Now that we've fairly successfully set up an autonomous agent to do our work for us, you might be thinking: can it do all of my work?
But surely it can't do all of my work, right? There are probably some things that require human in the loop involvement.
Your instinct is absolutely correct. When you're planning out work to complete a feature, you should be thinking carefully about which bits require human in the loop involvement, in other words, where you need to be present, and which bits can be done autonomously.
The dream is that we're able to delegate all of our work and don't need to be there for any of it. But the truth is that lots of work requires human in the loop involvement.
We already know one of the things that requires human in the loop: planning.
An AI can assist with creating a plan, but without the human, it doesn't have the source of truth to bounce off for what it's supposed to be creating.
Another thing we've seen in the course is QA (quality assurance). You need a human eventually to actually go in and test the thing that's being built.
Humans can surface things which aren't present in the AI's feedback loops:
You might be getting a sense for the things that require human involvement. Anywhere that you need to apply taste to what you're doing.
What do I mean by taste? I mean human judgment, human feel.
<TableWrapper>
| Area | Why Humans Are Needed |
|---|---|
| Planning | Make design choices that feel sensible |
| QA | Give feedback based on personal taste |
| Architecture | Ensure the internal structure reflects values |
| User Experience | Ensure it feels right to end users |
| </TableWrapper> |
We need taste in planning because we need to work out together what we're building and make design choices that feel sensible.