Enterprise RAG: AI search over your documents, cited to the page
Corpus is retrieval-augmented generation (RAG) for your organization’s documents. It searches your files by exact words and by meaning, writes a short answer, and cites the document and page so you can check it. Files a role cannot open are removed before search runs. If nothing on file supports an answer, it is designed to say “Nothing on file.”
Answers people can check, from files they may see.
A common place RAG pilots stall: the answers sound right, but nobody can check them, and the index can see files some people should not.
What teams often say:
- “It answered, but I couldn’t tell which document it came from.”
- “It quoted a clause that isn’t in the contract.”
- “The pilot indexed everything, including the HR folders.”
- Scanned PDFs, old versions and folder permissions are where RAG projects often get hard.
How Corpus answers
- Current Hybrid search: each question is matched against your files by exact words and by meaning, so a clause number and a question in plain words both find the passage.
- Current Citations: the answer is written from the passages it found and cites the document and page. Open a citation and the page opens with the passage highlighted.
- Current Refusal: if nothing on file supports an answer, it is designed to say “Nothing on file” instead of guessing.
- Current Access by role: files a role cannot open are removed before search runs, so answers never draw on them. Set up for you Tying roles to your named people is part of full-deployment setup.
Example questions, not results
Written for this page; the demo’s own files are engineering documents.
- Which reports mention this site, and what did each one recommend?
- What notice period does this agreement require for termination?
- Where in our manual is the approval process for a change order?
- Which version of this document did we send, and what changed after it?
Corpus finds and cites. People decide.
- A person reads the cited page before relying on an answer.
- Whether the cited document is the latest, final version.
- Who may see which files. Corpus removes files a role cannot open, and your people decide who gets which role.
- An empty result. “Nothing on file” does not prove that no such record exists.
Corpus finds and cites. It does not make decisions: your people read the cited pages and decide.
A free call, then a pilot on your own files.
Start with a free 30-minute call. Then a $5,000 fixed-price pilot on a copy of one real project’s files. How the pilot works.
See how citations and refusals work.
Try page citations, “Nothing on file” and roles on a sample engineering firm’s files.
→ Corpus for engineering firms → 7 RAG refusals that were pipeline bugs → Private AI → Corpus by industryFrequently asked questions
What is enterprise RAG?
Retrieval-augmented generation over an organization’s own documents. The system first retrieves the passages that match a question, then writes an answer from those passages. Corpus cites the document and page for each answer.
How does Corpus keep answers tied to the files?
Each answer is written from retrieved passages and cites them. If nothing on file supports an answer, Corpus is designed to say “Nothing on file” instead of guessing. A person still reads the cited page.
Does it read scanned PDFs?
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.
Where does it run?
Set up for you on servers you choose, your own or a cloud such as AWS, Azure or Google Cloud, with an open-weight model and no public AI API. We don't have a SOC 2 report. The Private AI page covers how a private deployment is set up.
Is there a demo?
Yes. The live demo is built for engineering firms: a fictional sample firm with real public records from US public agencies. Its search also reaches a public-domain collection of U.S. court opinions. There is no demo built on another industry’s files. A pilot runs Corpus on a copy of your own files.
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.