Aug 25, 2024

[Perplexity AIの 業務活用 完全制覇 Kindle版]

[Perplexity AI 業務活用 完全ガイド:最強の情報収集・分析ツールを使いこなす】

本書は、革新的な AI 検索プラットフォーム「Perplexity AI」の 業務活用法を詳細に解説した実用書です。従来の検索エンジンや他の生成型 AI サービスとは一線を画す Perplexity AI の特徴を理解し、ビジネスや学習、日常生活での効果的な活用方法を学ぶことができます。

Perplexity AI は、AI による情報生成と実時間のウェブ検索を組み合わせた革新的なプラットフォームです。本書では、その多様な検索オプション(全て、学術、数学、作成、ビデオ、ソーシャル)や高度な AI モデル(Claude 3.5 Sonnet、Sonar Large、GPT-4o, Llama 3.1 405B)の特徴と使い分け方を詳しく解説します。

Perplexity AI の強みは、単なる検索結果の羅列ではなく、ユーザーの質問に対して直接的で包括的な回答を提供する点にあります。本書では、この特徴を活かした効果的な質問の仕方や、得られた情報の活用法についても具体的に説明しています。

特に注目すべきは、Perplexity Pro の「Pro Search」機能です。本書では、この有料サービスが他の生成型 AI の有料サービスを利用する必要がないほどの高い性能を持つことを詳しく解説しています。マルチステップ推論、高度な数学・プログラミング能力、より深い検索と分析、リアルタイムデータアクセス、多言語サポートなど、Pro Search の優れた機能を最大限に活用する方法を学べます。

■ こんな方におすすめ

  • ビジネスパーソン:市場調査、競合分析、戦略立案に活用したい方
  • 研究者・学生:学術情報の効率的な収集と分析に興味がある方
  • 語学学習者:AI を活用した効果的な学習方法を知りたい方
  • IT プロフェッショナル:最新の AI 技術とその応用に関心がある方
  • 一般ユーザー:日常生活での情報収集や問題解決に AI を活用したい方

■ 著者について

本書の著者は、AI 技術と情報検索の分野で豊富な経験を持つ専門家です。最新の技術動向に精通し、実務での AI 活用にも深い知見を有しています。著者情報: https://amazon.com/author/charlychoi

■ 目次

序章

第1章 Perplexityとは?

1.1 Perplexityの概要

1.2 Perplexityの特徴と強み

1.3 Perplexityが検索をどのように変えるのか

第2章 Perplexityを使いこなすコツ

2.1 効果的な問い合わせ方法

2.2 検索オプションの活用法

2.3 検索結果の絞り込み方

2.4 検索履歴の活用法

第3章 Perplexityで様々な情報検索と文章を書く方法

3.1 全ての情報を探す

3.2 学術情報を探す

3.3 数学的問題を解決する

3.4 テキストやチャットを作成する

3.5 ビデオコンテンツを探す

3.6 ソーシャルメディアの情報を探す

第4章 Perplexityを業務に活かす

4.1 ビジネスにおける情報収集

4.2 マーケティングとリサーチへの活用

4.3 職場での問題解決と意思決定

4.4 専門スキルの習得と自己啓発

4.5 各種契約書および法律文書の分析

第5章 Perplexityの応用的な使い方

5.1 AIとの対話を通じた知識の探求

5.2 外国語の学習とコミュニケーション

5.3 創作活動とアイデア発想への活用

第6章 Perplexityの未来と可能性

6.1 AIと検索技術の進化

6.2 Perplexityの新機能と改良

6.3 社会とビジネスにもたらす変革

終章


Amazon Kindle Store : https://bit.ly/4cAmXlP









Apr 16, 2024

[Kindle Book] Mastering Claude AI: Empowering Writers and Professionals with AI: Opening a New Horizon for AI Utilization



Unlock the Power of AI Writing and Business Innovation with "Mastering Claude AI"

Are you ready to revolutionize your writing process and take your business to new heights? "Mastering Claude AI: Empowering Writers and Professionals with AI" is your ultimate guide to harnessing the unparalleled potential of Claude AI, a groundbreaking conversational AI that outshines even the renowned ChatGPT.


In this transformative book, you'll discover how Claude's advanced natural language processing capabilities and vast knowledge base can elevate your writing skills and drive innovation across various business domains. From crafting compelling content to analyzing complex data, "Mastering Claude AI" provides you with the practical strategies and real-world examples you need to leverage AI for unprecedented success.


Inside, you'll find:

  • An in-depth exploration of Claude's superior features, including its outstanding conversational skills, powerful writing performance, and ability to understand context and generate original ideas

  • Step-by-step guidance on prompt engineering, the key to unlocking Claude's full potential and tailoring its outputs to your specific needs

  • Real-world case studies and hands-on exercises demonstrating Claude's applications in writing, data analysis, information summarization, and visualization

  • Invaluable tips and techniques for applying Claude to various business tasks, such as document creation, academic research support, investment analysis, and HR management

  • Eye-opening insights into the ethical considerations and best practices for collaborating with AI in a business setting


"Mastering Claude AI:Empowering Writers and Professionals with AI

Opening a New Horizon for AI Utilization" is not just a book; it's a roadmap to the future of writing and business innovation. By embracing the harmonious collaboration between human expertise and artificial intelligence, you'll gain a competitive edge and unlock new possibilities for growth and success.


Whether you're a professional writer, a business leader, or an entrepreneur seeking to stay ahead of the curve, this book is your essential guide. Join the AI revolution and discover how Claude can become your ultimate partner in writing excellence and business transformation.

Don't miss out on this opportunity to master the art of AI-powered writing and innovation. Get your copy of "Mastering Claude AI" today and embark on a journey that will redefine your approach to writing and business forever.


This innovative book guides readers through discovering Claude, an advanced conversational AI that transforms writing. The author shares personal experiences and insights to show how Claude's power can be harnessed to boost creativity, simplify writing, and open up new possibilities in diverse domains.

  1. Chapter 1: The Author's Journey with Claude The author shares their personal account of encountering Claude and the profound impact it had on their writing process, leading to the creation of this guide.
  2. Chapter 2: The Rise of Generative AI and Claude's Capabilities This chapter explores the development of generative AI technology, including Claude, and examines the advancements in natural language processing. It highlights Claude 3's core features and the value it brings to writers.
  3. Chapter 3: Mastering Prompt Engineering Chapter 3 focuses on prompt engineering, the key to effectively utilizing Claude. It covers the concept and importance of prompts, methods for designing effective prompts, and optimization strategies for various genres, accompanied by practical prompt examples.
  4. Chapter 4: Writing a Book with Claude The author shares their experience of completing a book in collaboration with Claude, from topic selection and outlining to writing and proofreading. Readers will gain valuable insights into Claude-based book writing and creative writing tips.
  5. Chapter 5: Expanding Claude's Applications in Business The final chapter explores Claude's potential in business settings, such as document creation, data analysis, academic research support, and solutions for investment, finance, and HR tasks. It presents a blueprint for Claude's role in the global business environment.

Appendix: Hands-on Examples of Claude Utilization The appendix provides carefully selected examples of Claude utilization that readers can practice directly, including Gmail analysis, chart creation, and SQL query generation.


Contents:
Introduction
Chapter 1: The AI Writing Revolution with Claude
1.1 What is Claude?
1.2 The Purpose and Structure of This Book
Chapter 2: Understanding Generative AI and Its Application in Writing
2.1 The Concept and Development Process of Generative AI
2.2 Overview and Characteristics of the Claude 3 Model
Chapter 3 Mastering the Claude prompt
3.1 The Concept and Importance of Prompts
3.2 Effective Prompt Writing Techniques
3.3 Prompt Utilization Tips for Creative Writing
3.4 Prompt Engineering Techniques Applicable to Claude
3.5 Genre-Specific Prompt Optimization Strategies
3.6 Techniques for structuring your writing and generating ideas using prompts
3.7 Methods for improving and advancing prompts
Chapter 4: The Process of Writing Practical Books Using Claude
4.1 The Role of the Author
4.2 Writing Titles and Subtitles
4.3 Structuring the Table of Contents
4.4 Writing Main Content for Each Chapter in Collaboration with Claude
4.5 Utilizing Claude in the Proofreading, Editing, and Revision Process
Chapter 5: Business Application Strategies for Claude
5.1 Utilizing Claude for Business Document Creation and Analysis
5.2 Utilizing Claude in Legal and Contract-Related Work
5.3 Utilizing Claude in Research Institutes and Academic Fields
5.4 Leveraging Claude for Data Analysis and Report Writing
5.5 Utilizing Claude for Investment and Finance-Related Tasks
5.6 Utilizing Claude in HR and Organizational Management
5.7 Utilizing Claude in the Global Business Environment
Conclusion
Appendix 1: Generating Graphs and Charts with Python Code
Appendix 2: The Process of Generating SQL Statements from Natural Language Queries
Appendix 3: Analyzing Large-scale Gmail Logs with Natural Language
Appendix 4: List of Claude Prompt Engineering Techniques
Appendix 5: Using Claude for Proofreading, Editing, and Revision

Mar 24, 2024

[Claude AI Tips] How Claude makes your business work better - 1

 How Claude makes your business work better - 1



Notes: This article is adapted from a white paper posted on Antropic's homepage 'Prompt engineering for business performance' [1]

This is an in-depth analysis and adaptation of the whitepaper with the same title. (** Adapted using Claude)

Prompt engineering is an important tool for optimizing Claude's performance. Well-designed prompts improve Claude's output results, reduce deployment costs, and ensure that the customer experience is on brand.

One Fortune 500 company leveraged effective prompt engineering to build a Claude-powered assistant that answers customer questions more accurately and quickly.

When building generative AI models in your business, crafting effective prompts is critical to achieving high-quality results. With the right prompts, businesses can unlock the full potential of AI to increase productivity across a variety of tasks.

Anthropic's Prompting Engineering team is helping Fortune 500 companies build customer-facing chat assistants that answer complex questions quickly and accurately.

Benefits of designing effective prompts include

  • Improved accuracy:Effective prompts can further reduce the risk of inaccurate output.
  • Maintain consistency: Well-designed prompts ensure that Claude produces consistent results in terms of quality, format, relevance, and tone.
  • Increase usability: Prompt engineering helps Claude deliver experiences that are customized for the desired audience and industry.
  • Reduce costs: Prompt optimization can minimize unnecessary iterations and save money.

Claude is an AI assistant that can perform a variety of tasks through natural conversations with you. You can give Claude instructions in everyday language, just like you would ask a human, and the quality of the instructions you provide can have a significant impact on the quality of Claude's output. Clear, well-organized instructions are especially important for complex tasks.

The directives you give Claude are called "prompts". Prompts are often in the form of questions or instructions, and serve to guide Claude to generate relevant output. For example, if you give Claude the prompt "Why is the sky blue?", Claude will generate an appropriate answer. The text that Claude produces in response to a prompt is called a "response", "output", or "completion".

Claude is an interactive assistant based on a Large Language Model (LLM) that works through sequence prediction, which means that it considers both the prompt you type and the text it has generated so far, and builds a response by predicting the next word or phrase that will be most helpful. At the same time, Claude can only process information within a context window of a set length, so it can't remember previous conversations unless you include them in the prompt, and it can't open links.

If you want to have a conversation with Claude, you can use the web interface at claude.ai, or you can get started quickly via the API. The maximum length of your prompts is limited by the size of Claude's contextual window, so be sure to check the contextual window size of the model you're using.

More advanced techniques and tips for creating more effective prompts are covered in the topic 'Prompt Engineering'. The Prompt Engineering guide explains in detail how to design prompts with best practices, things to watch out for, real-world examples, and more. We encourage you to try different prompts and techniques and observe how they affect Claude's response and performance.

Anthropic also provides a large collection of prompt examples for different use cases in the 'Prompt Library'. If you need ideas or want to see how Claude can be utilized to solve a specific problem, the Prompt Library is a great place to start.

Finally, Anthropic also offers experimental "helper metaprompts" that guide Claude to generate prompts based on guidelines you provide. These can be useful for creating initial prompts or for quickly generating different prompt variations.

As you can see, Claude is a powerful AI assistant that can perform a variety of tasks through conversations with you. With prompt engineering and a library of prompts, you can unlock Claude's full potential. We encourage you to try out different prompts and share your results with Anthropic's Discord community.

Prompt engineering is a critical tool for companies looking to leverage Large Language Models like Claude to drive business outcomes. Well-designed prompts can help improve the quality of Claude's output, reduce deployment costs, and ensure that customer experiences are consistent and on-brand. In fact, one Fortune 500 company built a Claude-powered customer-facing assistant through effective prompt engineering, which led to significant improvements in accuracy and speed.

As organizations adopt generative AI models, effective prompting is essential to achieving high-quality results. With the right prompts, you can unlock the full potential of AI to increase productivity across a variety of tasks. Effective prompts can improve the accuracy of your output, ensure consistency in quality, format, relevance, and tone, and deliver experiences that are tailored to your desired audience and industry. They can also save you money by minimizing unnecessary repetitive tasks.

Here are three tips for utilizing prompted engineering in your business.

First. Apply step-by-step thinking

When solving a complex problem or making a decision, step by step is a technique for breaking down a problem into smaller steps that are analyzed and solved sequentially. This allows you to understand the problem more clearly and approach it in a systematic way. Especially when working with AI models, applying step by step can make the model's reasoning process explicit, increasing the logic and reliability of the answer.

There are two ways to apply step-by-step thinking to prompted engineering. The first is to use the "<thinking>" tag, and the second is to include "Think step by step" directly in the prompt.

1. Use the "<thinking>" tag:

The <thinking> tag allows you to explicitly represent the model's reasoning process. The user can see the model's thought process step by step, making it easier to understand the rationale behind the answer. In addition, the content within the <thinking> tag can be excluded from the final output or processed separately, avoiding exposing unnecessary information to the user.

2. Include "Think step by step" prompts:

Including "Think step by step" directly in the prompt is to instruct the model to analyze the problem step by step and show the intermediate steps. This method can be simpler and more intuitive than using the <thinking> tag.

The main differences between the two methods are

1. output format:

- Use the <thinking> tag to clearly separate the model's thinking process from the final answer.

- With "Think step by step", the model's thought process and final answer are presented in one output.

2. Easy to extract information:

- The <thinking> tag makes it easy for users to extract the part they want (final answer or intermediate thought process).

- When using "Think step by step", additional post-processing may be required to extract only the part the user wants.

3. Prompt engineering considerations:

- When using the <thinking> tag, you must design your prompts with the tag usage and structure in mind.

- When using "Think step by step", the model's thought process is directly exposed in the prompt, so the prompt should be written with this in mind.

The Think step by step technique can be used in a variety of areas, such as analyzing legal issues, constructing investment portfolios, creating marketing strategies, human resources assessments and feedback, and managing project schedules. However, you don't need to use it in every situation, and it's flexible enough to adapt to the nature of the task and your needs. For simple questions or clear instructions, it might be more effective to skip the step-by-step thought process and just present the final answer. On the other hand, for complex problems or tasks that involve helping users make decisions, it might be useful to utilize a step-by-step thought process to explain in detail the model's reasoning process.

It is very useful to analyze and solve problems using a step by step thinking technique. The <thinking> tag allows you to explicitly show the reasoning behind your model, making your answers more logical and reliable. Here are some examples of how it can be utilized

The step-by-step thinking technique utilizing the thinking> tag can be utilized in a variety of areas. When a model explicitly shows intermediate thought processes, users can easily see the logical flow of answers and ask additional questions or request corrections as needed. It also helps to debug and improve the model's reasoning process. However, this technique should not be used in every situation, and can be flexibly applied to suit the nature of the task and the needs of the user.

1. Analyze the legal issues:

Prompt: "Identify the issues in the case presented, and analyze your anticipated ruling based on relevant law and precedent, using the <thinking> tag to explain step-by-step."

2. Investment portfolio construction:

Prompt: "Considering the client's investment objectives and risk tolerance, suggest the optimal asset allocation for him/her. Show the portfolio construction process step-by-step with <thinking> tags."

3. Develop a marketing strategy:

Prompt: "Analyzing the characteristics of the product and the target audience, suggest effective marketing channels and messages. Using <thinking> tags, describe the strategy formulation process step by step."

4. Human Resources Assessment and Feedback:

Prompt: "Evaluate an employee's job performance and competencies, and suggest ways to improve. Use <thinking> tags to show the steps in the evaluation process and the process of deriving feedback."

5. Manage project schedules:

Prompt: "Analyzing the project's work and resources, develop an optimal schedule for the project. Using <thinking> tags, describe the process of developing the schedule step by step."

For example,

Prompt: Evaluate an employee's job performance and competencies, and suggest ways to improve. Use the <thinking> tag to show the steps in your evaluation process and feedback."

Explanation: This prompt asks Claude to analyze an employee's job performance and competencies and provide suggestions for improvement. By specifying that Claude thinks step-by-step using the <thinking> tag rather than simply drawing a conclusion, it encourages Claude to analyze the problem systematically and provide an accurate response.

The difference in prompting with and without the <thinking> tag can be described as follows

1. with the <thinking> tag:

  • You are explicitly asking the model to show you the thought process of the intermediate steps.
  • The model will explain in detail, step by step, the reasoning process that led to the final answer.
  • Users can easily understand the model's thought process and see the logical basis for the answer.
  • The content within the thinking> tag can be excluded from the final output or handled separately, so you don't expose unnecessary information to the user.

Example:

Prompt:

Evaluate an employee's job performance and competencies, and suggest ways to improve. Use the <thinking> tag to show us step-by-step the process of evaluation and deriving feedback."

Claude answers:

<Thinking>

Step 1: Know who your employees are and what they do

  • Name: Jiyoung Kim
  • Job Title: Representative
  • Department: Marketing.
  • Primary responsibilities: Marketing campaign planning and execution, market research, customer data analysis.

Step 2: Evaluate your performance

  • Planning and executing marketing campaigns: You have above-average performance based on goal achievement and ROI analysis of recent campaigns. Creative ideas and organized execution stand out.
  • Market research: Analyzed competitors and identified trends, generating useful insights, but needs to work on better utilization of findings.
  • Customer data analysis: Good data analytics capabilities, contributing to customer segmentation and targeting. However, strategic recommendations based on analytics are somewhat lacking.

Step 3: Assess competencies

  • Communication skills: Communicates and collaborates well within the team and with other departments. Possesses persuasive presentation skills.
  • Problem-solving skills: Proactively seeks solutions to work challenges and offers creative ideas.
  • Subject matter expertise: You have knowledge and skills in marketing and data analytics, but need to continue learning and developing your skills.
  • Leadership: Your ability to lead and motivate team members has room for improvement.

Step 4: Identify ways to improve

  • Better utilize your market research findings: Develop specific action plans based on research findings and enhance sharing with relevant departments.
  • Strengthen data analytics capabilities: Focus on deriving strategic insights from customer data analysis and incorporate them into marketing strategies.
  • Professionalize your work: Learn the latest trends and techniques in marketing and data analytics, and develop your skills through participation in external training programs.
  • Develop leadership skills: Provide coaching and feedback to grow and empower team members, and drive communication and collaboration within the team.

</thinking>

Evaluation results and feedback:

Ms. Kim has shown excellent performance in planning and executing marketing campaigns, conducting market research, and analyzing customer data. We particularly appreciate her creative ideas, systematic execution, and data analysis capabilities.

However, we believe that you need to focus more on utilizing market research results and deriving strategic insights through data analysis. To this end, we recommend that you develop specific action plans and strengthen collaboration with relevant departments.

We also encourage you to further professionalize your work through continuous learning and competency development. We encourage you to learn about the latest trends and techniques in marketing and data analytics, and to participate in external training programs.

In terms of leadership skills, we expect you to be committed to the growth and empowerment of your team members. Providing coaching and feedback to team members, and driving communication and collaboration within the team will help you become a better leader.

We recognize your talent and growth potential and look forward to your continued contributions to the company. We hope you will take the suggested improvements into consideration and further develop your performance and capabilities.

2. without the <thinking> tag:

  • The model presents only the final answer and does not reveal the intermediate thought process.
  • It's hard for users to see how the model reached its conclusion.
  • The rationale or logical flow of answers may be unclear.
  • You may have difficulty debugging or refining the model's thought process.

Prompt: Evaluate an employee's job performance and competencies, and provide suggestions for improvement

Claude's answer:

Based on the employee information and job description, we evaluated your performance and competencies, and found that you performed well in the areas of marketing campaign planning and execution, market research, and customer data analysis. In particular, your creative ideas, systematic execution, and data analysis skills stood out.

However, there are some areas for improvement. We need to put more practical use of our market research findings and focus more on deriving strategic insights from data analysis. To this end, we recommend that you develop a concrete action plan and strengthen collaboration with relevant departments.

We also encourage you to continue to learn about the latest trends and techniques in marketing and data analytics to enhance your professionalism. We encourage you to develop your skills by participating in external training programs.

In terms of leadership, I would like to encourage you to provide coaching and feedback to your team members to help them grow and strengthen their capabilities, and to lead communication and collaboration within the team.

We recognize your high level of competence and growth potential, and look forward to seeing you take the suggested improvements to further develop your performance and capabilities.

Let's take a look at a possible application of "Think step by step" in the enterprise.

Example: Developing a marketing strategy for a new product launch.

Prompt:

My company is launching a new smartphone. The product's primary target audience is young people in their 20s and 30s, and we want to emphasize its innovative features and sleek design. Let's think step by step to create an effective marketing strategy.

Claude answers:

Step 1: Analyze your target audience.

- Understand the characteristics and needs of young people in their 20s and 30s

- Analyze the key features and design elements they expect in a smartphone

- Research their lifestyles, spending patterns, media consumption behaviors, etc.

Step 2: Identify product strengths and differentiators

- Innovative features: AI-powered camera, 5G support, high-capacity battery, etc.

- Sleek design: premium materials, bezel-less display, multiple color options, etc.

- Analyze how you stack up against the competition to highlight your points of differentiation

Step Three: Select marketing channels

- Select social media platforms frequented by your target audience (e.g., Instagram, YouTube, TikTok, etc.)

- Utilize online and mobile advertising channels (e.g., Google search ads, mobile app ads, etc.)

- Consider offline channels (e.g., outdoor advertising in college towns and younger demographics, pop-up stores, etc.)

Step Four: Develop a creative concept

- Establish key messages that highlight your product's strengths and differentiators

- Develop visuals and copy that appeal to the emotions of your target audience

- Maintain a tone and manner consistent with your brand identity

Step 5: Plan promotions and events

- Generate initial demand through pre-booked events

- Provide product experience opportunities (e.g., pop-up stores, road shows, etc.)

- Collaborating with social media influencers to promote your products

- Promote free gifts or discounts for customers who make a purchase

Step 6: Measure and optimize performance

- Set and monitor performance metrics for each marketing channel

- Optimize creative and messaging through A/B testing and more

- Analyze customer feedback and responses to modify and refine marketing strategy

Step 7: Manage long-term customer relationships

- Keep customers engaged by providing product usage tips and updates

- Foster brand loyalty by running loyalty programs

- Run promotions for existing customers at launch

By creating and executing your marketing strategy in the steps above, you'll be well on your way to a successful new product launch. It's important to be flexible and responsive to the insights gleaned from each step, and to continually monitor customer feedback to optimize your strategy.

Let's explain the difference between "Think step by step" with and without the prompt.

Prompt 1 (without Think step by step):

My company is launching a new smartphone. The main target audience for this product is young people in their 20s and 30s, and we want to emphasize its innovative features and sleek design. Please present your ideas for creating an effective marketing strategy.

Prompt 2 (Give Think step by step):

My company is launching a new smartphone. The primary target audience for this product is young people in their 20s and 30s, and we want to emphasize its innovative features and sleek design. Let's think step-by-step to create an effective marketing strategy.

Your model's answer to prompt 1 is likely to be a list of ideas for a marketing strategy-for example, they might list ideas like social media marketing, influencer collaboration, and giveaways. In this case, the connection or prioritization between the ideas is not clear, and it's difficult to see a systematic strategy development process.

On the other hand, if you assigned "Think step by step" to prompt 2, the model would present a step-by-step approach to creating a marketing strategy: analyze your target audience, identify product strengths and differentiators, select marketing channels, develop creative concepts, and so on, which would lead to subsequent steps such as planning promotions and events, measuring and optimizing performance, and managing long-term customer relationships.

This "Think step by step" allows the model to show a systematic thought process for solving a problem, so users can understand the context of strategy formulation and see the connections between each step. In addition, this step-by-step thought process can be used as a roadmap for actually creating and executing a marketing strategy.

In sum, without "Think step by step," you're more likely to get a list of sporadic ideas, whereas with it, you're likely to get an organized, sequential problem-solving process. So, for complex problems or situations that require strategy formulation, the "Think step by step" technique can be more effective.

---------------------------------------------------------------------

In the next post, we will discuss: 2. Utilizing Few-shot prompting , and third. Utilize prompt chaining techniques in more detail.