Rules Manager reference

Built-in rules, custom rules, rule types and actions, per-rule options, priority, and AI-assisted rule creation.

The Rules Manager is where guardrail rules are created and governed.

Built-in rules#

The built-in "System" rules cover the common vectors: jailbreak detection, PII masking, toxicity filtering, and data-exfiltration blocking. Each can be enabled or disabled from the Rules Manager.

Custom rules#

Create, edit, enable/disable, and delete custom rules with:

OptionWhat it controls
TypeRegex / keyword, or semantic (natural-language intent)
Actionblock, mask, log_only (accept, no content persisted), or accept (accept and log)
SeverityYour own triage label
Pattern / intentThe regex, keyword, or intent description
Skip semantic checkOpt a matching request out of the semantic tier
Source IP / subnetApply the rule only inside a CIDR
Destination IP / subnetApply the rule only when the backend resolves inside a CIDR
Key mode / streamingPin upstream key behavior and streaming mode for matching requests
Rule scopingApply to agents (ids, globs, tags, groups), exclude agents, exclude source IPs

Evaluation#

Rules are evaluated in a fixed order: built-ins, then block rules, mask rules, accept/log rules, then the semantic tier, then the implied default action. See the guardrails guide for the full order. Deny always wins over accept.

Create Rule with AI#

The Create Rule with AI card drafts a rule from a plain-language objective (keyword or semantic), with an editable preview before the rule is committed. See Create rules with AI.

Prompt Analyzer#

The Prompt Analyzer card tests any prompt against the enabled inbound rule base without sending it upstream. It is safe under any license or quota state: no model call is made and no log rows are written.

  • Matched rules: each text, regex, or keyword rule that fires, with its action and severity.
  • Semantic scores: per-rule cosine scores with block and flag banding, plus the overall verdict (block, flagged, or allowed).
  • Masked preview: the redacted prompt when mask rules apply.

Paste a prompt and run the analysis to see exactly which rules would fire and why, before you commit the rules to production.