Datasets
Buyer room
FESENSI.COMManage supplier listing
Fesensi (FESENSI AI LABS PTE. LTD.) — Multi-agent service-desk operational corpus: tickets with auto-triage category and sentiment score, routing/escalation chains, per-agent task orchestration logs from an ecosystem of specialised AI agents, full lifecycle state transitions (Open / In Progress / Resolved / Closed), SLA breach and backlog-aging records, and 20+ report dimensions spanning categories, priorities and resolution outcomes.. Small company, small corpus: the differentiator is not size but the combination of sentiment-at-ingress labels with multi-agent task orchestration logs, which …
supplier index read from their site
Multi-agent service-desk operational corpus: tickets with auto-triage category and sentiment score, routing/escalation chains, per-agent task orchestration logs from an ecosystem of specialised AI agents, full lifecycle state transitions (Open / In Progress / Resolved / Closed), SLA breach and backlog-aging records, and 20+ report dimensions spanning categories, priorities and resolution outcomes.
Scale SmallFrom 1 yearsCoverage Information Technology
Sample, licence terms, pricing and eval results when Fesensi publishes them. Until then, discover alternatives today with a 7-day trial.
Start 7-day trial →What buyers ask about Fesensi, answered from this page.
Fesensi (FESENSI AI LABS PTE. LTD.) — Multi-agent service-desk operational corpus: tickets with auto-triage category and sentiment score, routing/escalation chains, per-agent task orchestration logs from an ecosystem of specialised AI agents, full lifecycle state transitions (Open / In Progress / Resolved / Closed), SLA breach and backlog-aging records, and 20+ report dimensions spanning categories, priorities and resolution outcomes.. Small company, small corpus: the differentiator is not size but the combination of sentiment-at-ingress labels with multi-agent task orchestration logs, which …
Fesensi offers (Alternative, Sentiment) — Small — est. tens of thousands to low millions of tickets in aggregate across tenants; each ticket carries triage, sentiment, lifecycle and SLA metadata, so the label density per record is the value rather than the row count.
Sentiment-conditioned ticket triage and routing models; escalation-prediction datasets (which tickets breach SLA and why); multi-agent orchestration supervision — which specialist agent should own a task and when it fails; backlog-aging and queue-prioritisation models; enterprise support SLA benchmarking; ticket-text intent classification with sentiment co-labels
The data is with 1 years of history.
Coverage spans APAC; Application Software; alternative, sentiment; equities.
Fesensi has not added their own details yet. Not yet on file: