AI search for public agency plans, permits and records
Corpus is AI search over your own plans, permits, standards, RFPs and records. Ask in plain words and get a short answer cited to the document and page, or “Nothing on file” when nothing supports one. Your staff decide what applies. There is no published price for agencies; the next step is a free 30-minute call.
The answer is on file. Finding it is the work.
A records request or a design question can mean pulling plan sets, permit files and old RFPs from several systems, many of them scans.
- “What did the permit for this crossing require for restoration?”
- “Which edition of our standard applied when this project was designed?”
- “What did we ask consultants for in the last on-call RFP?”
- Plans, permits, standards and contract records live across departments, drives and decades of scans.
Answers from your own files, cited to the page.
- We load a copy of your plan sets and record drawings, permits and their conditions, standards and specifications, RFPs and contract records, 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.
Example questions, not results
These questions are examples written for this page. They are not results: Corpus has no customers in this industry yet, and the live demo is built on engineering documents.
- What restoration conditions did the permit for this utility crossing set?
- What does our standard specification say about trench backfill compaction?
- What evaluation criteria did our last on-call engineering RFP use?
- Which project files mention the water main replacement on this street?
Corpus finds and cites. People decide.
- Staff confirm which edition of a standard governs. Corpus does not label current and superseded editions today.
- Whether a search found every record. An empty result does not prove that no such record exists.
- Public records and retention rules, which your records officer applies.
- Engineering and permit decisions, which stay with your qualified staff.
Corpus finds and cites. Your staff decide what applies, under your own procedures.
Start with a free 30-minute call.
- There is no published price for public agencies. The next step is a free 30-minute call.
- We tell you on the call whether we can work under your standard terms.
- Company data for procurement is on our government and prime contractors page.
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. It shows what works the same in any industry: page citations, “Nothing on file” and roles.
→ Corpus by industryFrequently asked questions
Is there a price for agencies?
There is no published price for public agencies. The next step is a free 30-minute call. We tell you on the call whether we can work under your standard terms.
Can it read our scanned records?
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.
Can it compare two editions of a standard?
Not yet. You can ask about each edition and open both citations, and your reviewer records which one governs. An answer that compares editions on its own is not built.
Do you have customers in this industry?
Not yet. Corpus has no customers in this industry. Engineering firms are our first, worked-out example, and the live demo uses fictional engineering firms.
Where do our files go?
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 nothing goes to a public AI API. In the pilot, your files are never used to train or fine-tune a model. In full deployment, fine-tuning on your files happens only if you agree in writing. We don't have a SOC 2 report, which is one reason you can choose your own servers.
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.