Gorgias intents power your auto-tagging, view filters, and macro suggestions. Most brands set up intents once at onboarding and never retrain them. The result: intents that were 80 percent accurate at launch drift to 50 percent within six months as your product line and customer behavior change. This SOP makes intent training a quarterly ritual.
Inaccurate intents cascade through your support operations. Wrong tags break reporting. Wrong routing puts tickets in the wrong queue. Wrong macro suggestions train agents to ignore the AI. Retrain quarterly and you keep automation working for you, not against you.
Pull from Gorgias reporting. Filter to fully resolved tickets only.
Manager reviews each: was the intent correct? Calculate accuracy percentage.
These are your training targets. Don't try to fix everything at once.
Gorgias learns from corrections. More examples = faster learning.
If 'refund request' keeps catching cancellation requests, the rules need a cancellation intent split.
Don't push training to production until you've watched a week of fresh tickets.
Same 100-ticket sample method. Target 80+ percent accuracy.
Calendar it. Intent training is a forever job, not a one-time setup.
Record your screen while performing the gorgias intent training. ReccordSOP turns the recording into a SOP with timestamped screenshots. When your live setup changes, drift detection flags it.
Generate this SOP freeQuarterly minimum. After major product launches or campaigns, retrain immediately because customer language shifts.
80 percent or higher. Below 70 percent and the automation actively hurts your team. Above 90 percent is excellent.
Yes. Use the bulk import feature and correct intents on resolved tickets. This is the fastest way to build a baseline.
I built ReccordSOP after watching too many DTC ops teams lose months to undocumented workflows. These SOPs are battle-tested with Shopify operators running $1M to $50M brands.
Last reviewed June 1, 2026