Replay an incident you already solved
Any vendor can quote an accuracy number about themselves. This is the other thing: bring one failure you already debugged, tell us what it turned out to be, and watch the engine work the log without that answer. Then read the score.
Your answer is sealed first
It is hashed and the hash is handed to you before the log field unlocks.
Only the log is sent
The diagnosis request carries your log text and nothing else. A test in our repo fails the build if that ever changes.
You can recompute it
The receipt publishes the salt, so the hash is yours to verify.
What a miss looks like
A wrong answer is recorded as wrong, in those words. If the engine declines to name a cause because the log does not support one, that is reported as declining, not quietly counted as a win. And if you did not tell us how long your investigation took, no time saving is shown at all. We would rather lose the demo than publish a number you can take apart.
Step 1. Record what the cause actually was
We hash this and hand you the hash before you paste anything. That is what proves the engine could not have seen it.
Leave it blank and we will not show a time saving at all. We do not substitute an average for a number you did not give us.
Step 2. Paste the redacted log
Only this text reaches the engine. Redact whatever you need to; hostnames and paths are not what the diagnosis turns on.
One replay is a demonstration, not a measurement
A single scored incident tells you how we did on that incident. Our published accuracy methodology, its sample sizes, and what it does not yet prove are on the evidence and evaluation status page, and the reproducible benchmark corpus is at the benchmark page.
See what a live cluster adds to this