That's ArchiveLM. And when it can't read a page, it tells you so. It never makes something up.
Contamination, asbestos, title and other long-tail matters turn on decades-old company files, permits, ledgers, letters and local newspapers. E-discovery platforms are built for modern email — typed 1950s memos, handwritten ledgers and foreign-language records still get read by hand, at hundreds of hours a matter. Miss the one page that shows who knew what, and when, and the case turns on it.
When did the plant first receive complaints about the drainage pond?
Every document that mentions the Ridgeway parcel before 1975, oldest first.
Which people and companies appear alongside the 1962 sale?
Your team uploads scans, PDFs or photos of the documents you hold or obtain. Nothing is supplied by us.
AI reads every page — typed, printed or handwritten, in any language. Unreadable pages are flagged, not guessed.
Each page is indexed by meaning, not just keywords, along with the people, places, companies and dates it mentions.
Plain-English questions get answers that cite the exact source page, so every fact can be checked in one click.
Weeks of reading become minutes of searching — find "who knew what, and when" without hundreds of hours of manual review
Nothing invented: every answer is tied to a page you can open, and an unreadable page is disclosed, not papered over
The records other tools skip — e-discovery platforms are built for modern email, not old, handwritten or foreign-language files
Timelines and cited findings feed straight into memos, expert reports and deposition preparation
Each account's documents sit in an isolated database and storage bucket, enforced by row-level security — no other customer can see or search them.
Encrypted in transit (TLS 1.2+) and encrypted at rest.
Your documents are never used to train AI models — we instruct our providers not to train on your data.
Documents are stored in the United States.
Deleted on request, and removed within 30 days of an account closing.
A published list of every subprocessor that touches your data, with its role and location (legal.archivelm.com/legal/subprocessors on the main site).
We are not yet SOC 2 certified. We'll share our security overview and subprocessor list on request.
| Plan | What's included | Price |
|---|---|---|
| One-off | ||
| Pilot | Up to 50 of your own pages, your hardest ones, processed and walked through with you | Free |
| Matter setup | We load and process up to 5,000 typed or printed pages (or up to 1,500 handwritten or foreign-language pages), check them with your team and run a 30-minute walkthrough | $2,500 per matter |
| Additional pages | Typed or printed / handwritten or foreign-language | $0.40 / $1.50 per page |
| Ongoing | ||
| Active matter | Up to 10 users on the matter team, all research tools, exports and support. Pause or close any time | $1,250/month |
| Additional users | Beyond 10 on a matter | $99/user/month |
| Firm plan | Up to five active matters and 50 users. Matter setups and extra pages billed as above | $4,500/month |
| Security | ||
| Standard security | Encryption, account isolation, no AI training on your documents, deletion on request | Included |
| Private environment | A dedicated database and storage on your own web address, shared with no other customer. (Isolation, not a compliance certification.) | $7,500 setup + $1,500/month |
For perspective: historians and paralegals reviewing archival records by hand typically bill several hundred dollars an hour, and a document-heavy matter can run to a hundred hours or more. A typical six-month matter on ArchiveLM (setup plus six months) is about $10,000.
Legal pricing above is pending verification and may change.
No. There's no legal hold, Bates numbering or privilege review here. ArchiveLM is the research layer for the historical, handwritten and foreign-language material that modern e-discovery tools weren't built to read — it runs before or alongside discovery, not instead of it.
Yes — that's exactly what matter setup is for. We load and process up to 5,000 pages for that matter, verify them with your team, and bill per matter. The firm plan is only worth it once you have several active matters running at once.
It's flagged rather than guessed. A page that comes back low-confidence or unreadable is marked for review instead of producing a confident-sounding answer that isn't actually on the page — that's the difference between a citation you can rely on and one you can't.
No. We instruct our AI providers not to train on your data, and each client's documents are stored in an isolated account that no other customer can see or search.
Yes — a private environment gives you your own isolated database and storage, on your own web address, shared with no other customer. It's a $7,500 setup plus $1,500/month, on top of standard security.
Send up to 50 pages — the faded, handwritten or foreign-language ones from a real or closed matter — and we'll show you exactly what ArchiveLM finds and where it can't read a page. No cost, no commitment.
ArchiveLM is in private beta. We review each request and typically respond within 1–3 business days.