Please turn your device to portrait.
Oslo-based startup launches AI construction software that interprets and understands drawings.
With the stated aim of ‘making any design buildable’, this Norwegian start-up has outflanked their competitors and launched what may be, or soon will be, the default go-to software that bridges the gap between design documents and the unforgiving reality of a construction site.
With large construction projects invariably generating over a hundred design documents and frequent updates, misinterpreting designs due to static PDFs, spreadsheets, and missing critical construction data, the consequences of poor file management can be dire.
Enter Sparkel, a cloud-based software which according to a company release, “Deploys the Model Derivative API to extract and translate 2D and 3D designs and the Viewer to display models in a web browser.”
In effect, it’s using AI and ChatGPT to extract, and update data from building information models (BIM) and PDFs to identify design issues, estimate quantities, adapt to changes, and facilitate effective communication with stakeholders.
“With Sparkel, construction professionals can:
Watch their story
According to a company release: “Sparkle’s AI engine also allows users to pose questions such as, ‘How much precast concrete is on the 2nd floor?’ The software then presents tables and information directly linked to the drawings, providing quick and precise answers.”
On launching their AI construction software, Peder Aaby, Co-founder & CTO at Sparkel, said, “We have developed an application that interacts with various databases to extract data that is not included or missed in the [construction] model. In order to achieve this, we have implemented advanced algorithms utilising Webworker, enabling us to extract and aggregate data in order to retrieve different quantities to make pricing and extract CO2 emissions, and various parameters for each phase of the project.”
Sparkle’s ultimate goal is to enable circularity within the construction industry, and by using digital twins, (which also holds precise information about the building), they’re also positioning it to be of value with adaptive reuse.
Sparkle also estimates that take-offs happen five times faster compared to manual processes, resulting in substantial time and cost savings.
See: https://sparkel.io/
