Most verticals aren’t clean, well-oiled SaaS databases; the reality is ugly documents, proprietary schemas, implicit workflows, and long-running tasks that most general-purpose models struggle with.

This prompted construction project management company Trunk Tools to build a specialized, three-layer architecture — perception, semantics, agents — based on highly-detailed data to support high-accuracy, highly-relevant industry automation.

Their purpose-built stack has shrunk review cycles from months to days, prevented costly field errors, and given autonomous agents the ability to reason over millions of pages of documentation, the company says.

“We really set out to take the data from dispersed systems, pre-process it, structure it, go through our ontology into a knowledge graph, and then train AI models,” said Sarah Buchner, Trunk Tools’ founder and CEO and a former carpenter.

For builders in other verticals, the company’s approach could serve as a blueprint for transforming data chaos into agent-ready, industry-specific workflows.

Where General-Purpose LLMs Break Down on Industry Data

Foundation LLMs, while powerful, are optimized for breadth, not always depth.

“General-purpose LLMs are trained to be okay at everything, so they’re weak at anything niche,” said Kriti Faujdar, a senior product manager working in AI infrastructure, agentic AI, security, and LLM platforms. For instance: rare terms, domain-specific reasoning, the unspoken context that any practitioner “just knows.”

Web, app, and software developer Sébastien De Bollivier agreed that the biggest bottleneck is reliability on data that is “jargon-dense, abbreviation-heavy, and format-specific.”

“A GPT-4-class model can understand a French legal contract, but will fumble the specific article references practitioners need to cite,” he said.

Besides, the most valuable enterprise data never made it into pretraining anyway, Faujdar pointed out. It’s sitting in internal systems and proprietary formats. “RAG helps a little,” she said. “But it’s just giving better facts to a model that still can’t reason properly in the domain.”

Pre-training on domain data is critical; enterprises should then fine-tune on good task examples and build their own evals. “A few thousand examples from real practitioners beats millions of scraped, noisy ones,” Faujdar said.

Mixture-of-experts (MoE) can provide specialization without inference costs blowing up. Pairing RAG with fine-tuning also works well; RAG handles the factual long tail while fine-tuning fixes vocabulary and reasoning.

De Bollivier pointed to the advantage of hybrid stacks: a general-purpose model for reasoning and orchestration, a smaller fine-tuned model (or dense retrieval over a curated corpus) for domain-specific extraction. He advised: “Don’t fine-tune to make the model ‘smarter’ about a domain — fine-tune to make it more reliable on the specific output format your workflow requires.”

The trades and construction are certainly industries seeing traction with these techniques, as are legal and healthcare, De Bollivier said. These verticals have “high stakes for errors plus standardized document formats, equaling clear domain-training ROI.”

One honest caveat worth mentioning, Faujdar said: specialized models can often fall apart outside their domain, so they’re frequently not useful beyond their area of expertise unless re-trained.

Perception, Semantics, Agents: Inside Trunk Tools’ Three-Layer Stack

In highly-specialized domains like construction, “data dumps” into large language models (LLMs) don’t cut it, said Trunk Tools’ CTO Amrish Kapoor. Most transformers are probabilistic models: when given an image, they report back that it is “probably” a tree, or “probably” a child playing next to a tree.

This makes them insufficient for high-precision symbolic interpretation. In construction documents, for example, a 2-millimeter-wide symbol has a vastly different meaning depending on where it’s placed.

Further, constrained by context limits, probabilistic models struggle with long-term project memory. “I don’t mean a context window of a few tokens,” Kapoor said. “I’m talking about long-term memory that stretches across months and years, because this is how long some of these projects are.”

Instead, the company’s three-layer system breaks workflows into:

  • Perception — reading and extracting data from messy documents like PDFs, drawings, or scans
  • A semantic/graph layer — making sense of that data and understanding relationships between elements
  • LLMs and agents on top

Construction drawings are typically symbolic, Buchner said. A door isn’t always labeled “door.” Sometimes it’s simply an arc on a wall that a trained eye learns to read based on years of practice.

“The perception layer is what teaches AI to read that language,” she said. The semantic layer then gives that information meaning — connecting the door to the drawing that details it, the spec that governs it, and the trade that installs it. This helps answer project engineers’ critical questions: not “is there a door here?” but “does this door create a problem down the line?”

In construction, that shift matters because the cost of a problem compounds with time. “A conflict caught in design is relatively low cost to address,” Buchner said, “whereas the same problem caught in the field might cost tens of thousands of dollars.”

At a high level, the system identifies the document type and begins extracting information based on content — drawings, schedules, paragraph text. This data is then transformed and augmented in the platform, which triggers agentic workflows including knowledge graph relationships and end-user workflows.

For instance, an agent might review an architectural bulletin and produce a visual overlay comparing an older version and a newer version, flagging additions and removals, then generate written narratives describing what those changes mean in plain terms. This helps users understand what’s changed and coordinate with trade partners on updated pricing and change orders.

The Scale of Construction’s Data Problem

Construction workflows are “ripe with implicit assumptions and connections between data in its myriad of sources,” Buchner said. The amount of unstructured data is “humanly impossible” to process or make sense of manually.

Buchner estimated the average high-rise building generates about 3.6 million pages of corresponding documentation. “If you print it into a stack of papers, it would be as high as the building itself.”

All three layers of Trunk Tools’ stack — perception, semantic, LLM — are trained on “very specific datasets” from customers with explicit permissions and auto-labeling controls, Kapoor explained. Customers who don’t want Trunk Tools training on their data can opt out.

Data is deidentified and aggregated, and Trunk Tools also collects additional labeled data through other pipelines such as 3D building information modeling (BIM).

The company says it only ships agents that achieve around 95% accuracy. The team maintains continuous evaluation pipelines based on ground truth data from customers and domain experts, and also employs an LLM-as-a-judge model.

“This notion of an LLM as a judge is to score how well you’re doing, both subjectively as well as objectively,” Kapoor said. Objectivity can be a straightforward right or wrong, but subjectivity requires more nuance. When creating an email, narrative, or explanation, an LLM-as-a-judge framework can produce a composite score — a numerical value that aggregates different metrics and tests a model’s performance or risk.

Latency presents ongoing challenges, Buchner noted; any time the reasoning capacity of underlying models increases, the risk of latency increases as well. Trunk Tools maintains a set of evaluation criteria to objectively measure latency whenever changes are made to underlying infrastructure, agents, and API calls.

“Before we release to customers, we ensure marginal changes to the end-user experience are well worth the performance enhancements,” Buchner said.

From 60 Days to 10: The Measurable Payoff

Trunk Tools’ platform powers seven AI agents purpose-built for construction, covering tasks such as analyzing request for information (RFI) responses, overviewing bids, and reviewing drawings and submittals.

The submittal agent, for instance, flags missing, conflicting, or noncompliant information in product specs and RFIs. While it’s an essential step in the construction process, “it’s a super annoying workflow,” Buchner said, because human reviewers must compare documents “with a bunch of other parts of documents.”

The agent completes this work in seconds. Trunk Tools says it has reduced submittal cycles from 50–60 days to 10, “which has massive schedule and financial implications.”

The company’s agents now communicate directly with each other, which Buchner called “quite exciting.” One agent will review an architectural drawing for accuracy, then autonomously hand it off to an RFI agent to ask follow-up questions. “If the drawings have problems, the RFI agent is taking over and is actively reaching out for clarification,” she explained.

Trunk Tools says its customers report savings of 20 to 40 minutes per field question. Users in the field know better than anyone how much of a “time suck” it is to travel back to office trailers, dig through project documents in scattered systems or printed PDFs, reconcile discrepancies, and return to coordinate with trade partners.

The company reports the following additional outcomes from customers:

  • Average 8-minute time savings for single-document retrieval (status checks, location lookups, quantity queries)
  • Average 20-minute time savings for standard referencing (cross-referencing 2–3 spec sections to form an answer)
  • Average 40-minute time savings for multi-document research (listing and filtering queries, mapping relationships, analyzing RFIs and submittals across 4–6 documents)
  • Average 75-minute time savings for complex tasks (creating RFIs and other communication materials, deep cross-referencing across documents, change tracking)

In one instance, the drawing review agent flagged that a structural beam had been moved up 8.5 inches without being documented by the architect. Had the change gone undetected, the project manager would likely have had to strip out and reinstall the correct beam — adding $10,000 or more to the budget and causing schedule delays.

Buchner also cited additional examples: an agent flagged $60,000 in exaggerated pricing with no justification from landscaping subcontractors; identified a fireplace that needed to be sealed prior to drywall installation, saving around $100,000 in labor, materials, and delays; and called out that an electric door required a panel that wasn’t included in electrical drawings.

Learnings for Other Industries

Trunk Tools’ approach to building agents is applicable to any vertical working with high volumes of unstructured, industry-specific data. Builders working in specific verticals must first understand the data challenges their end users face, then build technical infrastructure capable of transforming that unstructured data into something an LLM can traverse and understand, Buchner said.

Only then, she argues, can teams deploy agents that are precise enough to be trusted with consequential decisions — and fast enough to change how work actually gets done.