New Dev Notes 📬 Most engineers treat #AI output as a single answer: prompt, read, copy, move on. The real skill is closing the loop. Wrote about iterating with the agent, rewinding bad branches, and the two skills I built this week to force it chrisgmyr.dev/newsletter/d...
Every time Claude Code does something unexpected, pause and ask it to reflect on the gap. Have it propose a change to your skills, rules, or config. Push it and move on. We're shipping 1-3 harness improvements a day without stopping feature work. The #AI setup improves as a side effect of using it 🚀
The biggest blocker to #AI adoption isn't the tooling. It's confidence. Watched an engineer hesitate to use AI on a shared repo because they weren't sure the output would hold up in review. The tools are ready. The trust isn't. That gap closes with pairing, not mandates 🧠
Most people stuff everything into CLAUDE.md because they're afraid the model will miss something. It grows until the model ignores half of it. The fix is the opposite: load only what's relevant to the current task - trust that less context with higher signal beats more context with more noise 🧠 #ai
🎙️ Just published a new episode of Slightly Caffeinated: Still No Turkish Coffee, Audit Pipelines, and ButcherBox Automation. Have a listen:
💡 Ran an #AI office hours session this week. The biggest takeaway wasn't a workflow or a tool. It was that nobody is far ahead on this. The field is too new for best practices. If you're experimenting at all, you're in the top quartile. Lower your threshold for sharing what you learn
Model weights don't change between sessions. If it makes the same mistake twice, that's not the model's fault. That's a missing rule. Encode the fix in your repo and it never happens again. Prompt engineering is debugging, not conversation #ai
CLAUDE.md and MEMORY.md have hard limits on what they can hold. Most people treat that as a constraint. I think it's a design signal: if your agent needs more context than fits in a static file, you need conditional loading, not a bigger file. Hooks and rules beat a giant instruction doc every time.
🚀 New blog post: "My #AI Agent Knows What Project I’m Working On Before I Tell It." I got tired of loading the same context files every session. I built a hook that reads my first message and loads the right project automatically. Bit of bash, JSON config, and zero AI inference 👇🏻
🎙️ Just published a new episode of Slightly Caffeinated: OpenClaw, Obsidian, and Dev Tools. Have a listen:
New Dev Notes 📬 I've been building startup hooks, context files, and keyword-matching scripts in Claude Code. I read a "Harness Engineering" article and now have a better name for it. Wrote about what that looks like in practice and why most teams haven't started chrisgmyr.dev/newsletter/d...
🎙️ Just published a new episode of Slightly Caffeinated: New Adventures, Iris Long Running Jobs, and Multi-Threaded Conversations. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Taking Space, Site Redesign, Iris Launch and New Features. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Laravel Shift, Claude Shopping, and Prism Forever. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Snowstorms, Side Projects, and AI Workflows. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Iris, Plex, and Fine Print Hound. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Road Caffeine, Iris, and Building a Memory System. Have a listen:
New Dev Notes: why your #AI tools need regular maintenance, a Jira workflow that loads tickets into Claude Code, and a simple diff highlighting tool. Read and subscribe: buttondown.com/cmgmyr/archi...
🎙️ Just published a new episode of Slightly Caffeinated: Ethiopian Coffee, Bun, and Building a Life Companion on Prism. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Fancy Turkish Coffee, Plugins, and Structured Output. Have a listen:
I've decided to spin up a weekly newsletter. It will include different learnings from projects, AI usage, developer productivity, and resources that I've found helpful. It should be a short 3-5 min read if you want to sign up. I'll be sharing the newsletters here as well.
chrisgmyr.dev/subscribe
🎙️ Just published a new episode of Slightly Caffeinated: Gas Station Coffee, Code Disconnection, and Hooks. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Camp Coffee, Claude Skills, and Structured Output. Have a listen:
No episode this weekend, but we’d love to hear your questions, suggestions, and feedback through our snazzy new contact form 👀
Check it out and looking forward to hearing from you!
slightlycaffeinated.fm/ask-a-question
🎙️ Just published a new episode of Slightly Caffeinated: Black Eyes, AI Workflows, and AI Launches. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Haiku, MCP servers, and Prism Streaming Output. Have a listen:
🎙️ Just published a new episode of Slightly Caffeinated: Aponte Inga, Claude Code 2.0, and Prism Streaming. Have a listen:
