1
00:00:01,000 --> 00:00:06,010
This explanation accompanies our article on ChatGPT for business.

2
00:00:06,440 --> 00:00:10,330
How do individual prompts become a shared practice that colleagues can

3
00:00:10,360 --> 00:00:13,250
use, review and improve together?

4
00:00:13,720 --> 00:00:18,090
A fictional service team summarises the same working instruction.

5
00:00:18,120 --> 00:00:20,810
Each colleague takes a different approach.

6
00:00:20,880 --> 00:00:25,970
One summary loses an important exception, although the wording sounds convincing.

7
00:00:26,360 --> 00:00:30,730
The team selects one task: summarising an instruction for internal

8
00:00:30,760 --> 00:00:31,530
use.

9
00:00:31,800 --> 00:00:36,255
It defines the source, expected structure, boundaries and the point at

10
00:00:36,280 --> 00:00:38,490
which someone reviews the result.

11
00:00:38,920 --> 00:00:43,610
First agree which information people may use, who manages access and

12
00:00:43,680 --> 00:00:45,130
where results can be shared.

13
00:00:45,720 --> 00:00:50,090
Check the features actually available in your workspace and configuration.

14
00:00:50,520 --> 00:00:54,570
The instruction requests main steps and exceptions using only the

15
00:00:54,600 --> 00:00:55,930
supplied text.

16
00:00:56,200 --> 00:00:58,810
Missing information must remain visible.

17
00:00:59,080 --> 00:01:02,730
The output is a draft, rather than an approved instruction.

18
00:01:03,560 --> 00:01:06,970
A colleague checks the draft against the original instruction.

19
00:01:07,240 --> 00:01:08,970
Are conditions preserved?

20
00:01:09,000 --> 00:01:10,250
Has anything been added?

21
00:01:10,840 --> 00:01:15,050
A missing exception is corrected before anyone uses the summary elsewhere.

22
00:01:15,880 --> 00:01:18,970
Ask several colleagues to work through the same examples.

23
00:01:19,400 --> 00:01:22,930
Record errors, questions and correction effort.

24
00:01:23,240 --> 00:01:27,290
Polished wording or one successful example does not establish

25
00:01:27,320 --> 00:01:28,970
usefulness across the team.

26
00:01:29,800 --> 00:01:33,370
Choose an initial user group and an owner for instructions and

27
00:01:33,400 --> 00:01:34,090
changes.

28
00:01:34,680 --> 00:01:39,290
After the trial, decide which tasks continue, need adjustment or

29
00:01:39,440 --> 00:01:41,450
remain outside the agreed practice.

30
00:01:42,200 --> 00:01:46,170
Start with working agreements, rather than a collection of prompts.

31
00:01:46,600 --> 00:01:51,690
Our source article on ChatGPT for business explains how configuration,

32
00:01:51,720 --> 00:01:54,890
everyday use and evaluation fit together.