What happens after Tessary confirms a case?

The case reaches a person, and root-cause analysis is theirs to start on it. Starting one opens an isolated investigation against exactly that case: the trace evidence behind the finding, your repo when one is connected, and nothing carried over from any other case. It works backward through the failing traces, testing explanations and ruling out the ones that don’t hold, then writes a report: the hypotheses it can support with evidence, the checks it ran and discarded, and the files it points to. Where a cause is grounded enough to act on, the report names it along with the files involved. Where nothing clears that bar, the report says so instead of guessing. It runs on cases, not on every finding Tessary opens, and every run is a fresh look, with nothing inferred from a different case.

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