Digitization Companion (DigiCo)

The Digitization Companion (DigiCo) is AI-based prototype software for Smart P&IDs, developed from our research. It digitizes engineering diagrams such as Piping and Instrumentation Diagrams (P&IDs) and process flow diagrams (PFDs) and turns them into machine-readable data. The first beta version was released to selected users in February 2026.

From research project to platform

DigiCo started more than five years ago as a research project of the Process Intelligence Research group on AI-based digitization of engineering diagrams (see digitization of engineering diagrams). It is now being developed into prototype software for Smart P&IDs: machine-readable diagrams stored in a knowledge graph, which form the basis for generative AI applications such as ChatP&ID.

Several hundred users signed up for early access. A team of software engineers is turning the research into industry-grade software. A first beta release is planned for early 2027.

Features

• Automated data extraction. The AI identifies and extracts information from diagrams, including symbols, text, tables, lines, and connections. Users review and edit the results.
• Standard formats. Digitized diagrams can be exported in the DEXPI standard and in formats such as CSV, JSON, and XML, for use in existing engineering software.
• Smart P&IDs in a knowledge graph. Digitized P&IDs are stored as a knowledge graph that AI tools can query.
• Security. Proprietary engineering data are handled confidentially and stored encrypted.
• Collaboration. Several users can manage and work on projects together.

Further developments

Building on Smart P&IDs, we are developing:

• ChatP&ID: asking questions about P&IDs in natural language;
• automated error correction of engineering documents;
• multi-agent AI collaboration in process design;
• AI support for HAZOP studies.

Sign up

More information and the sign-up for access are available at www.digitization-companion.com. News about DigiCo is posted on LinkedIn.

Key publications

• Theisen, M. F., Flores, K. N., Schulze Balhorn, L., & Schweidtmann, A. M. (2023). Digitization of chemical process flow diagrams using deep convolutional neural networks. Digital Chemical Engineering, 6, 100072. doi:10.1016/j.dche.2022.100072 · Details
• Alimin, A. A., & Schweidtmann, A. M. (2026). GraphRAG for engineering diagrams: ChatP&ID enables LLM interaction with P&IDs. AIChE Journal, 72, e70540. doi:10.1002/aic.70540