What is agent reliability?

Agent reliability is how consistently an agent’s production behavior matches what it was built to do, measured across the inputs it actually receives and over time. It’s a property of the whole system, not just the model: behavior depends on the model, the prompts, the tools it can call, and the data it reads, and a change to any one of those shifts it. Agents are also nondeterministic, so the same input can produce different outputs on different runs. That means reliability isn’t a pass or fail on one run; it’s a statement about the distribution of behavior across many runs. A reliable agent keeps that distribution stable as everything around it changes. An unreliable one drifts, usually quietly: it keeps producing fluent text and completed tool calls, so a wrong decision looks the same on the surface as a right one.

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