Many in the chemical process industries (CPI) view generative artificial intelligence (genAI) as a powerful augmentation layer for the modern chemical workforce, and one that can unlock insights faster, lead to leaner operations and provide a more intuitive interface between people and plant data. This one-page capsule summarizes a set of emerging use cases for generative AI in chemical process operations.
GenAI and machine learning
Most currently adopted use cases for AI technology that have created value for manufacturers in the CPI involve machine-learning (ML), the subfield of AI in which computing systems use algorithms to identify patterns in data and infer relationships, rather than being explicitly programmed for each task. ML models learn to improve performance over time as they encounter increasing amounts of data. ML use cases have generally been focused on predictive maintenance, process optimization and emissions compliance, among others.
GenAI is a narrower subset of ML that leverages the use of learned patterns to create new material, such as text and images. Although there has been an explosion of genAI use in wider society through popular large-language models (LLMs) like ChatGPT, for example, the use of these tools in industry has been necessarily more cautious (Figure 1).
FIGURE 1. LLMs allow queries of plant data based on natural language
GenAI use case categories
Although they are still maturing, a number of use cases for genAI tools are gaining traction on plant floors, and are already starting to accelerate documentation, training, analytics and decision-making in manufacturing facilities. The following are brief descriptions of eight categories of use cases for genAI in the CPI.
Standard operating procedure (SOP) generation and knowledge documentation. GenAI can automatically draft SOPs, safety procedures and maintenance checklists by learning from existing documentation, historian data and control logic. Domain-tuned LLMs, which are specialized AI models adapted from general-purpose models, can parse engineering documents and synthesize coherent instructions customized to plant-specific operations.
Natural language interfaces to complex systems. With natural-language processing and tools (such as LangChain or Azure OpenAI Service) that connect LLMs to external data and memory, genAI tools can translate human language into structured queries or engineering logic. LLMs fine-tuned with domain-specific data can allow plant personnel to interface with plant data and query large datasets or historian systems in plain English (or other human languages).
Automated root-cause analysis reports. After a process deviation or equipment failure, genAI can compile multi-system data (from distributed control systems, alarms, maintenance logs and so on) and create narrative reports that summarize likely root causes, based on previous incidents and plant knowledge bases.
Technical report and audit preparation. GenAI can be used to prefill environmental-audit templates, emissions disclosures and performance reviews by pulling data from production reports, historian tags and manufacturing execution systems (MES). These models can also generate summaries in regulatory language aligned with U.S. Environmental Protection Agency (EPA; www.epa.gov), Occupational Safety and Health Administration (OSHA; www.osha.gov) or E.U. Registration, Evaluation, Authorization of Chemicals (REACH) frameworks.
Simulation and scenario narrative generation. When coupled with digital twins or process simulation engines, genAI can generate interpretive narratives of simulated outcomes. This helps plant personnel better understand the implications of parameter changes, equipment failures or operating strategies without needing to manually analyze timeseries outputs.
Code and logic generation for engineering applications. LLMs like Codex or GitHub Copilot are increasingly being used to accelerate development of engineering scripts, logic blocks and visualization dashboards. Engineers can describe the intent (for example, “plot batch cycle times over the last six months and flag anomalies”), and the GenAI tool produces code in programming languages such as Python, SQL, or even SCADA scripting languages to accomplish that function.
Training and operator enablement. GenAI systems are capable of generating quizzes, flashcards, safety walkthroughs and interactive training content based on actual plant procedures and historical performance data. By tailoring this content to specific unit operations or employee roles, companies can dramatically reduce onboarding time and reinforce critical knowledge.
Generative design and equipment layouts (emerging).While still early in their development, generative models are being trained to propose plant equipment layouts, process flow diagrams (PFDs) or even molecule structures based on desired outcomes or constraints. These tools can suggest design alternatives, compare tradeoffs and accelerate early-stage engineering work.
Editor’s note: The content for this column was adapted from the following article: Alexander, J., Use of AI in Chemical Manufacturing, Chem. Eng., June 2025, pp. 23–29. Other sources include: Mori, L., Macak, M. and others, How AI enables new possibilities in chemicals, McKinsey & Co. article, Nov. 2024, www.mckinsey.com; and ICIS, How chemical companies are implementing AI, Independent Commodity Intelligence Services, Web article, icis.com, accessed Feb. 2026.