ATS Software logo
Case Study

ATS: Turning Construction Specs and Drawings into Quote-Ready Product Data with AI

B2B
AI
SaaS
Construction Tech
Construction Tech
SaaS
Construction Tech
Document Intelligence
SaaS
Document Intelligence
SaaS
Construction Tech
Document Intelligence
Construction Tech
Document Intelligence
ATS Software logo
Case Study

ATS: Turning Construction Specs and Drawings into Quote-Ready Product Data with AI

B2B
AI
SaaS
Construction Tech
Document Intelligence

Overview

Allied Technical Solutions (ATS) builds software for the commercial construction industry. Its spec-to-quote product, Quoti, helps teams get from a project's specifications and drawings to a quote. ATS partnered with Crowdlinker to build the AI service underneath Quoti: a production-grade microservice that reads construction PDFs and returns the products they call for as structured data. It is live with ATS customers today.

Stage

Scale-up

Industry

Construction Technology

Deliverables

AI Proof of Concept, Document Extraction Microservice, API

80%

F1 score on written specifications

87%

F1 score on drawings

1 min

Target to process a 100-page specification
Six-step diagram of the extraction pipeline, from PDF upload to structured JSON

The Challenge

Before anyone can quote a commercial construction job, someone has to read the documents. Written specifications are long, and drawings carry product schedules, tags and callouts inside tables and diagrams. Finding every product, its manufacturer, its model number and the right CSI MasterFormat division is slow manual work, and a missed item affects the quote. ATS wanted to automate that first pass so its users could start from a product list instead of a stack of PDFs.

System architecture board for the document extraction service

Pain Points

Construction documents are not written for machines. A single upload can mix dense text, multi-column tables, scanned pages and drawings where the information that matters sits inside a diagram. General-purpose OCR and off-the-shelf LLM prompts each handled part of the problem and failed on the rest.

The bar was explicit. ATS needed accuracy it could measure, so the service was benchmarked on F1 score against labeled ground-truth files, with targets of 80% for written specifications and 87% for drawings. It had to be fast enough to sit inside a product workflow, with targets of about one minute for a 100-page specification and two minutes for a 20-page drawing set, and it had to return clean JSON that ATS's own front end could present.

Process and
Solution

We began with a proof of concept to test whether extraction was feasible at the accuracy ATS needed, then moved into a phased build. The service is a NestJS microservice that accepts batches of PDFs, queues them and processes them asynchronously. Each file is routed by type. Written specifications are converted to structured text and passed to a large language model for product extraction. Drawings go through a document AI pipeline tuned for diagrams. Scanned pages go through OCR first.

Reaching production accuracy was an evaluation problem as much as an engineering one. We measured every change against labeled ground-truth files and compared OCR engines, layout parsers, language models and prompt strategies head to head: Google Document AI, Azure Document Intelligence, PaddleOCR, PaddleOCR-VL, Docling, OCRFlux, MinerU, LandingAI, Gemini 2.5 Pro and Claude Sonnet. Computer-vision preprocessing crops each PDF to the pages and regions that matter before extraction. We also assessed fine-tuning and retrieval-augmented approaches and costed each one before recommending a path.

The second phase made the output easier to trust and act on. Every extracted product carries its page number and bounding-box coordinates, so ATS's interface can jump to the exact place in the document and highlight it. A feedback loop captures user corrections on the extracted product list and feeds them into post-processing and prompt optimization, alongside explicit rules that reduce hallucinated products.

Because accuracy depends on the quality of the answer key, we also audited the ground-truth data itself and reported inconsistencies back to ATS, so both teams were measuring against the same standard.

The OCR engines, language models and approaches benchmarked, with final F1 scores of 80% and 87%

Tools &
Technology

Node.js
NestJS
Google Document AI
Gemini 2.5 Pro
Claude Sonnet
Docling
PaddleOCR
LandingAI ADE
Azure Document Intelligence
YOLO
BullMQ
Redis
MySQL
AWS S3
Google Cloud
Labelbox

Outcome

After multiple iterations and benchmark runs, the service reached the contract targets: an F1 score of 80% on written specifications and 87% on drawings. Quoti is live with ATS customers today. PDFs go in, and a structured list of products comes back with brand, category, model number, tag, CSI division and the location of each item in the source document.

Impact

Work that used to start with a person reading every page now starts with a product list that points back to its source. The benchmark that proved the targets stays in place, so ATS can test new models and parsers as they are released and know whether they are better.

“I like those numbers. It gave me such a good feeling. All we care about is the accuracy going up, and having a full pipeline that keeps improving as we give feedback.”

News & Media

This is some text inside of a div block.
This is some text inside of a div block.
This is some text inside of a div block.
This is some text inside of a div block.
This is some text inside of a div block.
This is some text inside of a div block.

Read more
Case studies

Pippen: Reducing the Administrative Burden of Ontario-based Family Doctors Through AI
Abunda: Reshaping the Concept of Homeownership
The banfield.com homepage on desktop beside the Banfield Shop homepage on a phone
Banfield Pet Hospital: Rebuilding the Digital Front Door for 1,000+ Veterinary Hospitals
GET IN TOUCH
GET IN TOUCH

Want to learn more?

Let’s start collaborating on your most complex business problems, today.