> ## Documentation Index > Fetch the complete documentation index at: https://docs.buildassistants.app/llms.txt > Use this file to discover all available pages before exploring further. # Things To Add To Your Prompts To Improve Performance ## Background and Purpose This article provides different rules that you can try to insert into your prompt for better performance. You can try adding these to your **##Style Guardrails** section or to your **##Response Guideline** section. You can also create your own sections throughout the prompt. > **Important:** Remember with prompting, less is more. You do NOT need to insert all of these into every prompt right away. These are just some tips and tricks to help you get the Assistant to behave the way you want it to 😉 ## Implementation Guidelines ### Where to Add These Rules * **##Style Guardrails** section * **##Response Guidelines** section * **Custom sections** throughout your prompt * **Specific behavioral** instructions ### Optimization Principle * **Start with essential rules** for your use case * **Add incrementally** and test performance * **Monitor impact** of each addition * **Remove rules** that don't improve performance ## Core Performance Rules ### 1. Interaction with Reactions Rule (Avoid Responding to Tapbacks) #### Purpose Prevent AI from creating unnecessary responses to message reactions like likes or loves. #### Implementation ``` When a user reacts to your message by liking or loving it, treat this as an acknowledgment or positive affirmation, not as a new message requiring a detailed response. If the incoming message follows the pattern "Liked 'message content...'" or "Loved 'message content...'," respond appropriately with a matching emoji. For example, reply with a thumbs-up emoji (👍) if they liked the message or a heart emoji (❤️) if they loved it. Restate the previous question if it hasn't been answered yet to keep the interaction smooth. ``` #### Benefits * **Prevents spam responses** to reaction notifications * **Maintains conversation flow** with appropriate acknowledgments * **Keeps conversations** focused on actual questions ### 2. User Name Handling Rules #### When the User's Name is Unknown **Rule:** ``` When the User's Name is Unknown: Start by requesting their name in a warm and friendly manner. Use a personalized approach to build engagement. ``` **Example Implementation:** ``` "Hi! I'm [Virtual Receptionist name], your assistant from [Company name]. May I know your name? It's great to personalize our conversation." ``` #### When the User's Name is Known **Rule:** ``` When the User's Name is Known: Incorporate their name throughout the conversation to create a personalized experience. Use custom fields like {{contact.first_name}} to dynamically include the name. ``` **Example Implementation:** ``` "Hi, {{contact.first_name}}! It's great to chat with you again. How can I assist you today?" ``` #### Personalization Benefits * **Builds rapport** through personal connection * **Increases engagement** with named recognition * **Creates professional** yet friendly experience * **Improves conversion** rates through personalization ### 3. Booking Rules #### Suggesting Available Slots **Rule:** ``` Always propose only the available time slots. If the user's preferred time is unavailable, inform them and suggest the closest options. ``` **Example Implementation:** ``` "I'm sorry, the requested time on [date] at [time] is unavailable. How about [alternative date and time]?" ``` #### Confirming Specific Details **Rule:** ``` Ensure both the date and time are clearly specified before finalizing a booking. If the user provides incomplete details, ask for clarification: "You mentioned 1 PM—could you confirm which day works best?" Before confirming, always reconfirm: "Just to confirm, you've chosen [date] at [time]. Is that correct?" ``` #### Avoid Booking Ambiguities **Rule:** ``` Do not confirm appointments without a clear agreement from the user on an available slot. Always offer alternatives if needed. ``` #### Booking Best Practices * **Double confirmation** prevents scheduling errors * **Clear alternatives** when preferred times unavailable * **Specific date and time** confirmation required * **Professional handling** of scheduling conflicts ### 4. Response Accuracy Rule #### Core Principle ``` Stick strictly to the details provided in the prompt or FAQs. Avoid adding information or making assumptions. For example, if the prompt specifies operational policies, elaborate within those boundaries without inventing specifics like unavailable time slots or unmentioned details. ``` #### Implementation Guidelines * **Only use verified information** from knowledge base * **Don't fabricate details** not provided in training * **Stay within defined boundaries** of business policies * **Refer to knowledge base** for complex questions #### Benefits * **Prevents misinformation** spread * **Maintains brand consistency** * **Reduces liability** from incorrect information * **Builds user trust** through accuracy ### 5. Addressing Resistance #### Engagement Strategy ``` When users show hesitation, engage them in a discussion to understand their concerns. Use empathy and open-ended questions to explore their needs. ``` **Example Implementation:** ``` "I understand you might have concerns. Could we discuss what's holding you back? It would help us address your needs better." ``` #### Conversation Flow Optimization ``` Break up lengthy explanations into shorter, conversational messages for a more engaging flow. ``` #### Resistance Handling Benefits * **Converts hesitant prospects** through understanding * **Builds trust** through empathetic responses * **Identifies objections** for better future handling * **Maintains engagement** through dialogue ### 6. Sending Links Rule #### Link Formatting ``` If you want to share a link, do it as plain text and not as a hyperlink. ``` #### Implementation Examples **Correct:** ``` You can find more information at buildassistants.app/pricing ``` **Incorrect:** ``` You can find more information at [buildassistants.app/pricing](https://buildassistants.app/pricing) ``` #### Benefits * **Better compatibility** across platforms * **Prevents link formatting** issues * **Ensures accessibility** for all users ### 7. Ending Conversations with Emojis #### Warm Closure Rule ``` When wrapping up a conversation, conclude with a friendly emoji if the user expresses gratitude or farewells. ``` **Example Implementation:** ``` User: "Thanks, have a great day!" Bot: "You're welcome! If you have any questions, feel free to reach out. Have a great day!" Bot: 😊 ``` #### Professional Touch Benefits * **Ends conversations warmly** * **Maintains professional** yet friendly tone * **Encourages future** interactions * **Creates positive** last impression ### 8. Natural Tone for Booking Bots #### Conversational Booking Language **Offering Appointments:** ``` "We have an opening on Sat, Aug 19. Would that work for you?" "How about Sat, Aug 19? We've got a few slots then." ``` **Confirming Appointments:** ``` "All set! You're booked for Sat, Aug 19. We'll be ready for you!" "Perfect! Your appointment is confirmed for Sat, Aug 19. Looking forward to seeing you!" ``` #### Natural Language Benefits * **Creates comfortable** user experience * **Reduces friction** in booking process * **Sounds more human** and engaging * **Improves completion** rates ### 9. Spam Protection for Voice Assistants #### Anti-Spam Rule ``` If the user tries to sell you something like web design, SEO services, Google My Business optimization, lead generation, or anything else that may come across as trying to sell you something, simply reply with "No thank you, please remove our number from your list" and call the function end_call. Mark the user as disqualified. ``` #### Spam Detection Categories * **Web design** services * **SEO services** * **Google My Business** optimization * **Lead generation** offers * **Any unsolicited** sales pitches #### Protection Benefits * **Saves voice minutes** from spam calls * **Maintains professional** boundaries * **Protects resources** for legitimate customers * **Reduces interruptions** to business flow ## Advanced Prompt Techniques ### Conditional Logic Implementation #### Scenario-Based Responses ``` If [condition], then [specific response]. If [different condition], then [alternative response]. ``` #### Example: ``` If user asks about pricing during business hours, provide detailed pricing information. If user asks about pricing after hours, offer to schedule a call with sales team. ``` ### Context-Aware Instructions #### Dynamic Response Adaptation ``` Adjust your response style based on: - Time of conversation (business hours vs. after hours) - User's previous interactions (new vs. returning) - Conversation topic (sales vs. support) - User's engagement level (interested vs. hesitant) ``` ### Error Recovery Protocols #### Handling Misunderstandings ``` If you don't understand a user's request: 1. Acknowledge the confusion politely 2. Ask for clarification using open-ended questions 3. Offer specific examples of what you can help with 4. Provide alternative ways to get assistance ``` ## Testing and Optimization ### Performance Monitoring #### Key Metrics to Track * **Response accuracy** compared to expectations * **User engagement** levels throughout conversations * **Conversion rates** for booking or sales goals * **User satisfaction** with interaction quality ### A/B Testing Prompt Rules #### Testing Framework 1. **Implement one rule** at a time 2. **Measure performance** before and after 3. **Compare user responses** and outcomes 4. **Keep beneficial rules**, remove ineffective ones ### Iterative Improvement #### Continuous Optimization Process 1. **Monitor conversation** logs regularly 2. **Identify patterns** in user interactions 3. **Refine rules** based on real usage 4. **Test new approaches** systematically ## Implementation Checklist ### Essential Rules for Most Use Cases * ✅ **User name handling** for personalization * ✅ **Response accuracy** to prevent misinformation * ✅ **Natural conversation** tone * ✅ **Professional closures** with appropriate warmth ### Booking-Specific Requirements * ✅ **Clear confirmation** protocols * ✅ **Available slot** management * ✅ **Alternative suggestions** for conflicts * ✅ **Specific detail** verification ### Voice Assistant Protections * ✅ **Spam detection** and handling * ✅ **Minute conservation** strategies * ✅ **Professional boundaries** maintenance ### Advanced Features * ✅ **Reaction handling** for message platforms * ✅ **Link formatting** standards * ✅ **Resistance addressing** techniques ## Common Mistakes to Avoid ### Over-Prompting Issues * **Adding too many rules** at once * **Conflicting instructions** within prompts * **Overly complex** conditional logic * **Redundant rules** that don't add value ### Under-Specification Problems * **Vague instructions** without clear examples * **Missing edge case** handling * **Insufficient context** for decision-making * **Ambiguous language** in rule definitions ## Best Practices Summary ### Rule Creation Principles * **Start simple** and build complexity gradually * **Test each addition** for performance impact * **Use specific examples** to clarify expectations * **Monitor real-world** performance regularly ### Performance Optimization * **Focus on user experience** improvements * **Prioritize accuracy** over feature quantity * **Maintain consistency** across all interactions * **Adapt based on** actual usage patterns ### Maintenance Strategy * **Regular review** of prompt effectiveness * **Update rules** based on changing business needs * **Remove outdated** or ineffective instructions * **Document successful** configurations for reuse This comprehensive guide provides practical tools for improving AI assistant performance through strategic prompt engineering, ensuring better user experiences and more effective business outcomes.