Assess, Decide, Do + Substrate = Long Running, Self Improving Agents – Dragos Roua
[ad_1] Last week I read Addy Osmani’s piece on long-running agents. Halfway through I stopped and went back to the top, because something kept…
[ad_1] Last week I read Addy Osmani’s piece on long-running agents. Halfway through I stopped and went back to the top, because something kept…
[ad_1] Sam Altman, the CEO of OpenAI, recently said we are 1–2 years away from the first one-person unicorn — a $1,000,000,000 valuation company…
[ad_1] Apr 12, 2026 Apr 12, 2026 2026-04-12 Today I stumbled upon a nice write-up by Michael Grady about how he’s running AIGernon on…
[ad_1] A few months ago I published a mega prompt that teaches Claude to think with the Assess-Decide-Do framework. I wrote about it on…
[ad_1] Last weekend I stumbled upon Andrej Karpathy’s LLM Council project. A Saturday hack, he called it—born from wanting to read books alongside multiple…
[ad_1] For over 15 years, the Assess-Decide-Do framework has used a consistent visual system. Three colors and three symbols, each one supporting a specific…
[ad_1] A few days ago I integrated my productivity framework, Assess-Decide-Do in my LLM model of choice these days, Claude. If you want to…
[ad_1] 15 years ago, while on a trip to Thailand (one of my very first trips to Asia), I created a productivity framework called…
[ad_1] Fifteen years ago, I created the Assess-Decide-Do (ADD) framework out of frustration with productivity systems that treated humans like task-completion machines. I wanted…