The national telecommunications carrier of a small island nation.
About a thousand chats a day, cleared inside the day.
Agents open each one to a brief and draft already prepared, not an empty screen.
Send the queue, inbox, or report with the clearest delay.
Mia maps the first similar Rebotify fix.
The national telecommunications carrier of a small island nation.
About a thousand chats a day, cleared inside the day. Agents open each one to a brief and draft already prepared, not an empty screen.
Volume
~1,000 chats/day
Across the carrier’s primary channel
First-response time
Minutes → under 30 sec
Through the day, including peak
Autonomous resolution
60–70% containment
With re-contact rate held flat
Agent-side AHT
15–25% faster
On the cases that reach a human
A thousand customer chats a day across a small, dense market. Most of them were the same handful of questions: bill enquiries, prepaid top-ups, plan changes, roaming, SIM activations, outage check-ins. Each one looked routine until you’d answered it for the eighth time that morning.
Agents handled what they could during the day and the evening peak built into a queue that the overnight shift inherited. By the weekend the queue had texture: actual incidents tangled up with sixty repeat questions about the same evening’s mobile data top-up.
A chat triage officer.
Scoped to first-touch chats only. No billing changes, no service credits, no plan adjustments, no enterprise accounts.
Connections
- Customer account database (read-only)
- The chat platform
- Knowledge base and standard reply library
- Outage and incident status feed
- Escalation routing rules
- Read every incoming chat and classify against the top six categories
- Pull account context (plan, recent usage, last billing event, last service activity) before drafting
- For routine categories with a clear answer, draft the reply in house tone
- For service credits, complaints, enterprise accounts, or outage-impact compensation, route with one-line context
- Surface to the agent with the draft pre-loaded
After live volume settled in, the category mix needed refining. Prepaid top-ups and bill enquiries were clean; roaming and plan questions often blurred into each other, so drafts occasionally answered the wrong flavour of the same ask. Classification was tightened against the real chat mix (prepaid vs billing vs roaming confusion), and the wrong-flavour drafts dropped.
Agents were also spending more time than they should editing routine replies that were correct but wordy. Draft length and tone were pulled back to house voice: shorter, clearer, less to trim. Escalation routing labels were rewritten as one-line context agents actually trust (why it routed, what’s already known), so the handoff felt like a brief, not a dump.
- Billing adjustments, credits, refunds
- Plan and service changes
- Enterprise and B2B accounts
- Complaint resolution and any escalation
- Anything during an active outage: the wrong autonomous reassurance at the wrong moment is the worst-case interaction
- Reading the chat and classifying it
- Pulling account context before drafting
- Drafting the routine reply in the right voice
- Detecting outage patterns and pausing drafts
- Routing edge cases with reasoning attached
Outcomes sit in the same band as published comparable telecom AI deployments: first-response under thirty seconds during peak, 60–70% of triaged chats resolved without an agent typing, and 15–25% faster handle time on cases that reach a human, with re-contact rate held flat as the check that resolution stayed honest.
- Touch billing. Adjustments, credits, refunds: all human.
- Change a plan or service. The employee can describe options; only an agent makes the change.
- Handle enterprise accounts. B2B routes immediately, no exceptions.
- Speak during an active outage. Outage-pattern detection holds drafts and routes to a human.
- Send without review. Every customer-facing draft passes through an agent.
Agents now open each chat to a pre-built brief: customer context, recent activity, draft reply already prepared for the routine categories, edge cases pulled into the right queue with a summary attached. The evening peak still happens (it always will), but it clears inside the evening instead of waiting for the next morning. The work that needed a person (the complaints, the outage conversations, the enterprise escalations) is the work agents are actually doing.
Chat #2814: prepaid data top-up question, account in good standing, drafted from top-up template. Held for Aishath’s approval.
Chat #2901: roaming rates for travel next week, plan and destination matched to knowledge-base entry. Draft held for agent review.
Other deployments on the same operating model.
Energy · legal & regulatory drafting
A tier-1 Australian energy retailer.
Documents that used to take days now ship in under an hour. The in-house legal and regulatory team reviews and revises instead of retyping.
Read the caseHigher education · course advice & customisation
A leading Australian provider of online higher education.
Deeper answers, customised pathways, better experience for every prospect. The advisors who used to type the same unit explanations now spend the day on the conversations that need them.
Read the caseBring us one workflow. We will name the employee in 48 hours.
Send the queue, inbox, or report with the clearest delay.
Mia maps the first similar Rebotify fix.