Skip to main content
Thanuka.
Intelligence Hub

Articles & Insights.

Exploring the frontiers of enterprise AI, predictive modeling, and autonomous workflows. Practical field reports from engineering production systems.

Filter:
Featured PostData Science

ReviewRadar AI: Ensemble Sentiment That Actually Moves the Metric

Published evaluation metrics from model_metrics.json — an enhanced sentiment ensemble lifts accuracy from ~0.84 to 0.91 over prior pipelines on the Yelp review warehouse.

August 12, 20267 min read
AI Engineering

Job Hunter: An Autonomous RAG Agent That Applies With Evidence

FAISS-backed career persona retrieval plus Playwright form filling under a zero-hallucination policy — rank first, then apply only with grounded answers.

August 10, 20267 min read
Read
AI Engineering

RevOps AI: Multi-Agent Pods for Healthcare RCM Auditing

FastAPI + React B2B SaaS combining heuristic RCM audits, sklearn payment forecasting, Monday.com sync, and specialised agent pods.

August 8, 20267 min read
Read
AI Engineering

TrainIQ: Multi-Tenant LMS Isolation with Local AI

Three-layer tenant isolation, Stripe billing, a CEO platform console, and an Ollama-local AI suite — without requiring cloud LLM keys.

August 6, 20268 min read
Read
AI Engineering

Monday.com GraphQL Data Auditor: Local Hygiene Without Zapier

Streamlit + Monday GraphQL cursor pagination to find missing Files/Notes cells across boards and export clickable CSV remediation lists.

August 4, 20265 min read
Read
AI Engineering

Agentic Commerce on MCP: From Multilingual Intent to a Completed Checkout

A field report from the Kapruka Agent Challenge 2026 — building a shopping agent on the Model Context Protocol that parses English, Sinhala, and Tanglish intent into budget-aware cart plans and completes a real guest checkout.

July 24, 20267 min read
Read
Data Science

One Backbone, Three Heads: Multitask Learning for Scene and Emission Estimation

How a single ResNet-50 trunk can jointly predict Places365 scene categories, binary scene attributes, and a five-class carbon emission estimate — and what actually breaks when you fine-tune one head in isolation.

June 20, 20267 min read
Read
Thought Leadership

Statistical Rigor Before Machine Learning

Gradient boosting will happily fit noise and report a confident number. A short case for running descriptive statistics, hypothesis tests, and dimensionality checks before reaching for a model.

June 6, 20265 min read
Read
AI Engineering

Building Production-Ready RAG Pipelines: Beyond Simple Vector Search

Moving past naive semantic search into advanced retrieval-augmented generation. Exploring hybrid indexing, query rewriting, reranking, and verification gates for enterprise deployment.

May 18, 20266 min read
Read
Data Science

Machine Learning for Future Payment Prediction in Healthcare Revenue Cycle Management

An industry case study comparing Linear Regression, Decision Tree, Random Forest, and Neural Networks on transaction-level billing data to predict payment propensity.

April 29, 20268 min read
Read
Thought Leadership

Autonomous Agents vs. Traditional Automation: A Field Report

Deconstructing the architectural differences between rigid deterministic scripting and dynamic agentic orchestration. A review of agentic behavior in production workflows.

March 14, 20265 min read
Read