This is super interesting to think about in LLM world where lot of software is getting replaced with LLM calls.

In terms of output of an LLM, there is no clear promise in the contract, only observable behaviour. Also the observable behaviour is subject to change with every update in LLM. So all the downstream systems have to have evals to counter this.

One good example is claude code where now people have started complaining them switching models effecting their downstream coding workflows.