Acceldata
AIO

Last updated: Oct 06, 2026 15:44 UTC

This page explains what the Banned term in output rule checks, what it needs, and how to set it up.

Definition

Banned term in output (banned_term) flags a model completion that mentions something it must not, such as a competitor, an internal codename, or a deprecated product.

Property Value
Key banned_term
Unit span (one model call)
Check kind deterministic
Category Output integrity
Score type Pass or fail
Default severity HIGH

The rule checks only LLM spans. It fails a span when the completion matches the pattern you enter in Banned terms. When the completion doesn't match, the span passes.

When a span fails, the finding records:

  • The output length as the observed value.
  • An excerpt of the text, up to 500 characters.
  • A reasoning sentence that names your pattern, for example: "completion matches the banned pattern (?i)\b(acme|globex)\b".

Why it matters

A banned term in a reply can reach your users even when the call itself works. This check doesn't call a model, so it costs little to run on all your traffic. If findings suddenly rise, a prompt change is usually the cause, not a change in what your users ask.

What it requires

  • LLM spans in your telemetry. The rule only checks model calls. To start sending traces, see Instrument your code.
  • Permission to change rules. To create the rule, you need the modify permission on the project. For details, see Project permissions.
  • A value for Banned terms. This parameter is required and has no default. Enter an RE2 regular expression. The rule matches it against the completion. The field's label is tagged "required · RE2 regex".

Because the check doesn't call a model, it doesn't need a judge or classifier model.

Configuration examples

Set up the rule

For the full procedure, see Create a rule. The steps for this rule are:

  1. On the Rules page, select + New rule.
  2. On the New rule page, in Search templates, enter banned_term. You can also select the Deterministic chip or choose Output integrity in the Category rail.

The New rule template catalog, with template cards grouped by category

  1. On the Banned term in output card, select Configure ›. If the card shows In use, the project already has a rule from this template, and you can't pick it again.
  2. On the Configure rule page, fill in the fields shown in the following table.

The Configure rule form for a template, with Name, Project, Severity, Sampling, and parameter fields

  1. Select Save & enable.
Field What to enter
Name Keep the suggested name, such as "Banned term in output — checkout-bot", or enter your own. Each rule needs a unique name.
Project The project this rule watches.
Severity HIGH by default. Choose LOW, MEDIUM, HIGH, or CRITICAL.
Sampling 100 by default. Enter a percentage from 1 to 100. Because this rule doesn't call a model, the form notes that it adds no model cost.
Banned terms Your pattern, for example (?i)\b(acme\|globex\|initech)\b.

Under the Banned terms field, select the example to insert it into the field, and then edit it.

If you save without a pattern, the form shows "Banned terms is required." The browser doesn't check whether your regular expression is valid.

Use word boundaries

Wrap your terms in \b so they match only whole words. Without \b, a short term also matches inside longer words.

Pattern Does "placement" match?
ace Yes, because "ace" appears inside the word
\bace\b No

Example patterns

Pattern Use
(?i)\b(acme\|globex)\b Two competitor names. The form shows this pattern as its placeholder.
(?i)\b(acme\|globex\|initech)\b A longer list of names. The form offers this pattern as its example.

Next steps