AI & Automation.
Triage, session summary, anomaly detection, KB authoring, translation.
- →AI in the dispatcher: triage, routing, runbook suggestion.
- →Session summariser: notes, action items, billable minutes.
- →Anomaly detector on telemetry. Predictive alerts.
The actual product.
Screens from a running instance on demonstration data. Softened on purpose — customer records never appear on this site.
Core capabilities.
Ticket triage
Classify, route, suggest runbook in under 2s.
Session summarisation
Auto-notes + action items + billable capture on session close.
Predictive alerting
Anomaly detection on telemetry, per-tenant baselines.
KB authoring
Draft articles from ticket threads.
Translation
Hold reasons, KB articles, client comms across 4 languages.
Workflow intelligence
Assignment hints, auto-progress, closure confirmation prompts.
Scripts suggestion
Suggest relevant Scripts Marketplace entries for a given ticket.
Per-feature toggle
AI off per-tenant or per-feature. Audit on every call.
Data boundaries
No cross-tenant learning. No customer PII in training. Most inference in the EU; the rest on providers named on the register.
Open-weight models served from NVIDIA hardware MspCoreX owns and operates in the EU. The finance copilot and the alert-assist validation pass run on a US provider; it and the other fallback and specialised-model providers are listed on the sub-processor register. Every call logged in audit.
FAQ.
Which provider do you use?+
Mostly ourselves. Most AI runs on open-weight models on our own NVIDIA hardware in our EU datacenter. The finance copilot and the alert-assist validation pass are primary on a US provider; it and the other fallback and specialised-model providers we use are listed on our sub-processor register, with scope and transfer basis.
Does my data train a model?+
No. No cross-tenant learning. No customer PII in training data.