calebwoods (@calebwoods) profile picture

Solving business problems with technology. AI and custom software development. CEO @rolemodelsoft. Christian, husband, software craftsman.

Joined August 2008
Photo by calebwoods (@calebwoods)Photo by calebwoods (@calebwoods)Photo by calebwoods (@calebwoods)Photo by calebwoods (@calebwoods)Photo by calebwoods (@calebwoods)Photo by calebwoods (@calebwoods)
The businesses getting real value from AI aren't getting it by accident. They're working from a system. We wrote ours down. Four free guides, personal practice to team capability: Collaborating with AI AI Skills AI Tooling AI Workspace rolemodelsoftware.com/collab…
32
Paying for AI is not the same as protecting your company. The line is personal versus business, not free versus paid. On a personal account, your inputs train the model by default, and the opt-out is a checkbox each person has to go find.
1
20
Business tiers cost about what individual subscriptions already do. This is a decision, not a budget. Make it and your team has a foundation to build on, where what they figure out has somewhere to live. Our full guide on choosing AI tools: rolemodelsoftware.com/collab…
9
I run all of my AI work out of one local project. A workspace. Claude and Codex both operate in it. Same files, different tool, nothing rebuilt. Providers will keep changing. That should cost you a subscription, not the thing you have been building all year.
1
21
Past a point, more instruction makes AI output worse. Refine is the step people get wrong, because it does not just mean add more. Something comes out badly and the instinct is to write another rule. RoleModel's full AI Skills guide: rolemodelsoftware.com/collab…
14
"What problem are you trying to solve?" is a better question in a world of AI prototypes. It is also the easiest one to skip. The risk isn't that the prototype is wrong. It's that it works well enough to stop the conversation.
9
A fresh chat asks generic questions. A model that holds your prior work asks better ones, then weighs your answers against decisions you already made. The prompt is one line anyone can copy. The context isn't.
11
If you need the same answer every time, stop prompting for it. Have the model write the script. Then run the script. The LLM is the prototype. What proves itself gets hardened.
1
1
33
Published a new blog post from my learning on toggling offline mode during tests with Selenium/Chromedriver calebwoods.com/2019/02/02/in…
2
My post on the @rolemodelsoft blog about an alternative to estimates is live blog.rolemodelsoftware.com/a…
Blog post with part of my story of coming to @rolemodelsoft and the impact of Kevin Bridges as a mentor in my life and career blog.rolemodelsoftware.com/a…
1
After experimenting with fasting for the last 6 months, decide to write up my experience. An easy implement, high reward New Year's resolution. calebwoods.com/2017/12/29/my…
1
Wrote a blog post on learning Craftsmanship through Production Support experience nitter.gq/rolemodelsoft/status/9…
Why production support experience is key to your software project's success: bit.ly/2xoQfjV by @calebwoods
Summarized my recent thinking about naming projects in a blog post: calebwoods.com/2016/01/23/na…
Been running f.lux on my iPhone for a couple months and loving it, although an iOS solution should be more polished. nitter.gq/noelrap/status/6866266…
Looks like we now know why Apple was giving f.lux a hard time on iOS: apple.com/ios/preview/
1
New blog post: Testing @reactjs components in @rails using the Asset Pipeline calebwoods.com/2015/11/01/te…
1
New post: heuristics that I'm currently using when choosing what type frontend to use for a new application calebwoods.com/2015/10/19/ch…
Wrote a summary post of how I'm using @jekyllrb, @github, and @wercker to manage publishing on my blog. calebwoods.com/2015/08/23/mi…
1
3