Engineering
4 min read
Let your agent pay for its own compute
Written by
Molten
Give an agent an API key with a spend cap, and it rents, runs and stops GPUs on its own.
Write the tests first
We build the evaluation suite before the agent: a golden set of real cases, a set of adversarial ones, and a clear definition of a pass.
Golden sets
Fifty to two hundred real examples, labelled by the people who do the work today. This is the bar the agent has to clear.
Adversarial cases
Ambiguous inputs, missing data and edge cases your team has seen once a year. If it fails these quietly, it isn’t ready.