most auto-apply tools have a dirty secret: they only autofill the form. they drop your details in and stop. some press submit. almost none read the confirmation the applicant tracking system sends back afterward, which means they cannot actually tell a click from a landed application. so they show you "applied" and hope.
we read that confirmation. it is the whole point of what we build. and the side effect of reading it is that we have a status most tools do not: failed
. a column that says, out loud, this one did not go through.
having that column means we can be wrong out loud too. today we were.
our apply agent clicked submit on a real Greenhouse form. the form went through. then, about half a second later, a downstream network blip threw an error, and the old code took that to mean the whole run had failed. it stamped a real, registered application as failed
. a false negative on the one signal that matters most.
the fix (in submitter.ts
) is a gate we now call submitClickIssued
. once the agent has actually clicked submit, a later transport error can no longer produce a hard failed
. it resolves to requires_human_review
with a "likely landed, confirm this one" disposition instead. a blip after the click can no longer fake a failure. worst case, we ask you to double-check one, instead of lying to you in either direction.
it is not a glamorous ship. no new feature, no screenshot. but a tool that never fails is a tool that never tells you, and the boring reliability days are the actual product.
building this in public. no fabricated numbers, just the log.