsoring Organization:
USDOE Office of Science (SC), Biological and Environmental Research (BER)
DOE Contract Number:
AC05-76RL01830
OSTI ID:
3006464
Report Number(s):
PNNL-SA--216605
Country of Publication:
United States
Language:
en

Similar Records

VISION: a modular AI assistant for natural human-instrument interaction at scientific user facilities
Journal Article · Wed Jun 04 00:00:00 EDT 2025 · Machine Learning: Science and Technology · OSTI ID:2572358
The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science
Conference · Sat Nov 01 00:00:00 EDT 2025 · OSTI ID:3009442

Related Subjects

Artificial Intelligence
Computational Biology
Computational science
Engineering
Pedagogy
Software
Software development