Velaxe
Run A/B tests on routing and model choices | Chat Core

Chat Core

Run A/B tests on routing and model choices

Split traffic across rules/models and pick winners on KPIs like CSAT, cost, and containment.

Experiments dashboard
Split traffic & results

Overview

Split traffic across rules/models and pick winners on KPIs like CSAT, cost, and containment.

Problem

Routing and prompt changes ship without evidence; hard to know what actually helps.

Solution

Chat Core randomizes traffic across routes/models, tracks outcomes, and reports significance in InsightLake. Promote winners with one click.

How it works

Define experiments in the Admin UI; choose split, KPIs, and stop rules; export traces and outcomes for audit and reproducibility.

Who is this for

CX Ops Data/Analytics

Expected outcomes

  • Evidence-based routing & model selection
  • Lower per-contact cost without hurting CSAT

Key metrics

Cost per resolved contact

Baseline

2.1 USD

Target

1.4 USD

Containment (winner vs control)

Baseline

0 pp

Target

6 pp

Gallery

Experiments dashboard
Split traffic & results

Downloads & templates

Case studies

Retail CX trims LLM spend 23%

A/B between models cut cost while improving containment by 4pp.

Retail Enterprise NA

Security impact

  • Aggregated experiment metrics & traces · PII: none (aggregated)

Compliance

  • SOC2 (monitoring & change control)

Availability & next steps

Business Enterprise