Does turning off a classifier close the cases it already opened?

No. A case a classifier already opened stays open, because closing it would read as the regression having resolved itself when nothing actually changed except your settings.

Turning a classifier off suppresses it going forward: it stops writing new findings, stops paging anyone through alert rules, and its detail pages become unreachable while it’s off. What it already found stays visible in triage as history, and any case tied to it keeps its own state rather than getting silently marked resolved. Turn the classifier back on and its findings and cases pick up again where they left off, since nothing about the case’s own record was touched while it was off.

The distinction that matters: hiding a classifier changes who gets notified going forward, not what it already found.

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