JEV - AI Engineering
Private
9 members
$27 /month
Most AI apps send every small decision to a large language model: route this request, which tool to call, is the task done. Each call costs tokens and can answer differently next time. Put that in an agent loop and the bill grows faster than the results.
Here, code runs the workflow. AI handles only the judgments code can't make, and returns typed answers your program uses directly: a pick from a list, a score, a yes or no with a probability. Jev, TypeSafe's decision model, is our main tool. Claude and other LLMs come in when generating text or code is the job.
What you'll find:
- Build logs: real apps with token cost and accuracy measured before and after
- Courses: AI foundations, prompt systems, n8n self-hosting
- Straight answers on when not to use AI
I'm Gavin Stevens: 30 years in software, AI since 2003, Azure architect, America's Greatest Makers alum.
Independent community, not affiliated with TypeSafe.
skool.com/jev
Build AI apps that make decisions without burning tokens. Real projects, measured results, from a 30-year software engineer.
Powered by