There are many types of repair. Here are some of the most common triggers of a repair pattern. The bot's response to each type will depend on your content and use case.
- I don’t get it
- That’s not what I asked
- What is pronation?
- What is a cross-trainer?
- What did you say?
- Can you repeat that?
- Size 10 what?
- What do you mean?
- Can you say that another way?
- What are my options?
- What shoe brands do you carry other than Nike?
- Delectable means delicious?
- Flan is a dessert?
- A pizza with pineapple and papaya?
- Self-correction: “What sizes are the boots- er- shoes available in?”
A: They’re gonna drive back Wednesday.
A: Right, tomorrow.
A: How much do the Nikes in size 7 cost?
B: The Nike Air Max in size 7 costs $100.
Oh I thought those were $80.
B: The Nike Air in size 7 costs $80.
A: Oh okay.
- I didn’t hear that
- User-initiated vs. agent-initiated repair (who triggers repair?)
- User-repair vs. agent-repair (who fixes the problem?)
- Repair sequencing: What if an initial repair doesn’t work? How can you combine them? Looping through different repair strategies, fallback options, scaling up to agent-transfer.
- There could be different fallback strategies. Perhaps, a definition request could be answered, but if that doesn’t work, then use the general repair strategy, and if that doesn’t work, offer to transfer. Alternatively, a user could say a general “I don’t get it”, to which you could respond with a paraphrase.