Guiding Users

Implicit Confirmation

Implicit confirmation involves repeating details back to the user to reassure them that they were understood correctly. This also gives the user a chance to intervene if your assistant misunderstood.

Example:
"Can I get a large hawaiian and bbq pizza?"
"Sure, that's one large hawaiian and one regular bbq pizza."
"Anything else?"
"No they should both be large!"

Explicit Confirmation

Explicit confirmation means asking the user to clarify how you should help them. An important thing to remember about AI assistants is that the user is never wrong. When a user tells you something like "I just moved", they are being perfectly clear, even if your assistant is not sure how to help them. If the user goal is ambiguous to your assistant, ask for clarification.

Examples:

• "I just moved"
• "I'm not sure I understood you correctly. Do you mean ...?"
• "I want to cancel my contract"
• "I want to update my personal details."

Configuration Example:

policies:
- name: TwoStageFallbackPolicy
  nlu_threshold: 0.3
  core_threshold: 0.3
  fallback_core_action_name: "action_default_fallback"
  fallback_nlu_action_name: "action_default_fallback"
  deny_suggestion_intent_name: "out_of_scope"
...```

## Explaining Possibilities
AI assistants are always limited to helping users with a specific set of tasks, and should be able to explain to a user what they can do. That includes coherently responding to requests that are out of scope.

**Example:**  
- **User asks:** "What can you do?"  
- **Assistant replies:** "I can help you update your personal details, change your plan, and answer any questions you have about our products."

**When a request is out of scope:**  
- **User asks:** "Can you get me a pizza?"  
- **Assistant replies:** "I'm afraid I can't help with that."

**Example Stories for Context:**
```yaml
## user asks whats possible
* ask_whatspossible
  - utter_explain_whatspossible

## user asks for something out of scope
* out_of_scope
  - utter_cannot_help
  - utter_explain_whatspossible

Collecting User Feedback

Asking for feedback is one of the best tools you have to understand your users and determine whether you solved their problem! Storing this feedback is a powerful way to figure out how you can improve your assistant.

Feedback Example:
"Was that helpful?"

• no.

"Thanks. Why wasn't I able to help?"

• you didn't understand me correctly
• you understood me, but your answers weren't very helpful.

Form Action Example:

from rasa_sdk.action import FormAction

class FeedbackForm(FormAction):

def name(self):
        return "feedback_form"

@staticmethod
    def required_slots(tracker):
        return ["feedback", "negative_feedback_reason"]

Domain Configuration Example:

forms:
  - feedback_form
slots:
  feedback:
    type: bool
  feedback_reason:
    type: text
  requested_slot:
    type: text

Handing off to a Human

Users will be very frustrated if your assistant cannot help them and there is no way to reroute the conversation to a human agent. There should always be a way to break out of a conversation! There are multiple reasons why you might trigger a human handoff:

• The user asks to speak to a human
• The assistant is struggling to understand the user
• The assistant understands what the user wants, but a human is required to resolve the issue.

Examples:

• User: "Let me speak to a human"
• Assistant: "Let me put you in touch with someone."
• User: "I want to cancel"
• Assistant: "I'm afraid I can't help you with that."

Triggering Handoff Example:

intents:
  - request_human: {"triggers": "action_human_handoff"}

👋 I can help you get started with Rasa and answer your technical questions.