=================================

Recent Win ‣ #1 Product of the Day @ Product Hunt – July 13 2024 for "Sales Likelihood Calculator" – an interactive gamified checklist for sales-training I dev'd from scratch, wrapped in a fun 8-bit design.

Related Article I wrote ‣ Interpret your score from the calculator in the context of a Sales Pipeline Review. Includes many word-for-word questions to ask to explore & satisfy MEDDPICC buyer conditions to advance a sale toward the close.

🆕  I'm building an LLM application – AI RAG stack ‣ Next.js frontend, LlamaIndex, Firestore Vector KNN, Vertex AI, Llama 3.1. Claude 3.5 is my copilot for almost everything; it's f*cking incredible. Super fun!!

Rowe Morehouse visting Seoul Korea 서울 in 2024.

• 💲  Auditing SalesTech stack spend & effectiveness for a $20M bay area SaaS company.
• ✍  Writing call scripts, value messaging (my article), and "ROI impact statements" for complex sales; like enterprise software.
• 💬  Objection Handling training for Sales Enablement / Sales Management.
• 🌱  Coding on a SaaS product (RAG AI LLM backend) that helps new-client intake for personal injury attorneys – in natural language via a chat interface. Tuning context hyperparameters in a Vector DB w/ evals based a on data-set I created & cleaned. (see diagram below)
• 📈  Improving my GenAI prompt engineering skills w/ JSON input & output.
• 🧑‍🤝‍🧑  LinkedIn marketing w/ scraping from CLI to spreadsheets w/ outbound marketing messaging via automation tools.
• 📧  Using enrichment & personalization tools like Clay.
• 📊  SEO. Here's a gist I made for a curl command that pings IndexNow to get your pages instantly indexed.
• 🛠  Ecommerce optimizations for self-created info products I've been selling online since 2004.
• 😼  I like cats & techno music.
• 🏆  Eagle Scout.

Expanded Résumé CV ⇨ https://git.io/rowe

    graph TD
    A[User Query]
    Z[Next.js Front End]
    A --> Z
    Z --> B[Query Embedding]
    B --> C[Firestore Vector Store]
    C --> D[Retrieval]
    D --> E[Context Generation]
    A --> E
    E --> F[Vertex AI]
    F --> G[Llama 3.1 LLM]
    G --> H[Generated Response]
    H --> Z
    
    I[Raw Document Corpus] --> J[Data Cleaning]
    J --> K[Text Extraction]
    K --> L[Data Chunking]
    L --> M[Document Embedding]
    M --> C
    
    subgraph "Data Preprocessing"
    J
    K
    L
    end
    
    X1[LlamaIndex] --> L
    X2[LlamaIndex] --> B
    X3[LlamaIndex] --> D
    X4[LlamaIndex] --> E
    
    classDef orange fill:#ff9900,stroke:#333,stroke-width:2px,color:#000000;
    classDef blue fill:#00aaff,stroke:#333,stroke-width:2px,color:#000000;
    classDef pink fill:#f9f,stroke:#333,stroke-width:2px,color:#000000;
    
    class A orange;
    class Z blue;
    class X1,X2,X3,X4 pink;