What is a Tessary classifier?

A classifier scores one trace for one property: a number and a confidence, not a verdict on whether the agent did its job. The drift checks judge a trace against a baseline learned from that call site’s own recent history rather than a fixed number, so what counts as unusual is specific to your agent.

What it produces is a finding, and a finding carries which classifier filed it, the subject it fired against (a call site’s baseline, a tool, a behavior profile), what moved, when the current spell started, and how many observations the claim rests on. Triage reads it from there.

The precision it buys costs recall, and that trade is set per classifier rather than once for all of them: one is tuned so a reviewer queue holds only real things at the cost of being incomplete, another the other way. False positives are the price on that side of it.

keep reading

More on this.

What's the difference between an LLM and a classifier?An LLM reasons over open text and answers almost anything; a classifier is trained to score one narrow property, cheaply enough to run on every trace.answer →Why do Tessary's classifiers produce false positives?Because each classifier scores one narrow property of a trace and fires on a threshold. A flag is not a verdict: a rising rate, triage, or both decide what is real.answer →Why does Tessary check every trace instead of sampling?Sampling measures how often something happens; it is a poor tool for catching something rare, and in a mature agent nearly everything left to catch is rare.answer →Everything on tessary classifiersThe definition, and every question answered under tessary classifiers.concept →

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
start for free

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