A working slice of what I read Maxify to be, built on the workflow Mao Ting named in her hiring post and run on the live Software Engineer vacancy. The model extracts evidence from each application. A deterministic gate verifies spans, redacts protected attributes and routes. Every advance lands in a human queue. Eight runs are recorded below; one of them is my own application to this role.
Each file is served read-only and linked here. Every gate rule cites a published source below; founder-published figures are cited as published, and this demo does not audit them.
The workflow runs four stages with one model call; the expensive step is fenced on both sides by deterministic checks.
Duplicate hash, injection scan, subject format and protected-attribute redaction all run before the model; three of the eight recorded runs end here at zero token cost.
Structures every claimed system with a verbatim quote and any artifact URL. Instructed to extract boldly and judge nothing; the application text is data, never instructions.
Verifies each quote is a real span of the source, clears invented artifacts, flags metrics that carry no evidence as written screen questions.
A pure function of gate outcomes. The model never scores, ranks or compares candidates; a human makes every decision.
A scanner that blocks a candidate for managing system prompts, or a redactor that eats "single sign-on", fails real applicants quietly. Every contextual guard here earns published negative cases in the eval table.
This section renders only from saved transcripts and the eval report; nothing in it is hand-written. Fixtures fx-01 to fx-07 are synthetic and labeled. Run 08 is my real application, processed with no special treatment. Each sheet links its raw transcript.
This is the same pipeline, streamed. The lane opens on a capped budget; adversarial pastes are contained at intake for free. Load a sample or write your own.