Every post comes from something I've done on a real project. AI tools, development approaches, how I actually build things. You're getting a curation of my taste, not takes on stuff I don't use. Subscribers also get extras: things that went wrong, how my thinking about AI is changing, hacky workflows I use every day, and the occasional personal update. Stuff I share with subscribers because it's a little too personal or unpolished to blast across the internet.
two posts and a cat
|
Two new posts today. Oh, and we went out to get my wife new hairspray. It turned out the store is next to a petsmart. So now we have a cat. The first post is AI Coding Patterns 1: Vibe Coding. This is the first of an 18 post series on AI Coding. The series will build from here into more deliberate patterns and pitfalls The second (subscriber only) is My AI Writing Process. People ask me about this constantly. Few people talk about their AI writing process publicly, so I wanted to share mine. I ramble into a mic, index old projects and agent logs for context, brainstorm structure with AI, then run three Gemini editing passes built on Zinsser’s principles (prompt is included). Then I edit by hand. The writing process post is subscriber-only. You’re on the list, so just click through. I’ll be doing more of these for topics that feel better shared to a smaller audience. Reply if anything resonates or if you think I’m wrong about something. Isaac |
Isaac Flath
Every post comes from something I've done on a real project. AI tools, development approaches, how I actually build things. You're getting a curation of my taste, not takes on stuff I don't use. Subscribers also get extras: things that went wrong, how my thinking about AI is changing, hacky workflows I use every day, and the occasional personal update. Stuff I share with subscribers because it's a little too personal or unpolished to blast across the internet.
Today's post is about a project that I will take concepts from to improve my own work. So I studied the OSS prototype of it to understand how it works. Point and Talk: How Clicky’s AI Interface Works Clicky is an AI buddy made by Farza that lives on your Mac. You press a key, talk, and a glowing blue triangle flies across your screen, points at whatever you asked about, and talks you through the answer. Most apps with an agent should have something like this. Point and talk is closer to how...
Last week I shared my knowledge base tool, agentkb. This week I am OSSing my pi harness that uses it, Harpy. The most interesting part of the harness is that knowledge base <-> harness integration so that's what this week post dives into. It covers what RLM is, how it drives a python loop with state, how Pi (typscript) extension talks to python, and how that allows for smart delegation and fan-out to smaller models to give more accurate search results. How My RLM Tool Works An LLM writes...
Hey, This was a week of context switching 😅. Product release weeks are always odd. The goal is super specific, and yet the work is scattered small tasks (testing, polish, docs, marketing copy, etc.). We shipped the stoa beta, and I kept wishing my agents could remember more. That's why I'm open sourcing `agentkb`, my work-in-progress knowledge base framework today. The Pi harness built around it will be open sourced next. AgentKB: A Local Knowledge Base for Agents My agent should learn from...