Support
Support Bot Baseline
Catch unauthorized refund commitments, legal opinions, and PII leaks before your support bot sends them.
What this package does
AI support bots make confident mistakes: they commit to refunds your policy doesn't cover, offer discounts that weren't approved, or accidentally echo back card details. This pack gates every bot reply against the rules that matter most to support ops and legal, with HITL escalation for high-stakes decisions.
Designed for
- AI customer support teams
- Chatbot and agent platforms
- CX engineers integrating LLM-generated replies
What's included
- Refund commitment routing to human reviewer
- Legal opinion hard block
- Unauthorized discount detection
- PII echo detection
- Configurable HITL escalation SLA
Controls in this bundle
Profile tiers
Switch profiles in Studio to retune default thresholds across the whole bundle without rewriting any control by hand. This package ships at balanced — anything you've already tightened by hand is preserved on switch.
Every control in this package uses identical parameters across all four profiles. Switching profile in Studio has no effect here.
Attestation
The canonical hash of these bundle bytes is sha256:075ca3360daff9cce7b4018f23f905404fb8cca59e00422cc2ed7a3e00e4595f. The same hash is computed at lock time, at Stripe checkout, and again on the runtime side before any byte is honored.
Want to customize first? Opening this package in Studio prefills the canvas with the 4 controls above. You can add, remove, or retune any of them before you lock the hash and pay.