Top-Down vs Bottoms-Up AI
Anyone working with Agents which are deciding what to do, doing it and then considering next steps?
I've found that having some really well-defined concrete tasks to be the game-changer in how an Agent works. Teach it to do those things well, use them as building blocks, make sure it doesn't attempt to do things it doesn't know how to do (tell me when you don't know how to do something instead of guessing). I consider this to be Bottoms-Up AI. Teach tasks, tell it to do those tasks. Add more tasks until it's a skill. Eventually enough skills is mastery.
Starting with a vague ask (Top-Down) and expecting it to plan and decide and execute has really only wasted my money.
What's your experience with this?
4
2 comments
Matt Ferrante
3
Top-Down vs Bottoms-Up AI
The 4 Hour AI Workweek
skool.com/4houraiworkweek
Use AI to finish a 40-hour week's work in just 4 hours. Then build your AI empire to the BILLIONS with Systems: Workflows, Automation, & No code
Leaderboard (30-day)
powered by