Trunk Tools launches Cortex AI platform to interpret construction drawings

Trunk Tools launched Cortex, an AI that reads construction drawings and caught a $60,000 hidden change. It also slashes submittal review from 2 hours to under 10 minutes.

Published on: Jun 18, 2026
Trunk Tools launches Cortex AI platform to interpret construction drawings

New York-based construction technology vendor Trunk Tools launched Cortex on June 17, 2026, an AI layer trained to interpret construction drawings and connect them to specifications, RFIs, submittals, schedules, and change orders. The platform, developed over four years alongside some of the country's largest general contractors, powers seven AI workflow agents designed to reduce rework and speed document review across project teams.

The launch comes as construction technology providers race to expand AI capabilities, a shift that is reshaping how project documents are managed. This is part of a broader wave of AI for Real Estate & Construction innovation, where firms like Gilbane have already deployed earlier Trunk Tools AI agents. Drawings remain a persistent obstacle because software must interpret symbols, revisions, and relationships across hundreds or thousands of sheets while keeping those elements linked to the project record.

How Cortex interprets construction drawings

"We have trained for years AI models specifically on construction drawings," said Sarah Buchner, founder and CEO of Trunk Tools. "We're now at a point where our AI can detect hundreds of different objects on drawings and actually compare different drawings to each other." The system analyzes markups, the visual language of construction, and the relationships between sheets to give teams a connected view of project documents.

Instead of treating each drawing as a separate file, Cortex links objects on a floor plan to associated specs, schedules, and other records. Users can select an item on a drawing and immediately see its requirements, change history, and related submittals. That connection removes the manual cross-referencing that often slows down review.

Catching hidden changes and reducing rework

One of the platform's most practical capabilities is identifying modifications that occur outside of revision clouds - a common source of missed scope changes and costly rework. "We can tell you exactly what changed," Buchner said. "We can tell you exactly what changed, what the architects are trying to hide."

She pointed to a recent example involving an electrical issue outside a revision cloud that carried an estimated $60,000 in project impact. Cortex compares revised drawing sets, flags modifications, and analyzes how those changes affect related documentation such as RFIs and change orders.

Submittal review goes from hours to minutes

Cleveland Construction, based in Mentor, Ohio, began piloting Trunk Tools before expanding its use. The contractor has cut submittal review times from roughly two hours to under 10 minutes by routing documents through the platform before project staff review them. The software compares product data against specification requirements and categorizes each item as compliant, partially compliant, or non-compliant.

"Inherently in the business and construction, we give the most inexperienced part of the project management staff the submittal review for whatever reason," said Elliot Christiansen, the contractor's senior vice president of operations. "And it's probably one of the hardest technical things to wrap your head around as somebody new in the industry."

In one instance, Cortex flagged a waterproofing membrane specified for an underground elevator shaft. The specification called for a 10-year warranty, but the product data sheet - buried in fine print - listed a one-year warranty. The discrepancy was caught before installation. The system also helps identify missed ASTM and ANSI standards that less-experienced staff may overlook. Cleveland Construction reduced average submittal cycle times from 55 days to 13 days by improving first-pass accuracy and cutting revise-and-resubmit cycles.

Getting the workforce AI-ready

Buchner said the biggest barrier to AI adoption is not technology selection or security. "The biggest one is how do you get your workforce AI-ready?" she said. Contractors that see the most success are those where leadership drives adoption rather than waiting for field teams to discover the tools on their own.

Christiansen echoed that point from the field perspective. "If there's any additional work required in the field - where you make anybody's job any harder - they're just not going to [use] it," he said. "They're going to keep doing it how they've always done it." The platform's value, he noted, comes from making review and coordination easier, not adding steps.

Why this matters for real estate and construction professionals

For project teams managing document-heavy workflows, Cortex shows that AI can shrink review time from hours to minutes and catch specification mismatches before they become field problems. The real-world examples - a $60,000 electrical change missed outside a revision cloud, a warranty buried in fine print - make clear that these aren't theoretical risks. The technology works where it counts, but the adoption lesson is equally blunt: if a tool adds friction for the people on site, it won't be used. Teams that embed these capabilities into existing review steps, with leadership setting the expectation, will see the fastest payback.


Get Daily AI News

Your membership also unlocks:

700+ AI Courses
700+ Certifications
Personalized AI Learning Plan
6500+ AI Tools (no Ads)
Daily AI News by job industry (no Ads)