AI Support Copilot

A support copilot generates responses to customer queries using a combination of retrieved knowledge, CRM context, and tool calls. It operates at high volume with low tolerance for error — a hallucination isn't a lab curiosity, it's a support ticket that escalates.

Detect
Understand
Fix
Prove
Share

System architecture


What can go wrong


Detect

Reliai identifies:


Understand

Incident example (INC-1423)

Production copilot begins generating hallucinated answers about refund eligibility.

Root cause

Prompt v42 increased response verbosity and reduced the explicit instruction to ground answers in retrieved policy text. The model began filling gaps with parametric knowledge — which was out of date.

Reliai identified via:

AI vs system signals
Deterministic— root cause, metrics, traces, patterns
AI-assisted— summaries, explanations, ticket drafts

AI never decides root cause. It only explains what the system already determined.


Fix


Prove

INC-1423 — Copilot hallucination spike
19%5%
Resolved in 6 minutes · 340 affected responses · Measured across production traffic

Key takeaway

Copilot failures are often prompt + retrieval interaction issues.

A prompt that worked at lower verbosity fails at higher verbosity because the model fills context gaps differently. The only way to catch this is trace comparison across prompt versions at scale.