# OCR vs. LLM Document Understanding > OCR converts scanned construction documents into text. LLM document understanding reads that text, or the page image itself, and interprets its meaning. Precon tools often use both: OCR handles the pixels and the language model interprets the content. - Stages: Estimating, Preconstruction, Closeout - Concepts: Document Extraction, Computer Vision - Published: 2026-08-28 - Canonical: https://buildr.com/library/ocr-vs-llm-document-understanding ## Why it matters in construction A GC's document pile is not uniform. Some sub proposals are clean PDFs exported from an estimating package. Others are a photo of a printed quote with a signature scrawled across the bottom. Closeout brings scanned O&M manuals, warranty letters, and inspection cards that were never digital to begin with. Knowing what OCR does versus what a language model does tells you where AI will be reliable and where it needs a second look. Vendors blur the two, and that is how a bad scan turns into a trusted number. ## How it works OCR, or optical character recognition, looks at an image and outputs characters. It answers the question "what letters and numbers are on this page." OCR can also output coordinates for each word, which helps preserve table structure. It does not know that "$48,500" is a total or that "excl. permits" is an exclusion. LLM document understanding takes text from OCR or a native PDF and answers "what does this mean." It can identify a paragraph as a qualification, a line as an alternate instead of base bid, and two differently worded descriptions as the same scope. A typical pipeline: 1. If the file has a text layer, use it directly. If not, run OCR. 2. Pass the text, ideally with layout information, to the language model along with instructions about what to pull out. 3. Have the model return structured fields with page references. 4. Route low-confidence pages, usually the worst scans, to a person. Newer multimodal models can skip step one and read the image directly. That can work for a one-page quote. For a 300-page spec book, an OCR-first process may be more practical and gives the team searchable text to review. ## Example in practice Suppose a commercial GC is closing out a 4-story medical office building. The closeout package contains 212 documents: about 140 native PDFs from subs, 60 scanned inspection and warranty records, and a dozen phone photos of equipment nameplates. OCR handles the scans and photos, but two faded HVAC startup reports produce unreliable text. The language model then reads the available material and builds a warranty schedule with the equipment, sub, start date, term, and contact. It flags the two faded reports as uncertain, and the project engineer checks those source documents by hand. ## Go deeper - [AI for Estimators: 5 Practical Uses that Work Today (Not Someday)](/blog/ai-for-construction-estimators.md) - [Successful Project Closeout: The Comprehensive Guide](/blog/project-closeout.md) ## How Buildr applies this Buildr reads typed and scanned sub proposals alike and extracts the scope, pricing, and exclusions an estimator needs for leveling. See [Buildr Estimating](/estimating). ## Related terms - [Structured Data Extraction](/library/structured-data-extraction.md): Structured data extraction uses AI to turn unstructured construction documents, such as sub proposals, RFPs, and specs, into typed fields like line items, prices, exclusions, and dates that can be sorted, compared, and loaded into an estimate or CRM. - [Computer Vision](/library/computer-vision.md): Computer vision is AI that interprets images and video. In construction, it can read drawings for takeoff, identify symbols and rooms on plans, compare jobsite photos with progress plans, and check PPE compliance in camera feeds. - [AI Takeoff](/library/ai-takeoff.md): AI takeoff uses computer vision and language models to read construction drawings, identify building elements, and count or measure quantities so estimators can price a project without tracing every sheet by hand. - [AI Plan and Spec Review](/library/ai-plan-and-spec-review.md): AI plan and spec review uses language models to compare a construction drawing set with its specification book. It flags conflicts, missing information, and risk items for the preconstruction team to review before pricing. - [AI Project Closeout](/library/ai-project-closeout.md): AI project closeout uses document extraction and agents to collect, classify, and verify the O&M manuals, warranties, as-builts, and lien waivers required at turnover. It tracks outstanding items by subcontractor. ## FAQ ### Is OCR obsolete now that language models can read images? Not entirely. Multimodal models can read a page image directly, but a dedicated OCR pass can be more practical for dense tables and small fonts. Many production systems run OCR first and use the model on the result. ### Which documents give AI the most trouble? Faxed or photographed bids, handwritten markups, low-resolution scans of older drawings, and multi-column spec pages where the reading order is unclear. These are the cases where a human should check the output. ### Does the model see the layout or just the words? It depends on the pipeline. Text-only OCR loses layout, which matters for tables. Better systems preserve bounding boxes or send the page image alongside the text so the model knows which price belongs to which row.