Corpus by industry: AI search for document-heavy work
Corpus is retrieval-augmented generation (RAG) over your own files. You ask in plain words; it searches your documents and answers with a citation to the document and page, or says “Nothing on file.” Engineering firms are our first, worked-out example. It fits any organization with a lot of documents to search. We have no customers in these other industries yet.
Pick the files you search most.
Engineering firms
The first, worked-out example: bid/no-go, SOQ drafts and fee builds from your past projects, with page citations to check.
Law firms
Search across past matters, contracts and briefs, cited to the page; not legal advice, not e-discovery.
Insurance
Search across policy forms, claims files and underwriting guidelines, cited to the page; people decide coverage.
CPA and consulting firms
Search across engagement files, workpapers and past proposals, cited to the page; not tax or accounting advice.
Property management
Search across leases, management agreements, governing documents and minutes, cited to the page.
Public agencies and utilities
Search across plans, permits, standards, RFPs and records, cited to the page; no published price.
Architecture and construction
Search across specs, submittals, RFIs and past project files, cited to the page.
What Corpus does in any industry.
- We load a copy of your documents, saved as PDF. Corpus is retrieval-augmented generation (RAG): it answers from those files.
- Current You ask in plain words. Corpus searches by exact words and by meaning, then writes a short answer with citations to the document and page. Open a citation and the page opens with the passage highlighted, so you can check it.
- Current If nothing on file supports an answer, it is designed to say “Nothing on file” instead of guessing. An empty result does not prove that no such record exists.
- Current Access by role: files a role cannot open are removed before search runs, so answers never draw on them. In the demo, roles are illustrative and anyone can switch them. Set up for you Tying roles to your named people is part of full-deployment setup.
- Current Version history for drafts: each saved version shows who saved it, Compare shows what changed, and you can restore an earlier one. In the demo this covers fee, SOQ and contract drafts.
- Corpus reads PDF files, including scanned pages read by OCR. Set up for you OCR of your own scans is planned on the call and done during setup.
- Set up for you Corpus is cloud-agnostic: it runs on AWS, Azure, Google Cloud, or your own servers. It uses an open-weight model and no public AI API.
See how citations and refusals work.
The live demo is built for engineering firms: public engineering documents filed under fictional sample firms. Its search also reaches a public-domain collection of U.S. court opinions. There is no demo built on another industry’s files.
Frequently asked questions
Is Corpus only for engineering firms?
No. Corpus is retrieval-augmented generation (RAG) over your own files: it searches them, answers in plain words and cites the document and page. Engineering firms are our first, worked-out example. It fits any organization with a lot of documents to search.
Do you have customers in these industries?
Not yet. Corpus has no customers in these industries. Engineering firms are our first, worked-out example. The live demo is built for engineering firms: public engineering documents filed under fictional sample firms. Its search also reaches a public-domain collection of U.S. court opinions. There is no demo built on another industry’s files.
What does a pilot cost?
A $5,000 pilot on one real project or pursuit, after a free 30-minute call. Public agencies have no published price; the next step for them is the free call.
Have a folder full of questions?
Book a free 30-minute call. We talk about your files, the questions you need answered, and whether a pilot makes sense.