Checks

Checks inspect model inputs and outputs. Use them to measure response quality, detect policy violations, remove sensitive data, or stop unsafe content before it continues through your application. Each row shows what the check reads, the engine it uses, the action it takes, its scope, and its activity over the last 24 hours.

​

Start from a template

When you have no checks, Rules shows a gallery of common starting points. Select a template to add a pre-filled draft, then review it before saving. After you save your first check, open New check to find the same templates and custom options. The description pane explains what each template detects and what its default action will do.

​

Choose an action

The action determines when a check runs and whether it can change the call. Score checks are stored and run differently from enforcement checks. Changing a saved check between Score and another action creates a new check, so its previous activity history is not carried over.

​

Choose an engine

​

LLM checks

Use an LLM check when the rule depends on meaning or context—for example tone, intent, toxicity, or whether an answer addressed the question. Opper chooses and manages the classifier model. LLM checks use a failover chain and are billed at a flat rate for checks, regardless of which model handles the request.

​

Regex checks

Use a regex check for predictable formats such as email addresses, credit card numbers, SSNs, and API keys. Regex checks do not call a model and cannot use the Score action. Select a pattern chip to edit and test it.

​

Redaction behavior

When the action is Redact, a regex check replaces each match with *** by default. An LLM check uses [REDACTED]. Enter a replacement value if you want a different result. If an LLM check detects a violation but cannot identify the exact text to replace, Opper flags the call instead of changing its content. This can happen with broad findings such as toxicity.

​

Score checks

Choose Score to evaluate response quality after a call completes.

​

Score type

​

Sampling

Sampling controls how many outputs the judge evaluates and therefore how much the check costs. Adaptive sampling keeps evaluation costs more predictable during traffic spikes. If its counter is unavailable, Opper evaluates every output rather than silently skipping them. The judge model is managed by Opper and billed at the same flat rate for checks. Disabling a score check stops queued evaluations before the next judge call begins.

​

Set the scope

Run a check across the organization or limit it to selected projects. If you choose Projects, select at least one project before saving.

​

When checks overlap

Every matching check runs; there is no priority order. If several checks apply to the same call, the strictest result wins. One blocking result is enough to reject the call. Rules highlights checks with the same name and overlapping scope so you can confirm that the overlap is intentional.

​

Disable a check or review activity

Use a row’s toggle to stop a saved check without deleting its configuration. Disabled checks stop immediately and are excluded from validation until you enable them again. The activity label covers the last 24 hours: