cs.AINov 5, 2026

ChemE-as-Code: An Open-Source Platform for Agentic AI in Chemical Engineering

Authors: Artur M. Schweidtmann

Organizations: Process Intelligence Research Group, Department of Chemical Engineering, Delft University of Technology, Van der Maasweg 9, 2629 HZ Delft, The Netherlands

Abstract

ChemE-as-Code provides an open-source environment in which AI agents built on large language models (LLMs) can carry out chemical engineering work and engineers can check it. Its calculation tools range from catalysis through process simulation to plant layout, HAZOP and life cycle assessment, and skills tell a general-purpose agent how to use them. Engineering files are linked, machine-readable and versioned in Git; calculations run outside the LLM, each value records its origin, and automated checks report inconsistencies and out-of-date results by file and line. In an illustrative ammonia case, agents developed a written task into a preliminary basic-engineering package (simulation files, P&IDs, layout, HAZOP, datasheets, relief) for USD 224 of API cost in the design sessions. Planted faults and engineering changes show that the checks find what their rules cover and miss the rest, so they guide human review rather than replace it. No independent engineer has reviewed the design.

Figures & tables

Explore similar work

CardsList
  1. EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design

    May 19, 2026Gioele Molinari, Florian Felten, Soheyl Massoudi +1Multi-Agent LLM SystemsLLM Agent Evaluation

  2. Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning

    May 8, 2026Yuyang Wu, Yue Huang, Shuaike Shen +8AI Agents for Scientific DiscoveryLLM Agent Evaluation

  3. Context is all you need: Towards autonomous model-based process design using agentic AI in flowsheet simulations

    Mar 13, 2026Pascal Schäfer, Lukas J. Krinke, Martin Wlotzka +1Agentic WorkflowsAgentic Code Generation