Blog

I share first-hand lessons from AI product management, product strategy, Agentic AI, business analysis, delivery, research, and training.

The portfolio shows what I have built. This blog explains the decisions, methods, results, and trade-offs behind the work.

Artificial Intelligence

6 posts

Post indicators Includes images

  • What I Learned from Building a Kaggle AI Agents Project

    Building Clinical AI Kit for Google and Kaggle's AI Agents capstone: a Google ADK multi-agent system for clinicians, from product concept and Claude Design prototypes to a deployed, fully documented application.ai-agentsgoogle-adkkagglevibe-codingclaudeproduct-managemententerprise-architectureAug 202610 min read

  • What are Claude "Skills"?

    A plain-English look at Anthropic's Claude Skills: what a skill actually is, how it differs from a system prompt with an MCP, and why on-demand tools matter.claudeskillsanthropicaiOct 20255 min read

  • Responsible AI #1: AI-First Company Failures

    The first in a Responsible AI series: why so many self-declared 'AI-first' companies stumble, and what separates AI theatre from real adoption.responsible-aiai-strategyai-adoptionaiMay 20255 min read

  • The AI & ML Resource Library

    A curated, no-fluff library of the articles, courses, and tools I recommend for going from AI beginner to confident practitioner.aimachine-learningresourceslearningMar 202518 min read

  • For the Love of God, Don't Use Deepseek

    Why routing your prompts through chat.deepseek.com can hand DeepSeek broad rights over your inputs and outputs — and the safer ways to run the same open models.deepseekdata-privacyllmaiJan 20252 min read

  • Prompt Engineering User Stories

    How to write high-quality user stories with prompt engineering — a repeatable structure that turns a vague request into acceptance-criteria-ready backlog items.prompt-engineeringuser-storiesbusiness-analysisaiMay 202324 min read