Does Tessary run triage automatically on every finding, or do I have to trigger it myself?

Not by default. When a finding opens, Tessary’s triage step runs only when someone presses to analyze it, so a fresh finding sits waiting for that click. Running triage automatically on every finding the moment it opens, with no one pressing anything, is a setting an org can turn on instead.

Either way triage does the same thing: it checks the finding’s claim against the evidence and rules it sound, an artifact of the detector rather than the agent, or unclear. What changes is only who starts that check. Off, a person decides which findings are worth spending a look on. On, every finding gets one automatically, which is worth it once you trust the detectors firing on your traces enough to want every one of them checked without waiting on a person to get to it.

A frustration finding, like a high-confidence secret leak, never waits in that queue: it is ruled when it is filed and opens its case without triage, whichever way the setting is.

keep reading

More on this.

Two ways to run Tessary.

Tessary is an open-source agent reliability platform. Cloud and self-hosted run the same workflow on the OpenTelemetry traces your agent already emits.

Tessary Cloud

We host it for you. Send your first trace with nothing to deploy and no model key.

what's includedper organization
traces
10,000 per calendar month
stored trace data
1 GB
retention
30 days
model credit
$10, one-time, for triage and root-cause analysis
credit card
not required

Self-hosted Tessary

Run the open-source code on your own infrastructure with one command. Add your own model key for triage and root-cause analysis.

Self-host Tessary for me by following https://github.com/tessaryai/tessary/blob/main/setup.md

docker compose -f oci://docker.io/tessaryai/tessary:compose up -d -y