Adducia

Contact

Get in touch.

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

Email
contact@adducia.com

The fastest way to reach us. The link starts a short template; a couple of lines about your team and what you work on is plenty.

LinkedIn
Rahul Soneji

Founder. Connect or message there if that's easier than email. Based in the United States; we can meet on a call wherever you are.

Please don't send controlled, export-restricted, or proprietary material by email. When we work together, your data stays in your own environment. See Trust & Security.

What happens next

No funnel. Three steps.

01 A reply within a day Your note lands with a person, not a queue. You'll hear back quickly, usually the same day.
02 A short call Thirty minutes on how your team works today: where the documents live, where the hours go, and whether this actually fits.
03 A live run on a document you bring Bring one sanitized or public document. We run Adducia on it while you watch, and you keep the findings. Controlled data stays in your environment, always.

FAQ

The questions engineers ask us first.

Is this just a wrapper around a chatbot?

No. Structured documents are extracted deterministically, row by row. Every artifact ID in an answer is validated against the graph built from your documents, quotes are verbatim and checked against the source, the one judgment step (how columns are read) is shown and correctable, and reports are computed with no AI in the pipeline at all. The model is the interface. The graph built from your documents is the truth.

Where does our data go?

It stays in your environment. Adducia is built to run where your controlled program data already lives. Anything public, including demos and this site, uses synthetic data that is clearly labeled as such.

Will our documents be used to train AI models?

No. Your documents are used to build your graph and answer your team's questions, not to train models.

What can it read?

FMEA and FMECA (including multi-tab Excel workbooks with their severity, occurrence, and detection rating scales), FHAs and hazard logs, fault trees, reliability block diagrams, requirements, and V&V matrices, as PDF, XLSX, CSV, or pasted text, including the tables and figures where the real content lives.

Can it compare two revisions of a document?

Yes. Load a baseline and a newer revision of the same analysis and Adducia reports what appeared, what disappeared, and what changed value, whether that is a severity that moved, a rate that was revised, or a status that closed. It also shows which findings are new or resolved since the baseline. The comparison is computed deterministically, and a renamed or renumbered item is honestly shown as removed plus added rather than guessed at.

Does it replace our existing tools or our judgment?

Neither. It sits alongside your requirements and analysis tools and hands the engineer organized, source-linked information. Low-confidence reads are flagged for review, and the safety call always stays with the engineer.

What does working with you look like right now?

We're an early-stage company working closely with a small number of teams. The usual shape is a scoped pilot on your kind of documents, built around one live question your team is actually working. Reach out and we'll shape it together.