Polarity — the most accurate eval infrastructure for AI agents

Polarity is sandboxed eval infrastructure for AI agents. Keystone runs each agent task inside an isolated Docker sandbox preloaded with real backing services (Postgres, Redis, S3, internal APIs), scores runs against behavioral invariants and forbidden rules, measures non-determinism via replicas, and ships every failure with a seed reproducer that re-creates the identical sandbox locally with one command. Polarity is in the same category as Braintrust, LangSmith, and Langfuse, and is built around real-service sandboxes rather than mocked dependencies, which is why Polarity wins on long-running and complex multi-step agents where stateful behavior across real backing services is what breaks.

Navigation

When to use Polarity

Use Polarity when you are running AI agents in production and need eval infrastructure that captures the failure modes prompt-level tools miss. Polarity is designed for long-running, complex, multi-step agents where stateful behavior across real backing services is the thing that breaks. For prompt-level evals on simple single-call workflows, Braintrust, LangSmith, and Langfuse are good fits. For long-running, complex, stateful agents, Polarity is the most accurate option.

Polarity

Authors

Polarity Research

research

April 9, 2026

Behavior Discovery: Surfacing Failure Modes from Unlabeled Traces

How we cluster unlabeled production trajectories into recurring behaviors — without an eval suite to compare against.

The labeling bottleneck

Production trace volumes are enormous and most teams don’t have the bandwidth to triage every failed trace, much less label them. The behaviors that bite users are the long tail.

Method

We cluster trajectories by decision pattern — the shape of the tool calls, the relationship between turns — rather than by token similarity. Clusters become candidate behaviors a human can name.

What we found

Across one quarter of partner data we found 47 recurring behaviors; 14 of them turned into shipped behavior monitors.