Understood.
Take for instance, customer support Agent , that is supposed to resolve tickets. Assuming it resolves around 30% tickets by an objective measure. Do you think that cannot be captured and agreed upon by both sides?
Take for instance, customer support Agent , that is supposed to resolve tickets. Assuming it resolves around 30% tickets by an objective measure. Do you think that cannot be captured and agreed upon by both sides?
AI agent developers internally have a metric they are targeting to improve. That itself violates goodhart law.
The same oversight mechanism that applies to humans cannot correct the flaws of AI agents?
No I do not.
Once you shift to billing for outcomes like "resolutions," the vendor switches from a utility provider to the judge and jury of their own performance. At scale, that creates a "fox guarding the henhouse" dynamic. The friction of auditing those outcomes to ensure they aren't just Goodharted metrics eventually offsets the simplicity the model promises. Frankly, I just cannot and will not trust the judgment of tech companies who evangelize their own LLM outputs.
I get the binary part. The biggest difference is the subjective component of outcome? However, a tech provider - especially Agent provider - has to bring down the subjective to a quantitative metric when selling. If that cannot be done, I am not sure what we are going to be buying from Agent builders/providers?