Bimmatch

Client: Mekorot, The National Water Company of Israel Objective: Automate compliance checks across the client's projects. Create, manage, share, and analyze the client's 3D Organizational Database as a single source of truth for automated compliance control checks. Challenge: Mekorot teams waste valuable time checking project compliance against codes and regulations, technical documents, and utilities' digital twins across the planning to operational phases. Scope: 1200 elements (pipes, pipe accessories, fittings, etc.), 4,000+ document pages, 600 projects, multiple disciplines, and integration with 3 software platforms. Bimmatch's solution: Using AI-powered semantic and engineering logical algorithms, Bimmatch connects all data into a unified 3D interface. Operators and engineers can simply ask: "What are the gaps between the element 'Pump-X' and the engineering requirements?" and instantly retrieve relevant results from across siloed systems. Tech Used: Bimmatch core AI engine, Revit & Plant 3D & Civil3D plugins, Bimmatch CMS, ACC. Outcome: Reduced engineering review time by 80% Status: Commercial agreement signed; all tenders to integrate Bimmatch by 2026

Pilot: Autodesk, Inc. Objective: Currently, linking project schedule activities to 3D digital twin components is a manual task. This process is not only slow but also increases the risk of errors and inconsistencies. Scope: The BIM project included approximately 40,000 components with a lean level of detail. The associated Primavera P6 schedule contained around 15,000 activities in the Gantt chart. Bimmatch's solution: Connecting the project Gantt (Schedule activities and procurement activities) to the 3D digital twin, automatically, with no need for manual tagging. Tech Used: Bimmatch AI core engine, Autodesk Construction Cloud APIs, Automatic asset creation, Automatic enrichment included MasterFormat classifications, materials, trades, location, etc. Outcome: 90% accuracy (checked against client results), auto-matching each 3D component with the relevant activity task and referring to the row on the Gantt chart. Our AI solution surfaced +200 mismatches. Status: Pilot completed successfully

Client: Geothermal energy project (Ormat Technologies Ltd.) Objective: Engineers waste valuable time identifying tender risks before they become issues. Scope: Analyze the tender against the company’s historical knowledge and its established engineering best practices Bimmatch's solution: The system divided the 250-page tender doc into text chunks specifically for the client's specialized engineers, capturing elements and relationships between entities, e.g., pipe types, flow types, velocity of flow, standards, and pipe locations. Tech Used: Bimmatch AI core technology Outcome: Client's technical engineers across five different role types were provided with only the specific project requirements relevant to their scope of work. This targeted delivery eliminated the need to manually search through new documents, enabling each engineer to focus on accurate, role-specific data during the bidding process, improving both efficiency and quality of proposal preparation. Status: Pilot completed successfully

Client: NTA, Metropolitan Mass Transit System, Tel Aviv Metroline projects Objective: Today, ongoing requirements are disconnected from the engineering design process, causing discrepancies and changes along the way. Archiving engineering information from the 'architectural and structural security design' document and matching the requirements with the 3D model automatically. Scope: 250+ pages of project safety requirements, PIR, EIR, and the BIM metroline projects. Bimmatch’s Solution: Mapping, enriching, and analyzing the project’s documents and models and connecting elements with their real-world elements. Enrichment included: LOD, Disciplines, design areas, trades, MasterFormat, Rooms, and dependencies. The queries of the documents are carried out by connecting to the digital twin model and detecting discrepancies automatically. Results were generated in an Excel file. Tech Used: Bimmatch AI core technology Status: Completed

Client: Tel Aviv Municipality, Construction and Infrastructure Department, Public Buildings Division. Objective: Conflicts exist within the requirements documents due to multiple documents and versions. The client wishes to QA the consistencies of the requirements before sharing the documents with the various planners and operators. Bimmatch's solution: AI spots spec deviations and clash detection between requirements and as-built models. Scope: Mapping, analyzing, and enriching data of a 250-page document and a BIM model- connecting data down to the element type level. Fast and advanced information search and query on the 3D model. The client will be able to easily QA the materials. During Construction, more technical requirements and updated models will be added for automated QC. Bimmatch will compare the data to detect deviations (e.g., incorrect equipment, wrong installation height). Issues are prioritized and sent directly to the responsible contractor. Tech Used: Bimmatch AI core technology Outcome: Fewer manual checks. Instant identification of non-compliance. A central, traceable record of all QA/QC and verification activities.

Client: Army Corps of Engineering Challenge: Gaining full visibility into how project requirements influence downstream design and construction decisions is a significant barrier. Complex dependencies between system elements, standards, and materials are often buried in disconnected documents and models. Objective: Automatically extract and structure capital insights from unstructured, multi-disciplinary documents, such as SOWs, specifications, equipment procurement plan, and BIM project models, into clear, contextual action items and Bill Of Materials (BOM). Scope: A civil engineering project involving 12,000+ pages of documentation across formats and BIM models. Integration with multiple engineering disciplines, including the local building code classification system Bimmatch’s Solution: Bimmatch analyzes project data (past and present) to reveal gaps between design, execution, and field performance. Key insights are delivered visually through the 3D model and the enriched BOM. Tech Used: Bimmatch AI core technology, Graph RAG, LLM models, BOM generator. Revit and Plant 3D plugins. Proprietary knowledge graph aligned with military planning structure Status: Pilot initiated