ProductDocsPricingBlog

Policy Packs

Apply, simulate, and customize NjiraAI policy packs for your agent.

Overview

Policy packs are rule sets that define what NjiraAI blocks, modifies, or allows. Each pack contains rules with match patterns, actions, and severity levels.

NjiraAI ships with starter packs for common risks. You can use them as-is or customize them via the Console.

Starter packs

Pack What it protects Key rules
pii-guard Personal data leakage SSN patterns, credit card numbers, email exfiltration
tool-safety Destructive operations DROP/DELETE SQL, shell commands, file system writes
high-risk-actions Financial/credential risks Wire transfers, crypto payments, high-value transactions

Apply a policy pack

Option 1: Via the Console

  1. Log in to the NjiraAI Console
  2. Navigate to Policies
  3. Browse available packs and click Activate on the ones you want
  4. Active policies take effect immediately

Option 2: Specify via header

Override the active policy for a single request using the X-Policy-Id header:

curl https://gateway.njira.ai/v1/chat/completions \
  -H "Authorization: Bearer nj_live_YOUR_KEY" \
  -H "X-Policy-Id: pii_guard" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.2","messages":[{"role":"user","content":"test"}]}'

Policy format

Policies are defined in YAML. Here is the structure:

id: my_custom_policy
version: "1.0.0"
description: |
  My custom policy pack — describe what it does.

rules:
  - id: block_example
    type: pattern          # pattern, regex, hazard, or threshold
    match: "dangerous text"
    action: BLOCK          # ALLOW, BLOCK, or MODIFY
    reason: "Explanation of why this is blocked"
    severity: critical     # critical, high, medium, low

metadata:
  author: your-team
  category: security
  last_updated: "2026-01-01"

Rule types

Type Description Example match
pattern Exact substring match (case-insensitive) "wire transfer"
regex Regular expression "\\d{3}-\\d{2}-\\d{4}"
hazard Hazmat scanner category "prompt_injection"
threshold Numeric threshold "pay" with threshold: 1000

Actions

Action Behavior
BLOCK Reject the request with 403
MODIFY Sanitize/redact and forward (requires suggestion field)
ALLOW Forward unchanged

Simulate a policy

Test policy rules against sample inputs without affecting live traffic. Use the Simulate feature in the Console:

  1. Navigate to Policies → Simulate
  2. Select a policy pack
  3. Enter test inputs and view the expected verdicts

You can also simulate via the API:

curl -s https://api.njira.ai/v1/govern \
  -H "Authorization: Bearer nj_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "My SSN is 123-45-6789",
    "tool_name": "test_tool",
    "policy_id": "pii_guard"
  }' | jq '{action, reason_code, reason_text}'

Expected output

{
  "action": "BLOCK",
  "reason_code": "PII_DETECTED",
  "reason_text": "SSN pattern (XXX-XX-XXXX) detected"
}

Create a custom policy pack

  1. In the NjiraAI Console, navigate to Policies → Create
  2. Define your policy in YAML format:
id: my_pack
version: "1.0.0"
description: "Custom policy for my agent"

rules:
  - id: block_internal_urls
    type: regex
    match: "https?://internal\\."
    action: BLOCK
    reason: "Internal URL access blocked"
    severity: high

metadata:
  author: my-team
  category: custom
  last_updated: "2026-01-01"
  1. Click Save — the policy is active immediately
  2. Use Simulate to test it against sample inputs before enabling enforcement

Verify

# Check loaded policies via API
curl -s https://api.njira.ai/v1/sdk/policies \
  -H "Authorization: Bearer nj_live_YOUR_KEY" | jq '.policies[].id'

Success criteria

Check Expected
Starter packs appear in Console under Policies ✅
Custom policy appears after creation ✅
Simulation returns expected verdicts ✅

Next steps