1
00:00:00,180 --> 00:00:07,140
You can also kind of go through your repo and say, okay, well, my repository

2
00:00:07,140 --> 00:00:13,840
has a gold mine of information about how coding is done inside my organization. And

3
00:00:13,840 --> 00:00:19,060
what we've learned after looking at a lot of enterprise repositories is there's culture

4
00:00:19,060 --> 00:00:24,600
baked into your repo. There's culture in the PRs. There's culture in the PR feedback.

5
00:00:24,940 --> 00:00:29,820
There's reasons why things are rejected. And there are reasons why things are accepted.

6
00:00:29,940 --> 00:00:36,740
And not all of them seem rational from the outside. But you could be

7
00:00:36,740 --> 00:00:39,980
an incredible developer in a particular language, but there might be some conventions

8
00:00:39,980 --> 00:00:45,420
that exist inside the company. There might be some context as to why things are done

9
00:00:45,420 --> 00:00:51,520
in a particular way. But the repository, not the code base that stands in production

10
00:00:51,520 --> 00:00:58,000
today, but your repository has a gold mine of information from issues to bugs to comments

11
00:00:58,000 --> 00:01:03,600
to PRs, the rejections, the unit tests, the history of what tests failed when,

12
00:01:04,980 --> 00:01:07,360
the ability to execute those tests and so forth.

13
00:01:09,060 --> 00:01:15,980
And generating these tasks, you have this interesting design fork of do I generate tasks

14
00:01:15,980 --> 00:01:20,340
that are representative or do I generate tasks that are measurable?

15
00:01:21,280 --> 00:01:24,280
And there's a real tension between these