The best posts on this blog, grouped by the decision they help with: AI costs, agent governance, coding agents, AI strategy, and AI in retail and loyalty.
Most of what I write here is one argument per post. These guides group those posts by the decision a founder, CTO or leadership team is actually trying to make, with a short framing up front and the posts in a sensible reading order.
Why AI bills keep rising as token prices fall, how caching and model choice move the cost curve, and when a smaller or local model is the better call.
How much autonomy to give an AI agent, how to scope its permissions by blast radius, and how to keep a record of what it actually did in production.
What changes when AI writes most of the code: review becomes the bottleneck, technical debt costs more, and someone has to decide what the agent prefers.
How to run an AI pilot that tells you the truth, when to build versus buy, where AI pays off first, and why the model you pick is rarely your advantage.
What changes for retailers and loyalty programs when AI agents start shopping for people, and which parts of the customer relationship stay worth owning.