What you’re referring to here is “one shot” execution. The prompt given by managers is one that can be interpreted using context. This context can include current code, comms about what needs to be built, design assets available today, data, etc. Then the AI can ask questions to clarify what needs to be built.
What’s great is that you could also have AIs write tests - for performance or correctness. Then future prompts could rely on these tests to stay in the correctness bounds for existing projects.
Emulating cognition is almost limitless in what it can do once it gets sufficiently good. So good that it can operate itself. You could hire an AI founder and give them cognition and compute resources to solve any problem.
Here’s an example:
You: Build me a profitable company that uses AI generated content to entertain humans.
AI: How much can I spend on cognition and compute? How much time do I have?
You: I want you to spend at most $X before coming back to me. You have until Monday. Along the way I want to see your plan before we decide to execute. Spend at most 5% of that making the plan and 1% calculating its probability of success with confidence interval.
… within some small timescale
AI: Here’s my plan as a video with rough examples demonstrating the product and strategy. Here’s a table with our probability distribution of predicted success metrics and confidence intervals.
You: Plan approved you can spend the rest of the $X
… on Monday
AI: Done. We’ve made a profit of $Y, with total revenue so far of $Z. We have a plan for reinvesting these proceeds to make even greater future profit. Here’s a table of our expected success metrics based on reinvested amount. How much should we reinvest?
You: Reinvest 50% into perpetuity and deposit the remainder in my account. Book me a trip around the world using 25% of the current deposits with accommodations for my family.
Now go enjoy your life.