1
00:00:00,180 --> 00:00:05,780
And the key idea there is not that, well, firstly, there's all this power. And secondly,

2
00:00:06,020 --> 00:00:11,320
that languages like this tend to be very subtle, and so it is quite likely that we are

3
00:00:11,320 --> 00:00:15,940
going to want tools to help us reason about what these policies mean.

4
00:00:17,140 --> 00:00:21,020
But the secret here, and I'll get to a little bit of this later, is that if you had written

5
00:00:21,020 --> 00:00:23,080
the same logic in Python,

6
00:00:24,120 --> 00:00:28,620
for example, you would have exactly the same subtlety, but it would be less obvious.

7
00:00:29,380 --> 00:00:33,780
You could have exactly the same bug if you had written this in a general purpose programming

8
00:00:33,780 --> 00:00:39,460
language. It would be a bug that's harder to see and a bug that is much harder to formally

9
00:00:39,460 --> 00:00:40,440
reason about.

10
00:00:41,480 --> 00:00:43,660
I'll get to more of that in a second.

11
00:00:45,220 --> 00:00:51,660
Another example, no sudden spikes, and some within an hour, and make sure that the rate

12
00:00:51,660 --> 00:00:55,580
of things flowing through a system, the rate of an agent spending my money doesn't go

13
00:00:55,580 --> 00:01:02,380
up too fast. So there's just a ton of different things you can encode with what seems

14
00:01:02,380 --> 00:01:07,440
like a relatively limited and ultimately is a relatively limited policy language.