That distinction is the whole game. If you put a 2,000-word essay on testing best practices into the agent’s context, the agent reads it, generates plausible-looking text, and skips the actual testing. If you put a workflow there (write the failing test first, run it, watch it fail, write the minimum code to pass, watch it pass, refactor), the agent has something to do, and you have something to verify.
Process over prose. Workflows over reference. Steps with exit criteria over essays without them.
If you’ve ever resorted to MANDATORY or DO NOT SKIP, you’ve hit the ceiling of prompting.
Imagine a programming language where statements are suggestions and functions return “Success” while hallucinating. Reasoning becomes impossible; reliability collapses as complexity grows.
Herman Martinus, creator of Blog blogging platform
Mark Cuban has emphasized that the most critical, high-demand job in the coming years is not creating AI models, but integrating AI into existing business workflows . He predicts that millions of small and mid-sized businesses (SMBs) will need “AI integrators”—individuals who understand both the technology and operational strategy—to survive and compete. [[1]
I’m coming to the conclusion that the biggest challenge for Enterprise AI, and AI in general , as of now, is that it’s still impossible to make sure that everyone gets the same answer to the same question, every time.
Which is a great response to the doomers. AI doesn’t know the consequences of its output.
Judgement and the ability to challenge AI output is becoming increasingly necessary, and valuable.
Which makes domain knowledge more valuable by the second.
