1
00:00:00,900 --> 00:00:07,631
Best practices. Instruction files, version
control, careful habits: a whole series of them.

2
00:00:07,982 --> 00:00:12,790
Very responsible. Too long;
didn't read. Let's just vibe code.

3
00:00:14,386 --> 00:00:16,668
One request, to a team of agents.

4
00:00:17,239 --> 00:00:18,750
Twelve and a half minutes later:

5
00:00:19,261 --> 00:00:23,905
eighty-six years of a river's records,
analyzed, with figures for a paper.

6
00:00:26,800 --> 00:00:32,290
AI for Research Efficiency.
Episode zero: T L D R.

7
00:00:33,900 --> 00:00:35,283
First, the quick part.

8
00:00:35,815 --> 00:00:40,846
Make a folder for your project, right-click
inside it, and choose Open in Terminal.

9
00:00:41,724 --> 00:00:46,748
Paste one install line:
for Claude Code, Codex or Antigravity.

10
00:00:47,138 --> 00:00:51,762
Each has its own episode.
Then open the terminal again, the same way.

11
00:00:52,693 --> 00:00:57,094
Type the agent's name, sign in,
and tell it you trust the folder.

12
00:01:00,300 --> 00:01:04,113
Now the real part. Say who you are,
and what you want at the end.

13
00:01:04,444 --> 00:01:06,831
And ask it to spin up a team of agents.

14
00:01:12,700 --> 00:01:16,946
It works in auto mode: a second model
checks each step before it runs,

15
00:01:17,097 --> 00:01:19,179
so this run never stopped to ask.

16
00:01:20,339 --> 00:01:24,326
First, the lead agent set the project up:
a Python environment,

17
00:01:24,537 --> 00:01:26,190
eighty-six years of gauge records,

18
00:01:26,360 --> 00:01:31,068
an instruction file it reads every time
it starts here, and a first saved version.

19
00:01:31,989 --> 00:01:36,718
So those best practices we skipped?
It did them anyway. Show-off.

20
00:01:38,700 --> 00:01:40,143
Then it split the work.

21
00:01:40,515 --> 00:01:44,233
Three agents at once:
one on floods, one on low flows,

22
00:01:44,404 --> 00:01:47,371
and one on the river's whole pattern,
and the rain.

23
00:01:49,931 --> 00:01:52,942
As each one reported back,
it pulled the results together,

24
00:01:53,133 --> 00:01:55,882
checked the numbers it would quote,
and drew the figures.

25
00:02:00,500 --> 00:02:01,241
The finding:

26
00:02:01,572 --> 00:02:05,469
the river runs about sixteen percent
higher than before nineteen eighty-three.

27
00:02:05,900 --> 00:02:09,457
By the team's analysis,
more rain explains nearly all of it,

28
00:02:09,628 --> 00:02:12,773
and its floods and low flows
haven't changed detectably.

29
00:02:14,273 --> 00:02:17,411
Every stage is saved,
so you can go back to any of them.

30
00:02:19,500 --> 00:02:21,818
The same approach works on almost anything.

31
00:02:22,679 --> 00:02:27,224
In this series, a team of agents reviewed
fifty-seven files for a literature review.

32
00:02:27,655 --> 00:02:32,941
Others mapped a research field, turned a paper
into a narrated video, and built a web page.

33
00:02:34,713 --> 00:02:36,255
Some call it vibe coding.

34
00:02:36,786 --> 00:02:41,472
Say who you are, what you want at the end,
and: spin up a team of agents.

35
00:02:43,700 --> 00:02:48,324
Your run will look different: models update,
and every computer is set up its own way.

36
00:02:48,754 --> 00:02:51,876
If something goes wrong,
ask your agent to help fix it.

37
00:02:52,968 --> 00:02:56,415
Before you point it at sensitive data,
watch episode nine:

38
00:02:56,686 --> 00:03:00,033
your data, your keys,
and your campus's rules.

39
00:03:00,974 --> 00:03:05,569
And if you ever do want those best practices,
the rest of the series is right there.

40
00:03:05,941 --> 00:03:06,882
No pressure.

41
00:03:09,900 --> 00:03:13,368
Next: episode one, why the command line.