@FullStackML I have said it before. Choosing a model is only 5% of the job. The rest is engineering, testing and optimising context and workflow. In fact, context engineering is 90% of the job.

@Hans365days Depends on the problem but yes, context engineering usually takes majority of the time. In data likely 90%

@FullStackML For us, small changes to context, prompt, data ingestion or RAG pipeline has WAAAY bigger and less costly impact than changing to a newer model.