Project and information management company Newforma who specialise in architecture, engineering, construction and owner (AECO) firms has announced the acquisition of Lumi AI, a company whose analytics engine turns plain-language questions into accurate, explainable answers.
According to Newforma, AI used to inform project decisions should meet three tests. Answers must be explainable to ensure visible reasoning, they must be verifiable against the source data, so they can be checked, and they must be accurate enough to act on, because on a live project a decision carries liability. Lumi has built its engine around those tests, as it asks clarifying questions when a prompt is vague, shows the logic behind every answer, and proactively flags data quality problems when it finds them.
Architecture and engineering firms hold years of project history in their systems such as issues, RFIs, submittals and model coordination records. Not all firms have dedicated business intelligence teams. That data answers a question only when someone stops and builds a report, leaving much of the available data underused.
“A lot of companies are telling this industry their AI is better. We’d rather say out loud what better means and be measured against it. Explainable, verifiable, accurate enough to act on when liability is on the line.
“Our customers don’t need another AI that sounds confident, they need answers they can verify. Pairing Lumi’s engine with the deepest project data structure in AECO is how we set the standard rather than join the chorus.
“Everyone in this industry wants to be your single source of truth. We would rather be the single view into all of them.”
Peter Cannone, CEO, Newforma
Project teams often rely on technology from multiple vendors and project information sits across design tools, CA trackers, document systems, email, Teams messages and the field, and a firm’s real history spans all of it. According to the firm, vendors in this industry offers to be the single source of truth, which asks a firm to move its work into one place and leave the rest behind. Newforma is the single view into all the sources of truth a project already has, and Lumi’s agentic layer is what lets a question reach across them and come back with an answer that can be checked
Lumi’s engine builds a semantic layer over the operational systems it reads, so it works from what the data means rather than only where it lives. That semantic and clarification layer, developed over three years, supports the engine’s ability to deliver explainable, verifiable and accurate answers.
The engine will initially be integrated into Newforma platforms, drawing on over 20 years of AECO project data structure, comprising issues, RFIs, submittals and communication history. An RFI is a submittal cycle which has a shape, and a coordination issue means something specific. That structure provides the context needed to generate reliable answers for construction-related decisions. The result is insight nobody must go looking for.
Newforma Konekt will surface which consultant is slowing RFI turnaround, which project’s issue pattern matches one that went wrong before, and where a submittal cycle is drifting from a firm’s own baseline. Grounded in the firm’s data, with the reasoning shown.
“We started Lumi to redefine how people interact with their own data: to make it as simple as asking a question.
“Newforma brings rich project data and a large base of firms who depend on it. Combining that with Lumi’s engine unlocks far greater value for a much wider audience.”
Ibrahim Ashqar, Co-Founder and CEO, Lumi AI
Tudor Boiangiu, the Co-Founder and CTO of Lumi AI, joins Newforma as VP of AI Engineering, with the Lumi engineering team continuing to build from Toronto. Lumi’s agentic layer will extend Vojo, the AI assistant Newforma introduced at Newforma World 2026 in May.
“We spent three years building an engine that asks instead of guessing. That work is worth nothing without data that already means something, and Newforma has 20 years of it.
“They had also already committed to AI and built the framework to carry it. So, I am not here to convince anyone this matters. I am here to build it.”
Tudor Boiangiu, VP of AI Engineering, Newforma
Vojo runs on Newforma’s agentic framework, with planned capabilities including natural language search and cross-project queries across project data. Lumi adds the analytics layer that turns those questions into verifiable answers in Newforma Konekt’s smart project dashboards, with rollout details to follow.
