all answers

Tessary

Tessary cases

A case is Tessary's unit of investigation. Classifiers produce findings, triage runs on those findings, and the ones ruled real issues turn into cases, each with a lifecycle to open, work, and resolve.

A case contains what moved, by how much, and since when, in the detector's own numbers. It carries the triage ruling in prose, with a confidence and its citations, and says which lane ruled it: from trace evidence alone, or grounded in the repository, where the citations are file paths you can open. It also holds before and after exemplars, real traces from each side of the shift, so you can see what the numbers look like in practice.

From a case, Tessary runs root cause analysis: an agentic session in a fresh E2B microVM over the failing cohort, with the trace evidence, a dossier, and the connected repo. It returns grounded hypotheses plus the checks it ruled out, and cites the files involved.

8 questions

Answered, plainly.

Does a Tessary alert get dropped if a case opens during quiet hours?No. Tessary holds the notification and delivers it once quiet hours end, timestamped with when the case actually opened.answer →What happens after the same failure keeps recurring?A fast recurrence just updates the same open case; only after the detector's quiet window passes does a return reopen a closed one.answer →What is a case?A case is a confirmed finding: one record with the triage ruling, its evidence, and before-and-after examples, opened once triage rules a finding real.answer →When does a finding become a confirmed problem?A finding becomes a case the moment triage rules the claim sound or a person opens it by hand. A frustration finding or a high-confidence secret leak is ruled when filed.answer →Where can agent monitoring alerts be routed?Cases reach you over a webhook, PagerDuty, Sentry, or Linear, set up once in Settings → Notifications.answer →Why do a hundred failing traces need to become one thing to look at?Every classifier writes one finding per cause, keyed on that cause, so repeat firings attach to the same finding and one case wraps it.answer →Does Tessary run triage automatically on every finding, or do I have to trigger it myself?Not by default. Triage runs when someone presses to analyze a finding; running it automatically on every finding that opens is a setting an org can turn on.answer →Does turning off a classifier close the cases it already opened?No. The case stays open as a record of what happened; turning a classifier off only stops new findings and alerts, not the case's own state.answer →

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