OneDroid Argus

Case studies

What happened when
we ran it.

Each study says what was tested and how, what was found, and what the test could not see. The limits are part of the result, so they are in the text and not in a footnote. Most studies come in two versions with the same facts: the test page for engineers, and a blog post for leaders and product owners. The newest study, three ways to test code you did not write, has the test page only.

OneDroid · experiment

Two AI models, 86 checks, and 4 reported differences neither tested

Claude and Codex each wrote checks of a decades-old Fortran library against its user guide, reviewed each other's drafts, and OneDroid Argus sealed and ran both sets. All 86 held and 84 were proven able to fail, yet neither set tested the 4 differences an earlier study had reported.

26 to 27 Oct 2026 · 86 checks · 2 models · 1 run each

OneDroid · experiment

Three ways to test code you did not write

A long-lived scientific program nobody on our team wrote, tested three ways without reading its source first: against its manual, against an earlier release, and an AI rewrite against the original. What each comparison found, and what it does not show.

Three comparisons · a written prediction before every run · no names

OneDroid Argus · one system

Does the code do what its user guide says? 100 sealed checks against a decades-old Fortran library

A decades-old numerical Fortran library held to its own user guide: 100 checks, each quoting the sentence it tests, sealed before the run. 91 held and 9 failed, the checks that depend on the changed constants were shown able to fail, and the page lists what the result does not prove.

16 October 2026 · 100 checks · one certified run

OneDroid · experiment

Same modernization, three setups: what the tester checks decides whether it helps

A decades-old Fortran library ported to Go by Claude Code alone, with a tester checking the manual, and with a tester checking equivalence with the original, all judged on 109 hidden checks. What the tester checked decided whether it helped or hurt.

17 October 2026 · 109 hidden checks · 3 runs per setup

OneDroid · experiment

Claude Code alone or with an independent tester: the same quality, and where the money went

The same feature ticket, built by Claude Code testing itself and by Claude Code with OneDroid Argus as an independent tester, judged on 13 checks neither had seen. The same quality, a builder at half the cost, and a whole that cost 41% more.

16 October 2026 · 13 hidden checks · 3 runs per setup

OneDroid Argus · one system

Does the guardrail hold on every path? Seven sealed checks against a FINOS CALM demo

The FINOS CALM trades demo, an AI agent's tool server in front of trading data, against seven checks sealed before the run: does the running system match its architecture, and does the guardrail hold on every path. Two checks failed, and the page says which of them is about our own cluster.

7 October 2026 · 7 checks · two certified runs the same day

For leaders and product owners: the business view of the same study.

OneDroid Argus · compare

Six differences between two releases of a ticketing system

OTRS Community Edition 6.0.30 against its fork Znuny 7.3.7, one sealed set of checks. Six differences between the two releases, what stayed the same, and a list of what one REST web service, four pages and one laptop cannot tell you.

5 and 6 October 2026 · 26 checks · three runs per system

For leaders and product owners: the business view of the same study. The video: 56 seconds on YouTube.

The studies so far. OneDroid Argus is in early use, including compare.