My AI agent could do useful work. The little things that made it frustrating to use kept getting in the way.While setting up Milo, my Hermes agent, I kept running into friction: long silences, progress updates that just said “Python,” and no easy way to stop a long answer or get the agent into a conversation.Each annoyance became one small fix: more useful progress updates, a Stop button, a Join button. The interaction got smooth enough that I wanted to use it regularly.In this episode:Finding the little things that make you avoid using a toolTurning vague status messages into useful, sometimes funny updatesSolving one friction point at a timeWhy your simplest useful fix may look different from mineTry this with your own agent: “Here's the problem I'm trying to solve. What's the simplest fix?”Less Miserable Tech is a podcast and field journal about real workflows: where they get stuck, what small fixes actually help, and how to make systems fit the people doing the work.Website: https://lessmiserabletech.com/Watch, listen and read transcripts: https://podcast.lessmiserabletech.com/make-your-ai-agent-less-miserable/
I almost didn’t make this episode because I was trying to make it too perfect.The problem was not that I lacked equipment. I own four tripods. The problem was that I needed to record Episode 01, and all the equipment was packed somewhere in the middle of a move.The smallest useful fix turned out to be an outdoor table, a toolbox, and a cardboard box.In this episode:- Why naming the problem matters before choosing a tool- How chasing the perfect setup can become the problem- Why the simplest working solution is sometimes the right onePrinciple 01: Name the problem before picking the tool.Less Miserable Tech is a podcast and field journal about real workflows: where they get stuck, what small fixes actually help, and how to make systems fit the people doing the work.Website: https://lessmiserabletech.comEpisode page: https://podcast.lessmiserabletech.com/the-right-tool-was-a-cardboard-box/