1
00:00:00,320 --> 00:00:06,560
And so to recap, we just experienced a crew I project, which is in fact a UV project under the hood.

2
00:00:06,920 --> 00:00:11,160
We created it by saying crew I create crew debate.

3
00:00:11,440 --> 00:00:14,960
It created this directory structure which now should land with you.

4
00:00:15,000 --> 00:00:20,160
You should be more familiar debate census, then debate again, then config.

5
00:00:20,360 --> 00:00:24,920
We set up our agents YAML to define each of the agents, including the model.

6
00:00:25,360 --> 00:00:30,160
We set up the tasks that included the expected output and the output file.

7
00:00:30,520 --> 00:00:35,800
Crew is where we had the various decorators, and we brought it all together with our functions for

8
00:00:35,800 --> 00:00:37,640
agents, tasks and the crew.

9
00:00:37,680 --> 00:00:39,800
And we said that the process was sequential.

10
00:00:40,080 --> 00:00:46,800
And then we typed query run within our directory and it kicked the whole thing off, generated the output.

11
00:00:46,920 --> 00:00:48,720
And it was successful.

12
00:00:48,720 --> 00:00:52,320
And apparently there should be stricter regulation around llms.

13
00:00:52,480 --> 00:00:58,520
I encourage you to try debating some more controversial points of your liking and choose different models.

14
00:00:58,760 --> 00:01:01,600
So yes, we'll of course be getting much deeper into crew.

15
00:01:01,600 --> 00:01:06,280
But in the meantime, the assignment for you is to now play around with this.

16
00:01:06,320 --> 00:01:13,560
You could have a separate agent for the the agent that is proposing and opposing the motion.

17
00:01:13,600 --> 00:01:18,720
Break that into two different agents and have the tasks going to them separately.

18
00:01:18,800 --> 00:01:22,000
And the reason to do that is that then it's easy to have a different model.

19
00:01:22,000 --> 00:01:28,360
So that you could have OpenAI debate with deep seek or something like that, and then switch who's opposing

20
00:01:28,360 --> 00:01:32,080
and who's proposing to see whether it changes the outcome.

21
00:01:32,080 --> 00:01:38,400
And that's an amusing and entertaining way to battle Llms together, to see which are better at forming

22
00:01:38,520 --> 00:01:45,000
coherent arguments, persuasive arguments that convince a different model that is being the judge.

23
00:01:45,160 --> 00:01:49,840
So that allows you to come up with your own little leaderboard based on debating skills.

24
00:01:50,160 --> 00:01:53,160
So please go away and enjoy yourself with that.

25
00:01:53,160 --> 00:01:58,920
Get a good handle, get comfortable with the framework around crew and the sort of minimal scaffolding

26
00:01:58,960 --> 00:01:59,400
there.

27
00:01:59,680 --> 00:02:05,840
And next time we'll get a little bit deeper into crew and start building some more crew projects.

28
00:02:05,840 --> 00:02:06,800
I will see you then.