Our story
The same analyst workflow, over and over
While studying data analytics at Carnegie Mellon, our founder kept seeing the same pattern across every project — a bank-sponsored next-best-action system, internal tools, analytics engagements. The outputs differed, but the work was identical: translate a business question into the right data and definitions, clean and reconcile, run the right analysis, verify it, and present it in a form decision-makers could use.
Existing AI tools could help with isolated steps like writing SQL. But nothing existed that a company could trust to perform the complete analyst workflow inside its own walls — respecting permissions, computing with reliable tools, and connecting every conclusion to evidence.
AMOS is that missing operating layer. We are four technical founders who write every line of the product ourselves. In our first month we built a working Rust prototype that controls data access, executes and verifies analyses, preserves supporting evidence, and produces reviewable results — and pressure-tested the approach with nine data leaders, analysts, and technical experts alongside CMU faculty.
4
technical founders, all writing code
1 month
to a working verified-analysis prototype
9
data leaders and experts interviewed