1
00:00:00,040 --> 00:00:02,920
Speaker 1: The using artificial intelligence and the meat industry. So Alliance

2
00:00:02,920 --> 00:00:05,560
Speaker 1: has launched this new tech for farmers who can see

3
00:00:05,559 --> 00:00:07,840
Speaker 1: the eating quality of their lamb and beef through AI

4
00:00:08,039 --> 00:00:11,320
Speaker 1: in real time. These are special probes. They analyze fat

5
00:00:11,360 --> 00:00:13,560
Speaker 1: and lamb and marbling and beef. Anyway, the Alliance group

6
00:00:13,640 --> 00:00:16,520
Speaker 1: CEO Williebisus will this will E morning to you.

7
00:00:17,920 --> 00:00:20,520
Speaker 2: I'm Mike morning. Thanks for thanks for having me.

8
00:00:20,720 --> 00:00:23,239
Speaker 1: Not at all a probe already exists. I mean there

9
00:00:23,239 --> 00:00:25,440
Speaker 1: are probes all over the place. What does the AI

10
00:00:25,720 --> 00:00:26,200
Speaker 1: bit do?

11
00:00:27,840 --> 00:00:29,840
Speaker 2: So what the aim would do is more the link

12
00:00:29,920 --> 00:00:34,320
Speaker 2: to genetics and then the predictability of performance of livestock

13
00:00:34,400 --> 00:00:38,519
Speaker 2: unit performance specifically lamb and beef, and that's where the

14
00:00:38,560 --> 00:00:42,239
Speaker 2: algorithms run and it used machine learning to better predict.

15
00:00:43,000 --> 00:00:46,479
Speaker 2: We have also test and validated the outcomes of that

16
00:00:46,600 --> 00:00:51,720
Speaker 2: level of prediction versus with wet chemistry test. So initially

17
00:00:51,720 --> 00:00:54,600
Speaker 2: it was when we initially launched this, the initial view

18
00:00:54,760 --> 00:00:57,680
Speaker 2: was how do we ensure that we can manage eating

19
00:00:57,720 --> 00:01:02,640
Speaker 2: experience in a consistent way. So it's done that working

20
00:01:02,680 --> 00:01:05,240
Speaker 2: with AC Research and asked me in Australia. It's been

21
00:01:05,280 --> 00:01:08,480
Speaker 2: a twelve month twelve month project that's been delivered. The

22
00:01:08,560 --> 00:01:10,920
Speaker 2: next bet is how do we provide our farmers with

23
00:01:11,080 --> 00:01:14,160
Speaker 2: information so they can make behind the gate decisions to

24
00:01:14,200 --> 00:01:17,120
Speaker 2: get better value. First of all, so it wasn't initially

25
00:01:17,160 --> 00:01:20,400
Speaker 2: linked to genetics because the farmers know what genetics and

26
00:01:20,560 --> 00:01:22,959
Speaker 2: they already using and what parts of the farmer, what

27
00:01:23,360 --> 00:01:28,280
Speaker 2: their farming systems is. So we've seen significant improvement already.

28
00:01:28,319 --> 00:01:33,479
Speaker 2: But we've also seen really crossbreed lamps outperforming our whole

29
00:01:33,520 --> 00:01:36,240
Speaker 2: host of other genetic lamps, and that's on farm practice.

30
00:01:36,280 --> 00:01:39,119
Speaker 2: So there's a combination of that. Then we've moved more

31
00:01:39,160 --> 00:01:42,200
Speaker 2: into the AI around how do we provide farmers with

32
00:01:42,240 --> 00:01:48,480
Speaker 2: a predictable outcome because obviously there's editory genetic transition which

33
00:01:48,560 --> 00:01:53,600
Speaker 2: is roughly around fifty percent, you know, as they grow

34
00:01:53,920 --> 00:01:56,800
Speaker 2: their flocks, So how do we predict the performance of

35
00:01:56,840 --> 00:02:00,200
Speaker 2: those and therefore how does the farmer better by legit,

36
00:02:00,280 --> 00:02:03,920
Speaker 2: how does the farmer better predict a return based on

37
00:02:03,960 --> 00:02:07,000
Speaker 2: Because what we do in alliance, which is in a

38
00:02:07,080 --> 00:02:09,960
Speaker 2: lot of cases different to some other processes, we have

39
00:02:10,000 --> 00:02:12,080
Speaker 2: two key components that we look at or in how

40
00:02:12,120 --> 00:02:15,120
Speaker 2: we reward our farmers. The one is rewarding for quality

41
00:02:15,120 --> 00:02:18,560
Speaker 2: and this is specifically the yield performance that we measure.

42
00:02:18,560 --> 00:02:22,440
Speaker 2: So we measure lean net yield with obviously scanning technology

43
00:02:23,160 --> 00:02:25,360
Speaker 2: that's on the one axis. On the other axises the

44
00:02:25,440 --> 00:02:29,839
Speaker 2: intramuscular fat that has done through the probes. And then

45
00:02:30,560 --> 00:02:34,920
Speaker 2: for beef we also use a camera after twelve hours

46
00:02:34,919 --> 00:02:37,720
Speaker 2: of chilling to actually validate the information and to provide

47
00:02:37,720 --> 00:02:41,000
Speaker 2: additional information. So that was the first bit so on

48
00:02:41,040 --> 00:02:43,720
Speaker 2: that we created a sweet spot to say the lands

49
00:02:43,720 --> 00:02:47,760
Speaker 2: that has got operate within these lean meat yield parameters

50
00:02:48,120 --> 00:02:52,280
Speaker 2: and that operate within this intramuscular fat parameter. That is

51
00:02:52,320 --> 00:02:55,399
Speaker 2: the sweet spot that go into our handpit premium program

52
00:02:55,600 --> 00:02:59,320
Speaker 2: or our luminar program, which is separate from your normal

53
00:02:59,360 --> 00:03:03,600
Speaker 2: baseline baseline land products. And it's in that that we

54
00:03:03,680 --> 00:03:05,799
Speaker 2: then track that we track it per region. We can

55
00:03:05,880 --> 00:03:08,760
Speaker 2: compare farmers and how they perform relative to their region.

56
00:03:08,800 --> 00:03:11,880
Speaker 2: We can see how they perform relative to the national

57
00:03:11,919 --> 00:03:16,160
Speaker 2: averages as well, and that information our farmers are Platinum

58
00:03:16,560 --> 00:03:19,079
Speaker 2: Royal farmers. They can access it through a farmer portal

59
00:03:19,080 --> 00:03:23,200
Speaker 2: and they can see that straight after primary processing or

60
00:03:23,400 --> 00:03:25,080
Speaker 2: straight after the animal spinkilled.

61
00:03:25,120 --> 00:03:27,240
Speaker 1: That's cutting eat. I love it, Willie. Thanks for the insight.

62
00:03:27,240 --> 00:03:30,320
Speaker 1: I appreciate it very much. Willy Visa, who's the Alliance

63
00:03:30,360 --> 00:03:31,320
Speaker 1: Group CEO.

64
00:03:32,080 --> 00:03:35,000
Speaker 2: For more from the Mic Asking Breakfast, listen live to

65
00:03:35,120 --> 00:03:38,160
Speaker 2: news talks. It'd be from six am weekdays, or follow

66
00:03:38,200 --> 00:03:39,720
Speaker 2: the podcast on iHeartRadio