Custom Client GPTs

by

Consistent Brand Voice & Adherence to Brand Guidelines

Fine-tuned models can create copy that matches a brand’s voice and style.

On the left below is the standard model & on the right is the model trained on the brand voice & guidelines. Both models received the same instructions.

Which one do you think stuck closer to the brand? Which one is going to take less work before its ready for client review?

The Costs
—————-
1. This training was done with 10 data examples & for less than $1.
2. It uses GPT 4o Mini. The generation of 10 Google Ads headlines cost: 0.008 cents.


Submitted Brand Voice & Guidelines
——————————————–
Defined Brand Voice
1. Bold and Adventurous: Always trying new flavor combinations.
2. Fun Science Talk: Uses science words in a playful way to describe frozen treats.
3. Mix of Old and New: Combines childhood memories with new ideas.
4. Slightly Sarcastic: Uses gentle, self-aware humor.
5. Earth-Friendly: Often talks about sustainability and eco-friendly practices.

Brand Guidelines
Word Choice:
1. Call flavors “experiments” or “discoveries”
2. Use “creamologist” instead of “ice cream maker”
3. Call the store a “laboratory” or “flavor lab”

How to Write:
1. Mix short, snappy sentences with longer ones
2. Use at least one science word in every paragraph
3. End each product description with a question

Tone:
1. Sound excited and amazed, like each flavor is a new discovery
2. Use mild, family-friendly jokes about cold or science

What to Focus On:
1. Describe how the frozen treat looks, smells, and tastes
2. Talk about where ingredients come from and how they’re eco-friendly
3. Tell short, made-up stories about how each flavor was “discovered”

What Not to Do:
1. Never say “ice cream” – use creative alternatives
2. Don’t mention competitors or regular ice cream shops
3. Avoid overly cute or sweet language

Phrases to Use:
1. “Breakthrough in frozen delight technology”
2. “Quantum leap in flavor particles”
3. “Taste bud revolution”
4. “Eco-friendly brain freeze”

How Things Should Look:
1. Use colors like bright blue, neon green, and bright purple
2. Include science pictures like test tubes, atoms, and DNA in branding
3. Show nutrition facts as a “compound analysis”

How to Talk to Customers:
1. Call customers “fellow flavor explorers” or “taste pioneers”
2. Ask customers to share their own flavor ideas as “hypotheses”
3. Describe eating as “conducting a taste experiment”

Sentiment Analysis Tool

by

Problem Statement

  • Company Type: E-commerce
  • Problem: E-commerce companies need to quickly and efficiently analyze customer sentiment based on user reviews, feedback, and social media to gauge perception of new or existing product launches.
  • Challenge: Large numbers of user sentiments need to be efficiently analyzed close to real-time to provide timely feedback to the business.

Technical Approach

Languages & Tools:
  • Backend Development: Python & Flask
  • Frontend Interaction: JavaScript
  • Sentiment Analysis: OpenAI’s GPT Model
  • API Integration: OpenAI Python Package
  • User Interface: HTML & CSS
  • Asynchronous Requests: AJAX, Axios, Fetch API
  • Data Handling: JSON

– **Process:**

  – Details on setting up the Flask app, integrating OpenAI API for sentiment analysis, and creating a user-friendly interface with JavaScript.

Setting Up the Flask App

1. Install Python:
– Download and install the latest version of Python from the official website.

  1. Navigate to Python’s Official Website: Go to [https://www.python.org/downloads/][1] to find the latest version of Python. As of the latest information, Python 3.12.2 is the most recent stable release14.
  2. Choose the Correct Installer: Select the appropriate installer for your operating system. For Windows, you can choose from the Windows installer (64-bit) or Windows installer (32-bit) depending on your system architecture4.
  3. Run the Installer: After downloading the installer, run it on your machine. During the installation process, make sure to check the option to “Add Python to PATH” to ensure that Python is accessible from the command line


2. Create a Virtual Environment:
– Open Command Prompt and navigate to your project directory.
– Create a virtual environment: `python -m venv venv`.

3. Activate the Virtual Environment:
– Activate the virtual environment:
– On Windows: `.\venv\Scripts\activate`.



4. Install Flask:
– Install Flask within the virtual environment: `pip install Flask`.

5. Create Your Flask Application:
– In your project directory, create a new file named `app.py`.
– Initialize the Flask app by adding:
“`python
from flask import Flask
app = Flask(__name__)

@app.route(‘/’)
def hello_world():
return ‘Hello, World!’
“`

6. Run Your Flask Application:
– In Command Prompt, navigate to your project directory.
– Run the Flask app: `flask run`.
– Access the app in a web browser at `http://127.0.0.1:5000/`.


7. Integrate OpenAI API:
– Install the OpenAI Python package: `pip install openai`.
– Set up an endpoint in your `app.py` for sentiment analysis, using the OpenAI API to process the text.


8. Create a User-Friendly Interface with JavaScript:
– In your project directory, create a `templates` folder for HTML files.
– Use HTML & CSS to design the frontend, and JavaScript to handle user interactions.
– Implement AJAX calls from the frontend to your Flask backend for sentiment analysis.

9. Test the Complete Application:
– Ensure the Flask app is running.
– Open the web interface, input text for sentiment analysis, and view the results.

Code Snippets

API integration

import openai
...
   chat_completion = client.chat.completions.create(
        messages=system + user,
        model="gpt-3.5-turbo",
        max_tokens=60,
        top_p=1.0,
    )

Sentiment Analysis Logic

    system = [
        {"role": "system", "content": "You are a sentiment analysis bot designed to analyze feedback on various features of e-commerce products. \
        Your task is to identify specific features mentioned in a piece of feedback, assess the sentiment for each feature individually, \
        and classify them as positive, negative, mixed, or ambiguous. You should return the analysis in JSON format. \
        For example:\
        Feedback: 'The camera quality of this smartphone is outstanding, capturing vibrant colors and details. However, the battery life is disappointing, barely lasting a day with moderate use.'\
        Response: {\
        'features': {\
            'camera quality': 'positive',\
            'battery life': 'negative'\
            }\
        }\
        Another example: \
        Feedback: 'The laptop's screen is bright and crisp, making it great for watching movies, but I've had mixed feelings about the keyboard's responsiveness.'\
        Response: {\
        'features': {\
            'screen': 'positive',\
            'keyboard responsiveness': 'mixed'\
            }\
        }\
        And: \
        Feedback: 'The product dimensions were not as described, which was confusing.'\
        Response: {\
        'features': {\
            'product dimensions': 'ambiguous'\
            }\
        }\
        Always use this structured approach to ensure clarity and precision in sentiment analysis."}
    ]

Front-End Code for Displaying Results

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Sentiment Analysis Tool</title>
    <style>
        body { font-family: Arial, sans-serif; margin: 20px; }
        #result { margin-top: 20px; }
    </style>
</head>
<body>
    <h1>Sentiment Analysis</h1>
    <textarea id="textInput" rows="4" cols="50" placeholder="Enter text here..."></textarea>
    <button onclick="analyzeText()">Analyze Sentiment</button>
    <div id="result"></div>

    <script>
        async function analyzeText() {
            const textInput = document.getElementById('textInput').value;
            const response = await fetch('/analyze', {
                method: 'POST',
                headers: { 'Content-Type': 'application/json' },
                body: JSON.stringify({ text: textInput })
            });
            const data = await response.json();
            document.getElementById('result').innerText = 'Sentiment: ' + data.sentiment;
        }
    </script>
</body>
</html>

Strategic Thinking Practice Project for Junior Team Members

by

Project Title: Launch Campaign for Niche Product Line

Objective: Develop and execute a paid search campaign strategy for a new niche product line within a specific market segment, aiming to increase brand awareness and drive initial sales.

Scope:

  • Product Focus: A niche product line recently launched by the company, targeting a specific consumer group.
  • Target Market: Focus on one or two key markets where the product is expected to have high demand based on preliminary market research.
  • Budget: Defined starting budget with scope for adjustment based on early performance indicators.
  • Duration: 3-month campaign period with weekly reviews and adjustments.

Key Learning Areas:

  1. Market Research:
    • Conduct detailed market research to understand the target audience, including demographics, search behaviors, and preferences.
    • Analyze competitors in the niche market to identify gaps and opportunities.
  2. Keyword Strategy:
    • Develop a keyword strategy that targets the specific niche audience, utilizing both broad and long-tail keywords.
    • Use AI tools for keyword research and selection to maximize reach and efficiency.
  3. Ad Copy Creation:
    • Craft compelling ad copy that resonates with the niche audience, highlighting unique product features and benefits.
    • Experiment with different ad formats and messaging themes to test audience response.
  4. Campaign Setup and Management:
    • Set up the campaign in chosen paid search platforms, configuring targeting options, bidding strategies, and ad scheduling based on the strategic plan.
    • Monitor campaign performance closely, making necessary adjustments to bids, keywords, and ad copy based on data analysis.
  5. Performance Analysis and Reporting:
    • Utilize analytics tools to track campaign performance, focusing on metrics such as CTR, conversion rate, and ROI.
    • Prepare weekly performance reports detailing key insights, learnings, and adjustments made, to be reviewed with the mentor or team leader.
  6. Strategic Review and Optimization:
    • Conduct a comprehensive mid-campaign review to evaluate strategy effectiveness, incorporating feedback for optimization.
    • Explore advanced targeting and retargeting strategies to enhance audience engagement and conversion rates.

Outcome:

  • A comprehensive report detailing the entire process from planning to execution, including strategy rationale, campaign performance analysis, challenges faced, and key learnings.
  • A final presentation to the team, sharing insights, successes, and recommendations for future campaigns based on the project’s outcomes.

This project aims to provide junior members with hands-on experience in developing and managing a strategic paid search campaign, from concept to completion, fostering their strategic thinking and practical skills in paid search marketing.

Soft Prompting

by

Soft Prompting: If requesting exactly what you want is a “hard” prompt, a “soft” prompt takes a more subtle approach. A soft prompt will use metaphors, tone of voice, or narratives to “guide” the model in the direction you want leaning into its ability to infer. 

Imagine stepping into a world where morning rituals are imbued with the essence of sustainability, where the aroma of freshly brewed coffee mingles with the promise of a greener planet. Picture the innovators and eco-conscious minds coming together, driven by a shared vision to redefine the daily coffee experience. They seek not just to innovate but to inspire a deeper connection with our environment—transforming sunbeams into the energy that powers the start of each day. Reflect on the journey of crafting a device so in harmony with nature that it becomes a beacon for those striving to make every choice count for the earth's well-being. Delve into the story of a solar-powered coffee maker, designed not just for the environmentally conscious coffee lover but as a testament to what's possible when we channel the power of the sun into our lives. How does this tale unfold, from the spark of conception through to the hands of those it was made for?

Contextual Embedding Prompting

by

Contextual Embedding Prompting: Including specific context or background information into the prompt for more relevant & accurate responses.

Given the launch of a groundbreaking solar-powered coffee maker, designed to appeal to environmentally conscious consumers who value sustainability and innovative technology, develop a comprehensive go-to-market plan. This plan should consider the product's unique selling points (USPs) – its eco-friendliness, use of renewable energy, and convenience for outdoor or off-grid use. Outline strategies that cover:

1. Market segmentation and targeting: Identify the key consumer segments that would highly value sustainability and technological innovation in coffee making.
2. Positioning: Suggest how to position the solar-powered coffee maker as a must-have for eco-conscious consumers, differentiating it from traditional electric coffee makers.
3. Launch strategy: Propose a timeline and key activities for the launch, including any events, partnerships with eco-friendly brands, or influencer collaborations that could amplify reach and engagement.
4. Marketing mix: Define the product pricing, channels (including online platforms and brick-and-mortar stores focusing on sustainable products), promotional tactics, and distribution strategies tailored to the target market.
5. Metrics for success: Identify key performance indicators (KPIs) and metrics that will be used to evaluate the effectiveness of the go-to-market plan, including sales targets, market penetration rates, and customer feedback.

Iterative Refinement Prompting

by

Iterative Refinement Prompting: Refine prompts based on previous responses for more accurate answers.

First Prompt (Few-Shot):

**Example 1:**

**Product:** Water-Saving Smart Shower Head

**Launch Overview:**
Market research revealed a growing concern among homeowners about water usage and environmental impact. The product was developed to provide real-time water usage data and eco-friendly shower experiences. Testing focused on user interface usability and water-saving efficiency. Branding emphasized water conservation and smart home integration. The marketing strategy leveraged environmental blogs, social media engagement, and partnerships with eco-friendly home builders. Sales were directed through online retailers and home improvement stores. Customer service offered detailed installation guides and water-saving tips. The product successfully resonated with eco-conscious homeowners, addressing the need for water conservation efficiently.

**Example 2:**

**Product:** Compact Compost Bin for Urban Dwellers

**Launch Overview:**
Identifying the challenge of composting in limited spaces, market research pinpointed urban apartment dwellers seeking sustainable waste solutions. The development aimed at creating a smell-free, compact compost bin with a sleek design. Testing ensured the compost bin effectively managed waste without attracting pests. Branding focused on sustainability and modern aesthetics, appealing to environmentally minded city residents. Marketing used urban gardening blogs, social networks, and city lifestyle influencers to spread the word. Sales strategies included online marketplaces and eco-friendly stores. Customer service provided composting tips and troubleshooting advice, enhancing user experience. The product successfully introduced urban dwellers to easy and effective composting at home.

**Your Task:**

Introduce a **Solar-Powered Coffee Maker** designed for environmentally conscious consumers. It should highlight market research, development, testing, branding, marketing strategy, and execution. Detail how it appeals to eco-friendly coffee enthusiasts and differentiates from traditional electric coffee makers.

First Response:

Product: Solar-Powered Coffee Maker

Launch Overview:

In response to increasing environmental concerns and the growing demand for sustainable lifestyle products, the Solar-Powered Coffee Maker was introduced...

Now we introduce the Iterative Refinement Prompt:

Given the initial marketing plan for our solar-powered coffee maker, which focuses on sustainability and innovation, how can we refine our approach to improve audience engagement and adoption rates? Please suggest adjustments or additions that could enhance our strategy, taking into account emerging consumer behaviors and competitive market analysis.

Personalized Prompting

by

Personalized Prompting: Tailoring your prompt to receive a response back that is directly relevant (personalized) to your situation and/or needs.

Based on your understanding of marketing principles, sustainable product trends, and consumer behavior analytics, what comprehensive strategies would you recommend for the successful launch of a solar-powered coffee maker, considering the general objectives of maximizing reach, engagement, and positive reception among a broad yet sustainability-conscious audience?

Exploratory Prompting

by

Exploratory Prompting: Encourage the model to generate new ideas or hypotheses to explore new concepts.

Exploring the depths of your knowledge on consumer behavior, trends in sustainability, and effective marketing strategies, what insights can you share regarding the potential obstacles and prospects encountered when introducing a solar-powered coffee maker to the market? Delve into the crucial aspects that should be taken into account for successful marketing and broad consumer adoption. Furthermore, can you suggest inventive marketing tactics that could distinctly highlight the product's sustainable and innovative features in a competitive landscape?