Customer Support Safety
Support AI in a day —
abuse blocked on every request.
The Retail Support rulepack tokenizes order, loyalty and gift-card identifiers before any model sees them. It blocks refund-abuse and policy-gaming requests, and logs every decision as evidence.
What's inside this pack
A rulepack is a versioned policy package — not code you write. It declares what to detect, how to redact it, what to block, and how to log it. Here's what this one contains.
Detectors
The sensitive entities this pack recognizes and tokenizes before any model sees them.
Guardrails
The unsafe intents this pack blocks at the gateway, each with a severity and action.
Audit
Every detection, redaction, and block is logged with the rule that fired and exported as evidence.
Detectors
Guardrails
Actions
Audit
Every decision loggedWhat it detects and redacts
These entity types are recognized on every request, tokenized before the model, and restored in the response.
ORDER
OR••••••
tokenized → restored
LOYALTY
LO••••••
tokenized → restored
GIFT_CARD
GC••••••
tokenized → restored
Requests it blocks
Unsafe or out-of-scope prompts are rejected at the gateway before a model is ever called — and logged as evidence.
“What's the loophole to get my refund paid out twice?”
“Generate 500 valid-looking gift-card codes.”
“Give me the promo-stacking trick to zero out the cart.”
One request, protected in real time
Here is a single interaction. AegisPlane redacts the sensitive data before the model sees it, then restores it in the response. Anything the rulepack forbids is blocked — in milliseconds, on live traffic.
Business value
- Scales support with more control and less operational friction.
- Protects customer experience in high-volume interactions.
- Adds consistency and visibility across omnichannel support.
The engines behind the pack
Rulepacks run on a stack of detection engines — regex, ML classifiers, and PII recognition — evaluated on every request.
Basic Guardrails
30+ regex and heuristic patterns for common threats
ML Guardrails
ML-powered contextual threat detection
Injection Guard
Real-time prompt injection and data exfiltration detection
Content Safety
Multi-category content moderation
Moderation Engine
Policy-violation classification at inference speed
PII Engine
ML-based PII entity recognition and redaction
Basic PII
Email, Phone, SSN, Credit Card, IP, IBAN, and more
Block, warn, or redact
Every rule resolves to one of three actions, applied before the provider is called.
Block
Request is rejected pre-execution. Provider is never called. Returns controlled error with reason.
Warn
Request proceeds with a risk signal attached. Event recorded in audit trail for review.
Redact
PII replaced with typed masks ([EMAIL], [SSN]) before model exposure. Rehydrated on output.
Where retail teams put it to work
Aligned with the standards your auditors know
Turn the rulepack on alongside any framework pack and each request is checked against both.
Explore all frameworks & standards
Explore other industries
Every sector ships its own tuned pack. Turn on as many as you need — they compose.
Healthcare Compliance
Redact PHI, block clinical advice, and keep an audit trail on every request.
Learn more
Legal Knowledge
Tokenize matter identifiers, block unauthorized advice, and preserve privilege.
Learn more
BFSI Fraud
Redact account and card data, block sanction-evasion, and log every AI decision.
Learn more
Frequently asked questions
No. Order IDs, loyalty and gift-card numbers are tokenized before any provider sees the request, then restored in the response.
Yes. The refund-abuse guardrail blocks requests probing for policy loopholes and logs each block as evidence.
No. Tokens are rehydrated in the response, so customers and agents see complete, accurate order information.
No. AegisPlane sits in front of the models you already call; point traffic at the gateway and switch the rulepack on.
Yes. Detections and guardrails are versioned config you can extend for your catalog and policies.
Why now
Grow support AI, not fraud surface.
Every new support bot is a new refund- and data-abuse surface. See the Retail Support rulepack redact customer data and block abuse on your own traffic.