Update app.py

app.py

@@ -27,7 +27,7 @@ except Exception as e:
 
 def create_performance_comparison():
     """
-    Generates a bar chart comparing the current 2GB VRAM setup with an upgraded GPU.
+    Generates a bar chart comparing current setup with upgraded GPU.
     """
     categories = [
         'AI Model Loading',
@@ -41,8 +41,8 @@ def create_performance_comparison():
     potential_values = [100, 100, 100, 100, 100, 100]
     
     fig = go.Figure(data=[
-        go.Bar(name='Current Setup (2GB VRAM)', x=categories, y=current_values, marker_color='#FF6B6B'),
-        go.Bar(name='Potential (Upgraded GPU)', x=categories, y=potential_values, marker_color='#4ECB71')
+        go.Bar(name='Current Setup (2GB VRAM)', x=categories, y=current_values, marker_color='#2D3748'),
+        go.Bar(name='Potential (Upgraded GPU)', x=categories, y=potential_values, marker_color='#4A5568')
     ])
     
     fig.update_layout(
@@ -53,12 +53,11 @@ def create_performance_comparison():
         font={'family': 'Arial', 'size': 14},
         legend={'orientation': 'h', 'x': 0.2, 'y': 1.1}
     )
-    logging.debug("Performance comparison chart created.")
     return fig
 
 def create_roi_projection():
     """
-    Creates a 24-month ROI projection chart comparing current revenue growth with projected revenue after a GPU upgrade.
+    Creates a 24-month ROI projection chart.
     """
     months = list(range(1, 25))
     base_revenue = 1000
@@ -75,11 +74,11 @@ def create_roi_projection():
     fig = go.Figure()
     fig.add_trace(go.Scatter(
         x=months, y=current_revenue, name='Current Revenue',
-        line={'color': '#FF6B6B', 'width': 3}
+        line={'color': '#2D3748', 'width': 3}
     ))
     fig.add_trace(go.Scatter(
         x=months, y=projected_revenue, name='Projected Revenue with GPU Upgrade',
-        line={'color': '#4ECB71', 'width': 3}
+        line={'color': '#4A5568', 'width': 3}
     ))
     
     fig.update_layout(
@@ -90,12 +89,11 @@ def create_roi_projection():
         font={'family': 'Arial', 'size': 14},
         legend={'orientation': 'h', 'x': 0.3, 'y': 1.1}
     )
-    logging.debug("ROI projection chart created.")
     return fig
 
 def calculate_loan_details(loan_amount, interest_rate=5.0):
     """
-    Calculates and returns a detailed monthly breakdown of a loan repayment schedule.
+    Calculates detailed monthly loan repayment schedule.
     """
     try:
         amount = float(loan_amount)
@@ -129,7 +127,6 @@ def calculate_loan_details(loan_amount, interest_rate=5.0):
                 schedule += f"- {date.strftime('%B %Y')}: ${monthly_payment:,.2f} (Principal: ${principal:,.2f}, Interest: ${interest:,.2f})\n"
         
         schedule += f"\n**📊 Total Interest Paid:** ${total_interest:,.2f}"
-        logging.debug("Loan repayment schedule calculated.")
         return schedule
     except ValueError:
         return "⚠️ Please enter a valid loan amount"
@@ -140,7 +137,7 @@ def calculate_loan_details(loan_amount, interest_rate=5.0):
 
 def robust_web_scrape_agent(url):
     """
-    Extracts meaningful content from a URL using multiple user-agents and fallback methods.
+    Extracts content from URL using multiple user-agents and fallback methods.
     """
     user_agents = [
         "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/115.0.0.0 Safari/537.36",
@@ -148,157 +145,75 @@ def robust_web_scrape_agent(url):
         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 Chrome/114.0.0.0 Safari/537.36",
     ]
     headers = {'User-Agent': random.choice(user_agents)}
-    logging.debug("Fetching URL: %s with headers: %s", url, headers)
     
     try:
         response = requests.get(url, headers=headers, timeout=10)
         if response.status_code != 200:
-            logging.error("Error fetching URL %s: Status code %s", url, response.status_code)
             return f"Error: Received status code {response.status_code}"
         
-        # Parse HTML using BeautifulSoup and strip unwanted tags
         soup = BeautifulSoup(response.text, "html.parser")
         for tag in soup(["script", "style", "noscript"]):
             tag.decompose()
         text = soup.get_text(separator="\n").strip()
-        logging.debug("Initial extraction length: %d", len(text))
         
-        # Fallback: Use readability if text is too short
         if not text or len(text) < 200:
-            logging.warning("Insufficient content extracted; using fallback extraction.")
             try:
                 from readability import Document
                 doc = Document(response.text)
                 extracted_html = doc.summary()
                 fallback_soup = BeautifulSoup(extracted_html, "html.parser")
                 text = fallback_soup.get_text(separator="\n").strip()
-                logging.debug("Fallback extraction length: %d", len(text))
             except ImportError:
-                logging.error("Readability module not available. For better extraction, install readability-lxml.")
+                logging.error("Readability module not available.")
             except Exception as fallback_error:
                 logging.error("Fallback extraction failed: %s", fallback_error)
         
-        if not text or len(text) < 200:
-            logging.error("No substantial content found at URL: %s", url)
-            return "No substantial content found."
-        
-        logging.info("Content extracted successfully from %s", url)
-        return text
+        return text if text and len(text) >= 200 else "No substantial content found."
     except Exception as e:
-        logging.exception("Exception during web scraping:")
         return f"Error during scraping: {e}"
 
 def research_agent(query):
     """
-    Performs a web search using DuckDuckGo and returns formatted research results.
+    Performs web search using DuckDuckGo.
     """
     try:
         with DDGS() as ddgs:
             results = ddgs.text(query, max_results=5)
         if results:
-            formatted_results = "\n\n".join(
-                [f"**{result.get('title', 'No Title')}**:\n{result.get('href', 'No URL')}" for result in results]
-            )
-            logging.debug("Research results for query: %s", query)
-            return formatted_results
-        else:
-            logging.info("No research results for query: %s", query)
-            return "No results found."
+            return "\n\n".join([f"**{result.get('title', 'No Title')}**:\n{result.get('href', 'No URL')}" for result in results])
+        return "No results found."
     except Exception as e:
-        logging.error("Error during research: %s", e)
         return f"Error during research: {e}"
 
 def report_agent(data):
     """
-    Generates a summary report using a transformer model.
+    Generates summary report using transformer model.
     """
     try:
         if not report_summarizer:
-            return "Report summarization is not available (check your framework installations)."
+            return "Report summarization is not available."
         if len(data.split()) < 30:
-            return "Input text is too short to generate a summary. Please provide more details."
+            return "Input text is too short for summarization."
         summary = report_summarizer(data, max_length=130, min_length=30, do_sample=False)
-        logging.debug("Summary report generated.")
         return summary[0]['summary_text']
     except Exception as e:
-        logging.error("Error during report generation: %s", e)
         return f"Error during report generation: {e}"
 
-def planning_agent(goal):
-    """
-    Generates a detailed step-by-step action plan based on the provided goal.
-    """
-    steps = [
-        f"Understand the requirements of '{goal}'.",
-        f"Break down the goal into smaller, manageable tasks.",
-        f"Prioritize the tasks and assign realistic timelines.",
-        f"Execute the plan while monitoring progress closely.",
-        f"Review outcomes and iterate as needed."
-    ]
-    logging.debug("Action plan generated for goal: %s", goal)
-    return "\n".join([f"Step {i+1}: {step}" for i, step in enumerate(steps)])
-
-def get_coordinates(city):
-    """
-    Retrieves geographical coordinates for a given city using the Nominatim API.
-    """
-    try:
-        url = f"https://nominatim.openstreetmap.org/search?city={city}&format=json"
-        response = requests.get(url, headers={'User-Agent': 'Mozilla/5.0'})
-        data = response.json()
-        if data:
-            logging.debug("Coordinates for %s: %s, %s", city, data[0]["lat"], data[0]["lon"])
-            return data[0]["lat"], data[0]["lon"]
-        return None, None
-    except Exception as e:
-        logging.error("Error fetching coordinates for %s: %s", city, e)
-        return None, None
-
-def weather_report_agent(city):
-    """
-    Fetches current weather information for the specified city.
-    """
-    lat, lon = get_coordinates(city)
-    if not lat or not lon:
-        return "City not found. Please check the city name."
-    try:
-        url = f"https://api.open-meteo.com/v1/forecast?latitude={lat}&longitude={lon}&current_weather=true"
-        response = requests.get(url)
-        data = response.json()
-        if "current_weather" in data:
-            weather_code = data["current_weather"]["weathercode"]
-            temp = data["current_weather"]["temperature"]
-            weather_mapping = {
-                0: "Clear sky", 1: "Mainly clear", 2: "Partly cloudy", 3: "Overcast",
-                45: "Fog", 48: "Depositing rime fog", 51: "Light drizzle",
-                53: "Moderate drizzle", 55: "Dense drizzle", 61: "Slight rain",
-                63: "Moderate rain", 65: "Heavy rain", 71: "Slight snowfall",
-                73: "Moderate snowfall", 75: "Heavy snowfall", 95: "Thunderstorm"
-            }
-            description = weather_mapping.get(weather_code, f"Code {weather_code}")
-            logging.debug("Weather data fetched for %s", city)
-            return f"Current weather in {city}:\nTemperature: {temp}°C\nCondition: {description}"
-        return "Could not fetch weather data."
-    except Exception as e:
-        logging.error("Error fetching weather data: %s", e)
-        return f"Error fetching weather data: {e}"
-
 ##########################################
 #         EARNINGS PLOT FUNCTION         #
 ##########################################
 
 def create_earnings_plot():
     """
-    Plots the earnings history using personal pay data.
+    Plots earnings history.
     """
-    # Hardcoded personal earnings data
     dates = ["2024-12-10", "2024-12-17", "2024-12-24", "2024-12-31", "2025-01-07",
              "2025-01-14", "2025-01-21", "2025-01-28", "2025-02-04", "2025-02-11"]
     earnings = [156.02, 73.10, 97.07, 116.11, 79.05, 86.62, 54.57, 86.36, 61.50, 79.18]
     
-    # Create a line chart with markers for personal earnings over time
     fig = go.Figure(data=go.Scatter(
-        x=dates, y=earnings, mode='lines+markers', line=dict(color='#4ECB71', width=3)
+        x=dates, y=earnings, mode='lines+markers', 
+        line=dict(color='#4A5568', width=3)
     ))
     fig.update_layout(
         title={'text': 'Personal Earnings History', 'font': {'size': 24}},
@@ -307,229 +222,128 @@ def create_earnings_plot():
         plot_bgcolor='white',
         font={'family': 'Arial', 'size': 14}
     )
-    logging.debug("Earnings plot created with %d data points.", len(dates))
     return fig
 
 ##########################################
 #            GRADIO INTERFACE            #
 ##########################################
 
-with gr.Blocks(theme=gr.themes.Soft(), css="""
-    .header {
-        background: linear-gradient(90deg, #4ECB71, #FF6B6B);
-        padding: 20px;
-        text-align: center;
-        color: white;
-        font-family: 'Arial', sans-serif;
-    }
-    .header h1 {
-        margin: 0;
-        font-size: 36px;
-    }
-    .header p {
-        margin: 3px 0 0;
-        font-size: 18px;
-    }
-""") as demo:
-    # Custom header section
+with gr.Blocks(theme=gr.themes.Default(
+    primary_hue="slate",
+    secondary_hue="slate",
+    neutral_hue="slate",
+    font=["Arial", "sans-serif"]
+)) as demo:
+    # Ko-fi banner at top
+    gr.HTML("""
+    <div style="background: #2D3748; color: white; text-align: center; padding: 10px; font-size: 16px;">
+        Support this project on <a href="https://ko-fi.com/waynesletcher" target="_blank" style="color: #A0AEC0; text-decoration: underline;">Ko-fi</a>
+    </div>
+    """)
+    
+    # Header
     gr.HTML("""
-    <div class="header">
-        <h1>🚀 Sletchy Systems</h1>
-        <p>Empowering Local Offline AI Assistants, RAG-Powered Tools & SaaS Solutions</p>
+    <div style="background: linear-gradient(90deg, #2D3748, #4A5568); padding: 20px; text-align: center; color: white;">
+        <h1 style="margin: 0; font-size: 36px;">Sletcher Systems: Business Expansion Proposal</h1>
+        <p style="margin: 10px 0 0; font-size: 18px;">Scaling AI Innovation through Strategic Investment</p>
     </div>
     """)
     
-    with gr.Tabs(selected=0, visible=True):
-        # Overview Tab: Vision, Core Competencies, and Live Demo
-        with gr.TabItem("🏢 Overview"):
+    with gr.Tabs():
+        # Executive Summary
+        with gr.TabItem("📋 Executive Summary"):
+            gr.Markdown("""
+            ### Vision & Opportunity
+            Sletcher Systems aims to scale our AI development capabilities through strategic GPU infrastructure investment.
+            
+            ### Current Challenges
+            - Limited by 2GB VRAM setup
+            - Running at capacity with current projects
+            - Unable to take on larger clients
+            
+            ### Investment Request
+            - Amount: $3,000 for GPU upgrade
+            - ROI Timeline: 12-24 months
+            - Clear path to expanded services
+            """)
+            gr.Plot(value=create_performance_comparison())
+
+        # Market & Technical Analysis
+        with gr.TabItem("📊 Market Analysis"):
             with gr.Row():
                 with gr.Column():
                     gr.Markdown("""
-                    ### 🎯 Our Vision & Mission
-                    **Sletchy Systems** is dedicated to revolutionizing AI with secure, innovative solutions based on Retrieval Augmented Generation (RAG). Though I leverage many free open source tools (Huggingface Spaces, Google Colab free T100s, UNSLOTH, Axylotyl, TensorBoard, TensorFlow, YOLO models, etc.), running my own inhouse AI system 24/7 demands a serious GPU upgrade.
+                    ### Target Market
+                    - Small to medium businesses
+                    - Educational institutions
+                    - Software development firms
                     
-                    **Focus Areas:**
-                    - **Local Offline AI Assistants:** Advanced systems using Microsoft Graph RAG and multimodel RAGs for uninterrupted operations.
-                    - **Developer Tools:** VS Code extensions that integrate AI into every part of your workflow.
-                    - **SaaS Offerings:** Automated platforms for image/document scanning, labeling, and processing.
-                    - **24/7 Agent Uptime:** Enabling continuous operation of advertising agents, personal assistants, and a mini research lab.
+                    ### Market Size
+                    - Local AI services market: $50M annually
+                    - 25% YoY growth
+                    - Untapped potential
                     """)
                 with gr.Column():
-                    gr.Markdown("""
-                    ### 💪 Core Competencies & Differentiators
-                    - **Resilience & Innovation:** Born from overcoming adversity as a broke, part-time teacher.
-                    - **Technical Mastery:** Advanced skills across open source and proprietary AI technologies.
-                    - **Revenue-Driven Vision:** Combining SaaS, AI assistants, and marketing automation to turn passion into profit.
-                    """)
-            gr.Markdown("### 🔍 Live Website Analysis Demo")
-            with gr.Row():
-                demo_url = gr.Textbox(label="Company Website", value="https://sletchersystems.com", lines=1)
-            demo_scrape_button = gr.Button("🔍 Analyze Website")
-            demo_output = gr.Textbox(label="Website Analysis", lines=10)
-            demo_scrape_button.click(robust_web_scrape_agent, inputs=demo_url, outputs=demo_output)
-        
-        # Web Research Tab: Search & Scrape Web Content
-        with gr.TabItem("🌐 Web Research"):
+                    gr.Plot(value=create_roi_projection())
+
+        # Technical Capabilities
+        with gr.TabItem("💻 Technical Stack"):
+            gr.Markdown("""
+            ### Current Stack
+            - Python, TensorFlow, PyTorch
+            - Web Development (React, Next.js)
+            - Cloud Infrastructure
+            
+            ### Planned Expansion
+            - Advanced AI Model Training
+            - Real-time Processing
+            - Expanded Service Offerings
+            """)
             with gr.Row():
-                url_input = gr.Textbox(label="Enter URL for Analysis", placeholder="https://example.com", lines=1)
-                research_query = gr.Textbox(label="Research Query", placeholder="Enter your research topic", lines=1)
+                demo_url = gr.Textbox(label="Analyze Website", value="https://sletchersystems.com")
+                demo_output = gr.Textbox(label="Analysis Results", lines=10)
+            demo_button = gr.Button("🔍 Analyze")
+            demo_button.click(robust_web_scrape_agent, inputs=demo_url, outputs=demo_output)
+
+        # Financial Plan
+        with gr.TabItem("💰 Financial Plan"):
             with gr.Row():
-                scrape_button = gr.Button("🔍 Scrape Website")
-                research_button = gr.Button("🔎 Research Topic")
+                loan_amount = gr.Number(label="Investment Amount ($)", value=3000)
+                interest_rate = gr.Slider(label="Annual Interest Rate (%)", value=5)
+            calculate_button = gr.Button("Calculate Repayment Schedule")
+            schedule_output = gr.Textbox(label="Repayment Details", lines=15)
+            calculate_button.click(calculate_loan_details, inputs=[loan_amount, interest_rate], outputs=schedule_output)
+            gr.Plot(value=create_earnings_plot())
+
+        # Research & Development
+        with gr.TabItem("🔬 R&D"):
             with gr.Row():
-                scrape_output = gr.Textbox(label="Scraped Content", lines=10)
+                research_query = gr.Textbox(label="Research Topic", placeholder="Enter research topic...")
                 research_output = gr.Textbox(label="Research Results", lines=10)
-            scrape_button.click(robust_web_scrape_agent, inputs=url_input, outputs=scrape_output)
+            research_button = gr.Button("🔎 Research")
             research_button.click(research_agent, inputs=research_query, outputs=research_output)
-        
-        # Performance Tab: Comparative charts
-        with gr.TabItem("📊 Performance"):
-            gr.Plot(value=create_performance_comparison())
-        
-        # ROI Tab: Revenue projections with added agent uptime benefits
-        with gr.TabItem("💰 ROI"):
-            gr.Plot(value=create_roi_projection())
-            gr.Markdown("""
-            **Key ROI Drivers:**
-            - **24/7 Inhouse AI System:** Upgrading the GPU lets my custom agents run nonstop, powering advertising, personal assistant functions, and a dedicated research lab.
-            - **Enhanced Productivity:** Faster model training and continuous operation will drive significant revenue increases.
-            - **Scaling Revenue:** Unlocking new income streams through SaaS solutions and game development projects.
-            """)
-        
-        # Earnings Tab: Display personal earnings and growth potential
-        with gr.TabItem("💸 Earnings"):
-            gr.Plot(value=create_earnings_plot())
-            gr.Markdown("""
-            **Personal Earnings Snapshot:**
-            - **Balance:** $38.25 (current pay period)
-            - **Recent Payments:** From $54.57 up to $156.02 over the past weeks.
-            
-            **The Harsh Reality:**
-            I’m a broke, part-time teacher scraping by on weekend work while studying documentation and building code projects—even a tiny social media app. I have not a dollar to my name. With a GPU upgrade, I can harness my skills to build websites for customers, automate marketing agents, and launch new SaaS projects that truly pay off.
-            """)
-        
-        # Investment Tab: Loan repayment details and financial breakdown
-        with gr.TabItem("📝 Investment"):
             with gr.Row():
-                loan_amount = gr.Number(label="Investment Amount ($)", value=3000, minimum=1000, maximum=10000)
-                interest_rate = gr.Slider(label="Annual Interest Rate (%)", minimum=1, maximum=10, value=5, step=0.5)
-            calculate_button = gr.Button("📊 Calculate Repayment Schedule", variant="primary")
-            schedule_output = gr.Textbox(label="Detailed Repayment Schedule", lines=15)
-            calculate_button.click(calculate_loan_details, inputs=[loan_amount, interest_rate], outputs=[schedule_output])
-        
-        # Report Generator Tab: Summarize content with AI
-        with gr.TabItem("📋 Report Generator"):
-            report_input = gr.Textbox(label="Enter Content for Summary", placeholder="Paste your text here...", lines=10)
-            report_button = gr.Button("📝 Generate Report")
-            report_output = gr.Textbox(label="Generated Summary", lines=6)
+                report_input = gr.Textbox(label="Report Text", placeholder="Enter report text...")
+                report_output = gr.Textbox(label="Report Summary", lines=10)    
+            report_button = gr.Button("📑 Summarize Report")
             report_button.click(report_agent, inputs=report_input, outputs=report_output)
-        
-        # Project Planning Tab: Actionable project goals and plans
-        with gr.TabItem("📅 Project Planning"):
-            planning_input = gr.Textbox(label="Enter Project Goal", placeholder="E.g., Launch new product line", lines=2)
-            planning_button = gr.Button("🎯 Generate Plan")
-            planning_output = gr.Textbox(label="Action Plan", lines=6)
-            planning_button.click(planning_agent, inputs=planning_input, outputs=planning_output)
-        
-        # Weather Monitor Tab: Get current weather info
-        with gr.TabItem("🌤️ Weather Monitor"):
-            city_input = gr.Textbox(label="Enter City Name", placeholder="e.g., London", lines=1)
-            weather_button = gr.Button("🌡️ Get Weather")
-            weather_output = gr.Textbox(label="Weather Report", lines=3)
-            weather_button.click(weather_report_agent, inputs=city_input, outputs=weather_output)
-        
-        # Personal Pitch Tab: Your journey, personal background, and a note for your dad
-        with gr.TabItem("💡 Personal Pitch"):
-            gr.Markdown("""
-            ### About Me & My Journey
-            **Name:** Wayne Sletcher  
-            **Age:** 33  
-            **Background:**  
-            I have overcome a challenging, traumatic childhood to become a resourceful, determined individual. As a part-time teacher and self-taught coder, I work weekends to build projects and harness new skills—even if it means scraping by on every paycheck.
-            
-            **Strengths & Struggles:**  
-            - **Strengths:** Resilience, technical ingenuity, and unwavering determination.  
-            - **Struggles:** Limited funds, a 2GB VRAM setup, and the constant battle to survive.
-            
-            **A Note for Dad:**  
-            Dad, I know you worry about me. What I do isn’t easy—it’s groundbreaking work that pushes the limits of free open source tools into a fully operational, inhouse AI system. This loan isn’t just about survival; it’s about thriving and turning my passion into a future where I can build profitable websites, automate marketing, and launch a range of lucrative projects.
-            """)
-        
-        # SaaS Solutions Tab: Detailed description of your revenue model and technical offerings
-        with gr.TabItem("🖥️ SaaS Solutions"):
+    # Implementation Plan
+        with gr.TabItem("📅 Timeline"):
             gr.Markdown("""
-            ### SaaS Offerings & Technical Stack
-            **Our Products:**
-            - **Image & Document Processing:**  
-              Automate scanning, labeling, and processing to train custom AI models on company data—driving actionable insights.
-            - **Local Offline AI Assistants:**  
-              Leverage Retrieval Augmented Generation (RAG) with advanced modalities (Microsoft Graph RAG, multimodel RAGs) for secure, offline operations.
-            - **Developer Tools:**  
-              Powerful VS Code extensions that integrate advanced AI functionalities into your workflow.
-            - **Advertising Agents & Game Development:**  
-              Innovative solutions that generate revenue through targeted advertising and immersive experiences.
-            
-            **Technical Stack & Tools:**  
-            - **Languages & Frameworks:** Python, Next.js, React  
-            - **AI & ML:** TensorFlow, PyTorch, LangChain, Transformers  
-            - **Model Management:** Huggingface Spaces, Google Colab (free T100s), UNSLOTH for fine-tuning, Axylotyl integrations, TensorBoard, YOLO models  
-            - **Databases & Cloud:** PostgreSQL with pgvector, MongoDB, AWS cloud infrastructure
-            
-            **Revenue Model:**  
-            By transforming free tools into a full-scale inhouse AI system, our SaaS offerings and custom solutions will create sustainable revenue streams through subscriptions, enterprise contracts, and project-based work.
-            """)
-        
-        # Business Plan Tab: A comprehensive look at the company strategy and future projections
-        with gr.TabItem("📈 Business Plan"):
-            gr.Markdown("""
-            ### Comprehensive Business Plan
-            
-            #### Executive Summary
-            Our mission is to lead the AI revolution by delivering secure, innovative solutions through Retrieval Augmented Generation (RAG). We target industries that need offline, privacy-compliant AI analytics while adhering to strict data privacy laws like POPIA.
+            ### Phase 1: Infrastructure (Month 1)
+            - GPU procurement and setup
+            - System integration
+            - Initial testing
             
-            #### Company Description
-            **Sletchy Systems** is a next-generation AI solutions provider specializing in:
-            - Local offline AI assistants (powered by Microsoft Graph RAG and multimodel RAGs)
-            - SaaS platforms for image and document processing
-            - Developer tools, advertising agents, and game development solutions
+            ### Phase 2: Service Expansion (Months 2-3)
+            - New service rollout
+            - Client outreach
+            - Project pipeline development
             
-            #### Market Analysis
-            - **Local Focus:** Tailored for the unique regulatory and infrastructure landscape.
-            - **Growth Opportunity:** Filling the gap for secure, offline AI systems and data-driven analytics.
-            - **Competitive Advantage:** Customized, privacy-compliant solutions that drive operational efficiency.
-            
-            #### Product Offerings
-            - **AI Assistants:** Local, offline systems that operate 24/7.
-            - **SaaS Platforms:** End-to-end solutions for document scanning, labeling, and processing.
-            - **Developer Tools:** Extensions that boost productivity and innovation.
-            - **Advertising & Game Development:** New revenue streams from targeted ads and immersive experiences.
-            
-            #### Marketing & Sales Strategy
-            - **Digital Outreach:** Targeted campaigns through social media and local tech events.
-            - **Partnerships:** Collaborations with businesses, universities, and tech incubators.
-            - **Global Vision:** Starting locally with plans to expand regionally.
-            
-            #### Financial Projections & ROI
-            - **Initial Investment:** Approx. ZAR 5 million in technology infrastructure.
-            - **Revenue Growth:** Projected breakeven by year two, driven by SaaS subscriptions, advertising, and enterprise deals.
-            - **Enhanced Agent Performance:** A GPU upgrade will power continuous inhouse AI operations—critical for scaling the business.
-            
-            #### Organizational Structure & Operations
-            - **Team:** A dedicated group of AI experts, developers, and strategic planners.
-            - **Operations:** Agile, scalable, and continuously evolving.
-            - **Risk Management:** Comprehensive strategies to address market, technological, and regulatory challenges.
-            
-            #### Fundraising & Implementation Timeline
-            - **Fundraising:** Equity crowdfunding, strategic grants, and partnership investments.
-            - **Timeline:** Rollout within six months, initially targeting SMEs and scaling regionally.
-            - **Contingencies:** Prepared strategies to mitigate risks and adapt to market changes.
+            ### Phase 3: Growth (Months 4-12)
+            - Market expansion
+            - Team growth
+            - Revenue scaling
             """)
-    
-    # Persistent Ko-fi donation banner (appears across all tabs)
-    gr.HTML("""
-    <div style="position: fixed; bottom: 0; width: 100%; background: #4ECB71; color: white; text-align: center; padding: 10px; font-size: 16px; z-index: 9999;">
-        Support my journey on <a href="https://ko-fi.com/waynesletcher" target="_blank" style="color: white; text-decoration: underline;">Ko-fi</a> and help me thrive!
-    </div>
-    """)
 
 demo.launch(share=True)