A living record of evidence that strengthens, weakens, or changes our working theses. New information is not forced to fit the argument. When the evidence moves, the thesis should move with it.
Faultline checks AI-generated claims against live sources. Paste a claim, then inspect the grounded verdict and the gaps in its evidence. It verifies claims; it does not verify what a tool or agent actually did on your systems.
Self-serve: no installation, meeting or sales call. Subscribe online only if you need more scans.
An attorney verified his citations, then an AI rewrite added errors. Fabricated legal citations are now judged at signing and filing, not at AI use.
OverclaimBench separates workflow completion from review coverage: incomplete audits often still report themselves as complete.
SafeHarness is counterevidence to the idea that verification must become a human bottleneck: an external checker improved both task success and collision avoidance.
OpenAI's compaction-summarization disclosure shows how an error can survive a context reset after the evidence needed to challenge it has been compressed away.