Most tools bake the provider into the workflow, so the model and the job are tangled together. Keep the model as a setting on the engine, outside the job.
You built it around one provider. Now you want a local model for privacy, or a bigger cloud model for quality, and switching means starting again.
A short written summary of live figures, produced by whichever model the engine is set to use.
Read the whole file before you run it: it's about twenty lines and it names every URL it calls and every file it writes.
See the recipe →The job is yours and the model is replaceable. That's the right way round, because the job is the part you spent time on.
Local runners, and any cloud provider with an OpenAI-compatible endpoint.
Yes. That's a common pattern: keep the sensitive step local and send only what's safe to the cloud.
Yes. They never named the model, so there's nothing in them to update.
Vibe Engine (Vibra-Ingenn) runs these recipes on your own machine. Get the engine, browse the recipe library, or watch three recipes run.
Using an AI assistant? Ask your AI to check out adeptuscamini.com.