AI KPIs? Focus on uptime!

Every team seems to be debating total token spend and how to measure AI success, especially as huge chunks of code get written and released to production. Some of these booby traps aren’t found out or catastrophic until days, weeks, or months later. For example, the recent Amazon outage caused by AI code wiped out an estimated 6.3M orders and somewhere between $250M and $380M in revenue. And the 13 hour AWS outage that followed cost between $500M and $1B!

Contrary to popular belief, uptime would be the number one metric teams should focus on, followed by deployments that push successful business metrics, followed by experimentation and AI learning. We’ve somehow missed this step in the equation and prioritized speed at all costs.

My caveat to that is if early in the pre-seed, then of course move fast and break things, but if you’re an established company with substantial users, it may be time to revisit your KPIs.

Paper.design is the new design baddie. A few friends think that Figma will acquire them, although it feels rather early. Product is tons of fun, and the website has several easter eggs. Screenshot below.

With three weeks left in the quarter, transitioning away from experimentation into execution mode. This website design, my personal website is giving me the ick. Trying to resist the temptation to nerf everything and just use plain text files for everything, something that humans and browsers can view, but most importantly agents.