PinnedInData Science CollectivebyHerman Wandabwa·Apr 6Stop Guessing Staffing Needs: Predicting Daily Museum Visitors Before They Arrive (Part 1)How to predict daily visitor numbers for museums using feature engineering, XGBoost, and SHAP explainability.A response icon9A response icon9
PinnedInData Science CollectivebyHerman Wandabwa·Mar 24, 2025Building a RAG System with MMR for Safaricom’s Smart AssistantIn this post, we continue to explore the implementation of a Retrieval-Augmented Generation (RAG) system designed for Safaricom — a Telkom…
InData Science CollectivebyHerman Wandabwa·Sep 8How to Diagnose RAG Failures with a Groundedness JudgeLearn how to evaluate RAG systems, detect hallucinations, and trace failures across retrieval, context, and generation using a groundedness…
InData Science CollectivebyHerman Wandabwa·Jun 30Letting an LLM Query Your Database Tables SafelyHow tool calling connects language models to live data while keeping permissions, validation, and execution inside your codeA response icon1A response icon1
InData Science CollectivebyHerman Wandabwa·Jun 22Turning Patient Number Predictions into Staffing Numbers Without Fancy AIHow I turned a patient-volume forecast into a low-cost roster with wait-time targets and uncertainty built inA response icon7A response icon7
InData Science CollectivebyHerman Wandabwa·May 27Building a Multi-Agent Deep Research Agent with LangGraphA practical walkthrough of parallel specialist agents, citation auditing, and cited markdown report generation
InData Science CollectivebyHerman Wandabwa·May 10Predicting Daily Patient Volume for a Melbourne Urgent Care ClinicHow I built an XGBoost forecasting pipeline to turn patient demand into clinician rostering decisionsA response icon5A response icon5
InData Science CollectivebyHerman Wandabwa·Apr 27From Theory to Code — Building a SIM Replacement Agent in LangGraph (Part 2)How State, Tools, Nodes, and Edges Power an AI Agent
InData Science CollectivebyHerman Wandabwa·Apr 20What Agentic AI Actually Is: A SIM Replacement Use Case (Part 1)How a real, multi-step telco workflow exposes the architectural gap between chatbots and agentsA response icon1A response icon1
InData Science CollectivebyHerman Wandabwa·Apr 13From Jupyter Notebook to Full-Stack ML App with FastAPI, React, and SupabaseA hands-on guide to deploying an XGBoost model as a REST API and interactive dashboard for daily visitor forecastingA response icon4A response icon4