Overview

Prompting techniques are crucial when using LLM’s because they directly influence how effectively the AI understands and responds to user requests.

If you’re unable to access certain features or sections of this article, it’s possible that your firm doesn’t have access or hasn’t upgraded to the latest version. Please reach out to your internal support team for further assistance.

Step-by-Step Guide

1. Clear, Direct Statements

Explanation:

Clear and direct statements in prompts help avoid misunderstandings and enhance the efficiency of communication between humans and AI. A well-formulated prompt should be unequivocal and unambiguous, so that the AI understands exactly what is expected of it.

Example Prompt:

Example: Recording:
"What is mentioned in the transcript about the hobbies, goals, and desires of the customer?"

is better than
"What is mentioned in the transcript about the customer?"

Example: External Knowledge:
"Tell me which three factors most significantly impact the profitability of banks and insurance companies, and how they influence their financial performance"

is better than
_"Tell me something about banking and insurance?"

Advanced Example:
"I am looking for current high-performing investment opportunities for a client interested in long-term growth with moderate risk. Provide me with a comparison chart of the top five diversified equity funds based on their 5-year performance, risk rating, and management fees. Include only those funds that have a minimum investment grade rating of 'BBB' and exclude any funds that have had a management change in the past year. Additionally, ensure all data is up-to-date as of the last quarter."

This prompt is clear and task-specific, and uses keywords effectively.

2. Language of the Report (Only for Recording Platform)

Explanation:

If you would like the report in the same language as the recording, you can select this in the settings. However, if you want the report to always be in the same language, you must specify this at the beginning of the prompt.

Example Prompt:

"Force to write in German. Summarize the transcript."

3. What to Do Rather Than What Not to Do

Explanation:

It is more effective to directly state what should be done rather than describing what should NOT be done. This leads to more direct and productive responses.

Example Prompt:

Example 1: "What is mentioned in the transcript about the hobbies, goals, and desires of the customer?"

is better than
"What is mentioned in the transcript about the customer but don’t tell me the birthday and do not mention the address."

4. Persona Pattern

Explanation:

By assigning a specific persona, the prompt can generate specific and context-dependent responses that match the character or role of the persona.

Example Prompt:

Example Recording:
"Act as a skeptical scientist and summarize the transcript."

5. Audience Persona Pattern

Explanation:

This technique helps align the AI's responses better with the needs, expectations, and context of the target audience.

Example Prompt:

Example 1: "Assume I am a new bank clerk with limited experience in using financial software. Please summarize the transcript"

6. Context of the Recording

Explanation:

The context refers to the specific circumstances under which the conversation took place. A clear understanding of this context is crucial for interpreting transcript contents effectively.

Example Prompt:

"Analyze the attached transcript of a consultation between a customer advisor and a client of Bank XYZ, which took place in Munich. The main purpose of the conversation was to advise on real estate financing. Please identify the main topics discussed, as well as any concerns or special requests from the client."

7. Defining the Scope and Depth

Explanation:

Clearly defining the scope and depth of the desired response helps avoid overly general or specific answers.

Example Prompt:

Example 1: "Explain what was said about the basic principles of investing with a focus on ETFs for an audience that is new in this area."

8. Using the Right Keywords

Explanation:

Selecting precise keywords helps the AI better understand the topic and filter relevant information more effectively.

Example Prompt:

Example Recording: "Analyze the transcript of the conversation regarding investments and describe the most important topics, particularly ROI, Risk Assessment, and Market Analysis."

9. Setting the Tone or Style

Explanation:

The tone or style of a prompt guides how the answer should be formulated.

Example Prompt 1:

"Write a short, humorous summary about the above transcript from an internal meeting."

10. Requesting a Specific Format

Explanation:

Requesting a specific format helps obtain the AI's response in a particular structure.

Example Prompt:

Example Recording: "Summarize the above transcript in a list with bullet points."

11. Template Format

Explanation:

Using a template format ensures that the AI's output adheres to a predefined structure.

Example Prompt:

"From the above transcript, write an email to a colleague."

12. Multiple Choice Prompts

Explanation:

These prompts present the AI with a question and several potential answers to choose from.

Example Prompt:

Example Recording: "Given a customer's interest in securing a mortgage with the lowest possible interest rate, which of the following options should they consider? A) Fixed-rate mortgage, B) Adjustable-rate mortgage, C) Interest-only mortgage. Explain the benefits and drawbacks of each option based on the current economic conditions."

13. Zero-Shot Prompts

Explanation:

This refers to the AI's ability to handle a task without specific prior training or examples.

Example Prompt

Example Recording: "Analyze the following transcript and identify all important financial information, including risk factors and investment recommendations."

14. Providing Examples

Explanation:

Providing examples in a prompt can help improve the quality of the response.

Example Prompt:

"Make a CRM entry from the transcript. A good CRM entry should contain the following information: customer name, contact information, Company, Industry, Role, Purpose of Contact."

15. Cognitive Verification

Explanation:

This process involves breaking complex questions into smaller parts for detailed responses.

Example Prompt:

Example Recording:
"Given a transcript of a banking conference, break down the discussion on new compliance regulations into the following parts...".