Topic
25 essays. All writing
Agentic commerce depends on context assembly: giving a shopping agent the right information at the right moment.
How tool calling connects your request to product searches, stock checks, and an authorized purchase.
How an AI suggestion becomes a real-world action—and how permission checks, approval gates, and recovery logic keep a helpful agent from making an expensive mistake.
Most confusion in agent architecture begins when one system is asked to decide when work starts, how it proceeds, and when it is safe to act.
It can look like forgetting. Usually, it is something more ordinary: the information was kept in the wrong place — or it was never kept at all.
One GMV report, built three ways — and a four-layer model for knowing which layer should change.
What each component solves, what state it owns, and what breaks when you remove it.
A clear look at its real power, who should try it, and who should wait.
System Prompt, Skill, Workflow, Cron, and MCP are not rivals. They are one stack.
MCP is the badge. Skills are the training. The pattern that works is Skill orchestration plus MCP execution.
A practical framework for separating reusable capabilities from orchestration logic—and knowing when to use each.
The SaaS Customer Journey: From First Contact to Long-Term Value
A business model is the foundation of any company—it defines what you sell, how you deliver it, how you acquire customers, and how you generate revenue.
The shift toward AI-driven pricing models isn’t just theoretical—companies are already putting these strategies into practice.
The rise of AI-powered products is transforming how businesses price software and services.
Business models are about getting people to take action in exchange for value.
AI is not just enhancing existing products—it’s driving game-changing innovations.
Growing a business isn’t magic—it’s about turning the right knobs to drive success.
set a clear target
AI has taken center stage in consumer tech, transforming how users interact with everyday products.
OMTM is the one number your team is laser-focused on above everything else at your current stage.
Methodology & Lifecycle
“How would we know if we met our Objective?”
Think of an Objective as a mission statement—but shorter.
Product Management in Post ChatGPT Era
Leave your email and I’ll send new essays when they go up.