We're working with a small number of safety and certification teams. If you'd like to see Adducia on your own analysis, or just want to talk about the problem, reach out. A real person will read it.
Reach us
The fastest way to reach us. Click the address once to select it, or open a short template in your email app. A couple of lines about your team and what you work on is plenty.
Founder. Connect or send a message there if that's easier than email. We're in the United States and can meet on a call wherever you are.
What happens next
FAQ
No. The AI does the reading and the reviewing, and code checks its work. Each item the AI reads keeps the exact quote it came from, and code checks that quote against your document. The AI flags low-confidence reads for an engineer to review. Code checks each review finding the same way. Its quote must be in the document it cites, and its IDs must be where it says. No finding goes into a report until an engineer confirms it. Code also checks every artifact ID in an answer against the graph of your documents. What you keep is the record. The connected graph, the checked findings, and every engineer's decision stay with you across revisions.
In a pilot, your documents stay in a private workspace on a server we run, under NDA. We use them only to build your graph and answer your questions, and we delete them when the pilot ends. Export-controlled or classified material (ITAR, EAR, CUI) never comes to us. For that, Adducia runs in your own cloud tenant or on your own hardware. Anything public, including demos and this site, uses synthetic data that is clearly labeled.
No. Your documents are used to build your graph and answer your team's questions, not to train models.
It reads FMEAs and FMECAs, including multi-tab Excel workbooks with their severity, occurrence, and detection scales. It also reads FHAs, hazard logs, fault trees, reliability block diagrams, requirements, and V&V matrices. Files can be XLSX, CSV, ReqIF (the export format of DOORS and Jama), PDF, or pasted text. It reads the tables and figures too, where the real content often is. In workbooks and exports, the AI works out what each column means, and code reads every row.
Yes. Load a baseline and a newer revision of the same analysis. Adducia reports what appeared, what disappeared, and what changed value, such as a severity that moved, a rate that changed, or a status that closed. Code computes the comparison from the two reads. A renamed or renumbered item shows as removed plus added, and the tool doesn't guess.
Neither. It sits alongside your requirements and analysis tools and hands the engineer organized, source-linked information. It flags low-confidence reads for review, and the safety call always stays with the engineer.
For a pilot, you need a browser and a signed NDA. You get a private workspace with the sample program one click away, and you bring your own documents. There's no account to create, no card to enter, and nothing to spend. If your program data is export-controlled or classified, Adducia runs in your own cloud tenant or on your own hardware instead. That's how your export control team would want it anyway.
The pilot is free. It's forty-five days on your own work, with nothing to install, no account to create, and nothing to spend. After that, Adducia is licensed per program, each year. A program is one system's safety documents, and every engineer working on it is covered. A team with several programs licenses each one. There's no rate card, because the price follows the size of the program. A first call helps work that out.
We're an early-stage company that works closely with a small number of teams. Right now, that means free forty-five-day design partnerships. You use Adducia on real work in a private workspace under NDA. We talk every couple of weeks, and your team's needs shape what we build. The first few teams set the direction. Reach out, and we'll see if it fits.