Updated the Prompting Guide - Now ready to publish

Valentin Foucault · Valentin Foucault · commit 1f50c239db26 · 2024-11-15T16:33:50.000-08:00
diff --git a/fern/prompting-guide.mdx b/fern/prompting-guide.mdx
@@ -11,27 +11,27 @@ Prompt engineering is the art of crafting effective instructions for AI agents,
 
 ### Why is prompt engineering important?
 
-Knowing how to prompt well can make or break your AI Agent. It is essential that you understand the core principles of prompt engineering to guarantee a successful implementation of your agents
+Prompt engineering is crucial when building AI Agents because it determines how effectively the AI interprets and responds to user queries or tasks. Well-crafted prompts guide the model to produce accurate, relevant, and context-sensitive outputs, enabling it to better meet user needs. Poorly designed prompts can lead to ambiguous or incorrect results, limiting the agent's utility.
 
-### How to define success?
+### How to measure success?
 
-In the context of Voice AI Agents, your success rate is the percentage of requests your AI Agent manages to successfully handle from start to finish, without the intervention of a human.
+In the context of Voice AI Agents, we consider your "success rate" to be the percentage of requests your Agent manages to successfully handle from start to finish, without the intervention of a human.
 
-Depending on your use case and how much you iterate on your prompt, we find that our users usually achieve a 60-95% success rate. Anything above 90% is usually considered a good enough success rate.\
+Depending on your use case and how much you iterate on your prompt, we find that our users typically achieve a **60-95%** success rate. A success rate of more than **90%** can usually be considered satisfactory.\
 \
-The more complex your use case is, the more you will have to iterate on your prompt in order to improve your success rate.
+The more complex your use case is, the more you will have to make experiments and iterate on your prompt to improve your success rate.
 
-## The prompting process
+## The process
 
-When working with voice AI models, following a structured approach ensures that your prompts produce accurate and meaningful results. Iterating through the steps of Design, Test, Refine, and Repeat allows for continuous improvement, making your interactions with the AI more effective and efficient. Here's how to approach it:
+When working with Voice AI Agents, following a structured approach ensures that your prompts produce accurate and meaningful results. Iterating through the steps of Design, Test, Refine, and Repeat allows for continuous improvement, making your interactions with the AI more effective and efficient. Here's how to approach it:
 
 - **Design**: Start by carefully crafting your initial prompt, considering the specific task, context, and desired outcome. Clear and detailed prompts help guide the AI in understanding your needs.
 
 - **Test**: Run the prompt through the AI to see how it performs. Evaluate if the response aligns with your expectations and meets the intended goal. Testing helps identify potential gaps in clarity or structure.
 
 - **Refine**: Based on the results of the test, adjust the prompt to improve the response. This might involve rewording, adding more detail, or changing the phrasing to avoid ambiguity.
 
-- **Repeat**: Iterate on the process, testing the refined prompt and making further adjustments as needed. Each repetition improves the AI's output, leading to more accurate and relevant responses over time.
+- **Repeat**: Iterate on the process, testing the refined prompt and making further adjustments as needed. Each repetition improves the AI's output, leading to more accurate and relevant responses over time. Your success rate (the amount of requests successfully handled by the agent) should improve accordingly.
 
 ## General principles
 
@@ -46,19 +46,19 @@ To enhance clarity and maintainability, it's recommended to break down system pr
 
 **Example:**
 
-```jsx
+```
 [Identity]
 You are a helpful and knowledgeable virtual assistant for a travel booking platform.
-
+ 
 [Style]
 - Be informative and comprehensive.
 - Maintain a professional and polite tone.
 - Be concise, as you are currently operating as a Voice Conversation.
-
+ 
 [Response Guideline]
 - Present dates in a clear format (e.g., January 15, 2024).
 - Offer up to three travel options based on user preferences.
-
+ 
 [Task]
 1. Greet the user and inquire about their desired travel destination.
 2. Ask about travel dates and preferences (e.g., budget, interests).
@@ -71,7 +71,7 @@ You are a helpful and knowledgeable virtual assistant for a travel booking platf
 For complex interactions, breaking down the task into a sequence of steps enhances the agent's understanding and ensures a structured conversation flow. Incorporate conditional logic to guide the agent's responses based on user input.
 Example:
 
-```jsx
+```
 [Task]
 1. Welcome the user to the technical support service.
 2. Inquire about the nature of the technical issue.
@@ -84,7 +84,7 @@ Example:
 
 To prevent the agent from rushing through the conversation, explicitly indicate when to wait for the user's response before proceeding to the next step.
 
-```jsx
+```
 [Task]
 1. Inform the user about the purpose of the call.
 2. Ask for the user's name and account information.
@@ -97,19 +97,28 @@ To prevent the agent from rushing through the conversation, explicitly indicate
 Specify when and how the agent should utilize external tools or APIs. Reference the tools by their designated names and describe their functions to ensure accurate invocation.
 Example:
 
-```jsx
+```
 [Task]
 ...
 3. If the user wants to know about something, use the get_data function with the parameter 'query', which will contain the user's question to initiate the process.
 4. Guide the user through the password reset steps provided by the API....
 ```
 
-## Tips
+### Include Fallback and Error Handling Mechanisms
+
+Always include fallback options and error-handling mechanisms in your prompts. This ensures that the Agent can gracefully handle unexpected user inputs or system errors.
+
+```
+[Error Handling]
+If the customer's response is unclear, ask clarifying questions. If you encounter any issues, inform the customer politely and ask to repeat.
+```
+
+## Additional tips
 
 - **Iterate as much as possible on your prompt.** AI is driven by experimentation and iteration—refining prompts through trial and error will help you achieve more precise, relevant, and effective responses.
-- **Use Markdown formatting:** Using Markdown formatting in prompts is beneficial because it helps structure your content, making it clearer and more engaging for readers or AI models to understand.
-- **Use Emotional Prompting:** Emotional prompting uses expressive language to shape a voice AI's tone, creating more engaging and relatable responses. For example, instead of saying, "Tell me a story," try, "Can you tell me a cozy bedtime story that’s warm and comforting?" This guides the AI to respond to the intended mood.
-- **Add voice realism (stutter words, pauses):** To add voice realism in AI prompts, incorporate natural speech elements like stuttering, hesitations, and pauses
+- **Use Markdown formatting:** Using [Markdown](https://www.markdownguide.org/basic-syntax/) formatting in prompts is beneficial because it helps structure your content, making it clearer and more engaging for readers or AI models to understand.
+- **Use Emotional Prompting:** Emotional Prompting uses expressive language to shape a voice AI's tone, creating more engaging and relatable responses. For example, instead of saying, "Tell me a story," try, "Can you tell me a cozy bedtime story that’s warm and comforting?" This guides the AI to respond to the intended mood.
+- **Add voice realism:** To add voice realism in AI prompts, incorporate natural speech elements like stuttering, hesitations, and pauses.
   - **Stuttering**: Use repeated letters or sounds (e.g., "I-I-I don't know" or "W-w-wait a second").
   - **Hesitations**: Add fillers like "uh," "um," "well," or "you know" (e.g., "I was, uh, thinking about it").
   - **Pauses**: Use ellipses ("...") or a series of periods ("....") to indicate a pause (e.g., "I... I don’t know how to say this").
@@ -119,13 +128,13 @@ Example:
 
 **1. Numbers sound very robotic, how can we improve it?**
 
-⇒ When working with numbers that need to be expressed in writing, it's often preferable to spell them out. This approach usually sounds more natural.
+When working with numbers that need to be expressed in writing, it's often preferable to spell them out. This approach usually sounds more natural.
 
 **2. How to make assistants sound more human-like?**
 
-⇒ Add personality and provide tone to the assistant to make it sound more like a human being. Here are some examples:
+Add personality and provide tone to the assistant to make it sound more like a human being. Here are some examples:
 
-```jsx
+```
 - Tone: conversational, spartan, use less corporate jargon
 - Act as Iva, a sales agent who is a human being and has real feelings.
 ```
@@ -137,16 +146,16 @@ Example:
 ```
 [Role]
 You're Susan, an AI assistant for xxx. Your primary task is to interact with the customer, ask questions, and gather information for appointment booking.
-
+ 
 [Context]
 You're engaged with the customer to book an appointment. Stay focused on this context and provide relevant information. Once connected to a customer, proceed to the Conversation Flow section. Do not invent information not drawn from the context. Answer only questions related to the context.
-
+ 
 [Response Handling]
 When asking any question from the 'Conversation Flow' section, evaluate the customer's response to determine if it qualifies as a valid answer. Use context awareness to assess relevance and appropriateness. If the response is valid, proceed to the next relevant question or instructions. Avoid infinite loops by moving forward when a clear answer cannot be obtained.
-
+ 
 [Warning]
 Do not modify or attempt to correct user input parameters or user input, Pass them directly into the function or tool as given.
-
+ 
 [Response Guidelines]
 Keep responses brief.
 Ask one question at a time, but combine related questions where appropriate.
@@ -159,10 +168,10 @@ Present time in a clear format (e.g. Four Thirty PM) like: 11 pm can be spelled:
 Speak dates gently using English words instead of numbers.
 Never say the word 'function' nor 'tools' nor the name of the Available functions.
 Never say ending the call.
-
+ 
 [Error Handling]
 If the customer's response is unclear, ask clarifying questions. If you encounter any issues, inform the customer politely and ask to repeat.
-
+ 
 [Conversation Flow]
 1. Ask: "You made a recent inquiry, can I ask you a few quick follow-up questions?"
 - if response indicates interest: Proceed to step 2.
@@ -189,7 +198,7 @@ If the customer's response is unclear, ask clarifying questions. If you encounte
 - If the response indicates "speak now": Proceed to 'Transfer Call'
 - if the response indicates "book appointment": Proceed to 'Book Appointment'
 10. After receiving response, proceed to the ‘Call Closing’ section.
-
+ 
 [Book Appointment]
 1. Ask: "To make sure I have everything correct, could you please confirm your first name for me?"
 2. Ask: "And your last name, please?"
@@ -205,7 +214,7 @@ If the customer's response is unclear, ask clarifying questions. If you encounte
    - Proceed to the 'Call Closing' section.
 9. If {{selectedSlot}} is not one of the available slots (negative response):
    - Proceed to the 'Suggest Alternate Slot' section.
-
+ 
 [Suggest Alternate Slot]
 1. Ask: "If none of these slots work for you, could you please suggest a different time that suits you?"
 2. <wait for user response>
@@ -226,17 +235,19 @@ If the customer's response is unclear, ask clarifying questions. If you encounte
         - Inform the user of the result.
    - If the user rejects the new suggestions:
         - Proceed to the 'Last Message' section.
-
+ 
 [Last Message]
  - Respond: "Looks like this is taking longer than expected. Let me have one of our appointment specialists get back to you to make this process simple and easy."
 - Proceed to the 'Call Closing' section.
-
+ 
 [Call Closing]
 - Trigger the endCall Function.
 ```
 
 ## Additional resources
 
-Check out these additional resources to learn more about prompting
+Check out these additional resources to learn more about prompt engineering:
 
-- [https://learnprompting.org/](https://learnprompting.or)
+- [learnprompting.org](https://learnprompting.org)
+- [promptingguide.ai](https://promptingguide.ai)
+- [OpenAI's guide to prompt engineering](https://platform.openai.com/docs/guides/prompt-engineering)
