1
00:00:00,900 --> 00:00:04,372
In a few minutes, Claude Code will
be working in your project folder,

2
00:00:04,503 --> 00:00:06,488
and you'll know how
to keep it in check.

3
00:00:09,850 --> 00:00:15,763
AI for Research Efficiency.
Episode 2.1: Install Claude Code.

4
00:00:17,000 --> 00:00:22,776
Last time: a terminal, a project folder,
Git and Python, and an account.

5
00:00:22,980 --> 00:00:28,975
In this episode: install Claude Code,
sign in, run it in your project folder,

6
00:00:29,166 --> 00:00:31,691
and check each step
before you speed up.

7
00:00:34,100 --> 00:00:37,242
Step one: in PowerShell,
paste this line:

8
00:00:37,692 --> 00:00:45,716
irm https://claude.ai/install.ps1 | iex

9
00:00:49,116 --> 00:00:52,041
On a Mac, use the second line,
in Terminal.

10
00:00:52,432 --> 00:00:54,515
Both lines are on the companion page.

11
00:00:54,682 --> 00:00:56,842
You don't need administrator rights.

12
00:01:00,500 --> 00:01:03,945
Step two: close the terminal,
open a new one,

13
00:01:04,156 --> 00:01:06,950
and type claude --version.

14
00:01:07,541 --> 00:01:09,223
You should see a version number.

15
00:01:12,428 --> 00:01:15,052
If PowerShell says
claude is not recognized,

16
00:01:15,323 --> 00:01:18,027
open another PowerShell window,
and try again.

17
00:01:22,100 --> 00:01:24,965
Step three:
go into your project folder with

18
00:01:25,076 --> 00:01:28,722
cd agent-work, and type claude.

19
00:01:30,902 --> 00:01:34,671
Always start it in a project folder,
never in your home folder.

20
00:01:36,500 --> 00:01:40,648
Step four: the first time,
it asks you to pick a text style,

21
00:01:40,939 --> 00:01:46,931
then how to sign in: a Claude plan, or an
Anthropic Console account for an API key.

22
00:01:48,282 --> 00:01:53,386
Your browser opens. Sign in there,
and the terminal says: login successful.

23
00:01:55,700 --> 00:01:59,510
Step five: it reminds you
that Claude can make mistakes,

24
00:01:59,661 --> 00:02:02,568
and that you're responsible
for reviewing what it does.

25
00:02:03,356 --> 00:02:05,544
Then it asks whether
you trust this folder.

26
00:02:05,916 --> 00:02:08,625
It's your own project folder,
so: yes.

27
00:02:12,500 --> 00:02:16,102
Step six:
Claude Code now starts in auto mode,

28
00:02:16,232 --> 00:02:18,904
where a second model
approves most of its actions.

29
00:02:19,434 --> 00:02:23,596
While you learn, press Shift
and Tab once, for manual mode.

30
00:02:23,760 --> 00:02:27,550
In manual mode, it stops
and asks you before it edits a file,

31
00:02:27,681 --> 00:02:30,106
runs a command,
or reaches the network.

32
00:02:34,100 --> 00:02:37,832
Step seven: ask it something.
What's in this folder?

33
00:02:40,635 --> 00:02:44,057
It reads the notes and the data,
and answers in plain words.

34
00:02:44,447 --> 00:02:47,119
To open the Word drafts,
it needs to run a converter:

35
00:02:47,389 --> 00:02:50,110
that's a command,
so it asks you first.

36
00:02:55,700 --> 00:02:58,246
Step eight:
when you trust it with a task,

37
00:02:58,397 --> 00:03:02,056
press Shift and Tab until the
status line says auto mode.

38
00:03:02,447 --> 00:03:05,234
It works without stopping,
and much faster.

39
00:03:05,434 --> 00:03:09,400
Anthropic's own advice:
auto mode reduces permission prompts,

40
00:03:09,550 --> 00:03:11,473
but it doesn't guarantee safety.

41
00:03:14,900 --> 00:03:20,221
Pause now: install Claude Code, open
a new terminal, and check the version.

42
00:03:24,500 --> 00:03:29,932
So: one line to install, a new terminal,
your project folder, sign in,

43
00:03:30,244 --> 00:03:35,114
trust the folder, manual mode first,
then auto mode when you trust it.

44
00:03:36,300 --> 00:03:38,166
Next: a worked example.

45
00:03:38,598 --> 00:03:42,971
Agents read a whole literature folder
in parallel, and check every claim.