← All use cases

Bell Canada · Montreal, QC

Bell Canada automates 450,000 complaint cases a year with a ServiceNow triage agent

Customer SupportProductivity

450,000 cases automated per year
25% faster response times
90% accuracy on AI-assisted cases (partner-reported)

What was done

With implementation partner Ateko, Bell connected ServiceNow's triage agent to 11 complaint inboxes and 14 internal systems. When a complaint or escalation arrives, the agent opens the case, checks that the information is complete, fills in the key fields and flags duplicates before the case reaches a human queue.

Outcome

Ateko reports that about 450,000 cases a year are now handled this way, customer response times are 25% faster, and AI-assisted cases are 90% accurate. These figures come from the implementation partner.

Evidence: Vendor case study. Figures are as reported by the source and have not been independently audited by AgentsNorth.

Prompt Reconstructed by AgentsNorth

The source didn't publish its prompt. This is our reconstruction of a starting prompt for a similar workflow, not the company's actual prompt.

You triage incoming customer complaint emails. For each email: identify the customer and account, classify the complaint type and severity, and extract the required case fields (product, issue, dates, amounts, requested remedy). If a required field is missing, list it as missing rather than guessing. Search open cases for the same customer and issue and flag likely duplicates. Output a structured case record and a routing recommendation for the right queue.

Related use cases

Get new Canadian AI agent use cases each week

New use cases, one prompt to steal and one failure to avoid. Free. Unsubscribe anytime.