Notes from the work
Build notes, practical systems, and a closer look at what changed. Written to help you make a decision, try something useful, or avoid learning the annoying part twice.
Showing 31 to 34 of 34 articles in AI in Practice
Keep reading
AI in Practice
GPT-6 Astra can use computer-use tools, but the model does not supply the environment or decide whether a user-interface route is better than an API. Use it when the interface is part of the work, then compare it with the narrowest reliable
Read the articleAI in Practice
A dated comparison of GPT-6.1 Sol, GPT-6 Sol, Luna, Opus 5.5 and Gemini rates, hypothetical ticket costs, and the measurements needed to price accepted work.
Read the articleAI in Practice
GPT-6.1 Sol adds a new price-performance signal. Compare OpenAI, Anthropic and Google API rates, then decide what a workflow pilot should measure.
Read the articleAI in Practice
A five-part test for deciding whether repeated work should be removed, simplified, automated with review, or kept human.
Read the article
Follow the work
New builds, honest lessons, and practical ways to make more room for the work that needs you.
Free to read. Unsubscribe at any time. Privacy
