Civils.ai
AI takeoff and document-review platform for construction contractors and consultants that pulls quantities and geotechnical data from PDF drawings and checks them against specs and codes.
Best for: Estimators, groundworks teams, and pre-construction teams automating takeoffs and spec checks
Last reviewed 6/2/26
- Pricing
- Starter US$90/month (10 takeoffs); Professional US$270/month (30 takeoffs); Enterprise custom (API & MCP, SSO/SAML)
- Property types
- Infrastructure, Civil Works, Commercial
- Geography served
- Used by 200+ firms across 8 countries (United States, United Kingdom, Europe, Hong Kong, Singapore, Australia, New Zealand, South Africa)
How Civils.ai uses AI[1][4]
AI agents read PDF drawings and reports, extract takeoff quantities (areas, lengths, volumes, counts) and subsurface geotechnical data, and run compliance checks against specs and codes with cited sources, all under human QA review. The vendor claims 90% less manual effort and 97% accuracy on modern PDFs.
- • Extracts measurements from modern PDFs, scanned documents, and historic hand-drawn drawings
- • Pulls earthworks quantities and borehole data from geotechnical reports
- • Cross-checks drawings against specifications, contracts, and codes of practice with cited answers
- • Keeps a human expert team in the loop to review and verify AI measurements
AI type: Vertical AI agents for document extraction and retrieval
API: yes MCP: yes
Key numbers[1]
- • Company-reported 90% reduction in manual effort
- • company-reported 97% accuracy on modern PDFs
- • US$3 billion+ in projects supported
- • 200+ firms across 8 countries
- • JTC engagement reported 2,842 AI prompts processed and 528+ hours of efficiency savings
Credibility[1][3]
- Founders
- Stevan Lukic (CEO, civil engineer who previously did manual takeoffs), Mirko Vairo (COO, operations and customer success), Mohamad Fadil (CTO, leads AI and engineering)
- Customers
- 200+ contractors and consultants including AECOM, Arup, Jacobs, WSP, Costain, Kajima, Meinhardt, Penta Ocean, and JTC
- Investors
- Pre-seed backed by Atlas, Antler, and Iterative (round closed 2023)
Founded
2022
Headquarters
Singapore
Stage
Pre-seed
Employees
11-50
Related companies
Togal.AI
AI-powered construction takeoff platform that automatically detects and measures spaces from architectural plans, completing in seconds what traditionally takes hours.
Deep learning models read architectural drawings to detect, measure, label, and compare spaces and features, automating the takeoff that estimators traditionally do by hand. Togal.AI reports 98% accuracy on floor plans.
Digs
AI-powered collaboration platform for residential home builders covering preconstruction planning, 3D digital-twin handoff, and AI warranty management. Sells seats to builders, who invite trades and homeowners as collaborators.
Digs converts standard PDF and CAD building documents into searchable plans and interactive 3D digital twins, then layers natural-language Q&A on top so builders and homeowners find project details fast.
Volve
Volve uses construction-specific AI agents to turn full tender document sets into structured, linked context, then flags risks, deviations, and compliance gaps with traceable source links back to the original documents. The platform reads and connects PDFs, Word, and Excel files using retrieval-augmented generation and natural language processing trained on construction terminology and contract hierarchies. Volve reports users spend 60% more time on early mitigation and optimisation and see 30% less rework.
Volve uses construction-specific AI agents to turn full tender document sets into structured, linked context, then flags risks, deviations, and compliance gaps with traceable source links back to the original documents. The platform reads and connects PDFs, Word, and Excel files using retrieval-augmented generation and natural language processing trained on construction terminology and contract hierarchies. Volve reports users spend 60% more time on early mitigation and optimisation and see 30% less rework.