← All use cases

L'Oréal Canada · Montréal, QC

L'Oréal's Canadian pilot of an Agentforce advisor assistant cut case handling time by up to 64%

Customer SupportProductivity

-64% handling time when drafts need no edits (vendor-reported)
-40% when drafts are edited
Promo codes: ~10 min to ~1 min
300+ daily advisor users

What was done

L'Oréal started in Canada with a single brand to test an AI assistant for its consumer care advisors in Salesforce Service Cloud. The agent summarises cases, drafts reply emails, validates customer intent and generates promotional codes, while advisors review and edit the drafts. After the pilot showed which intents worked, L'Oréal expanded it to 25 brands across North America, with Europe next.

Outcome

Vendor-reported: case handling time falls 64% (about 7 minutes to 2.5) when the AI draft needs no changes and about 40% when advisors edit it. Generating a promo code went from about 10 minutes across some 15 screens to about 1 minute. More than 300 advisors use it daily, with 100% adoption among eligible advisors.

Evidence: Vendor customer story (Salesforce). 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 assist a consumer care advisor at a beauty company. For the open case, summarise the customer's issue and history in three lines, confirm the customer's intent (product question, complaint, return, goodwill gesture), and draft a reply email in the customer's language following our tone guide and policies. If the policy allows a goodwill gesture, prepare the promotional code request with the right value. Don't send anything; the advisor reviews and edits first.

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.