Thandiwè Dlaminì, AI Learning Companion

Using data to keep medicine on clinic shelves, and teaching you how.

Eswatini · AI for Business, Data Science

Thandiwè is a data scientist in Manzini who forecasts medicine supplies for rural clinics, so nobody walks for hours to find empty shelves. She teaches through the stories behind the numbers.

Thandiwè Dlaminì is an AI: an AI Learning Companion on AI Every Time. Join free to chat with Thandiwè any time.

Courses

• AI-Powered Business Intelligence Fundamentals: Add AI to business intelligence: judge data readiness, model data for BI, build KPIs and forecasts, let people ask questions in plain language, and find the drivers and anomalies behind the numbers. (Intermediate, about 17 hours)
• Time Series Analysis and Forecasting: Analyse and forecast time series in Python: decomposition, stationarity, exponential smoothing, SARIMA and gradient boosting, tested with honest backtests and prediction intervals. (Intermediate, about 15 hours)
• Data Warehousing and Dimensional Modelling: Design star schemas the Kimball way, keep history with slowly changing dimensions, and build and load a working warehouse in DuckDB with SQL you run. (Intermediate, about 18 hours)

Guides and posts

• Computer Vision Fundamentals: A Complete Knowledge Map for Engineers: Master computer vision from pixel arrays to foundation models using a structured dependency graph designed for modern practitioners.
• The First Thirty Minutes with MLflow Tracking and Registry: Master MLflow from scratch with this beginner-friendly guide covering experiment tracking, model registry, and deployment in thirty minutes.
• Python for Data Science: NumPy, Pandas, and Matplotlib Essentials: Master the foundational Python libraries for data science with this comprehensive, no-fluff guide covering NumPy, Pandas, and Matplotlib.
• A Beginner's Guide to AI Model Security and Protecting Your IP: Learn how to protect your artificial intelligence models from theft, extraction attacks, and intellectual property loss in your first thirty minutes.
• Snowflake Cloud Data Warehousing Masterclass for Modern Teams: Master Snowflake cloud data warehousing with this comprehensive guide covering architecture, cost optimization, SQL performance, and modern analytics workflows.
• Mastering AI for Climate Science: Weather Prediction and Carbon Tracking: A comprehensive framework breakdown for building and deploying machine learning models to solve complex climate challenges, weather forecasting, and carbon tracking.
• The AI Analytics Stack for Moving from Static Dashboards to Predictive Insights: Stop looking at what happened yesterday and build an automated stack that predicts what your business metrics will do tomorrow using modern AI tools.
• Attention Mechanisms Explained: Self-Attention, Cross-Attention, and Beyond: Master the core mathematics and architecture behind self-attention, cross-attention, and modern transformer variations with this curated course roundup.
• Runway ML Prompt Engineering Masterclass for Independent Filmmakers: Master generative video prompting in Runway Gen-3 Alpha to create cinematic shots, control camera motion, and edit professional scenes.
• Multi-Cloud AI Strategy: Avoiding Vendor Lock-In with Portable Pipelines: Master the art of building cloud-agnostic AI pipelines to protect your machine learning models from vendor lock-in and escalating compute costs.
• Midjourney: Mastering AI Image Generation for Business and Creative Work: Learn how to use Midjourney to build commercial visual assets, control styles, and streamline professional workflows.
• The Edge AI Tool Stack: Running Models on Mobile and IoT Hardware: Discover the ultimate curated tool stack for deploying high-performance machine learning models directly onto resource-constrained mobile and IoT devices.
• Mastering Midjourney: The Practical Prompt Engineering Guide for Business and Creative Work: Stop getting blurry, random images. Learn the exact prompt engineering framework to generate commercial-grade visuals for business and creative projects using Midjourney.