1
00:00:00,900 --> 00:00:04,163
One agent, four small jobs,
one after another:

2
00:00:04,533 --> 00:00:10,077
a list, a table, a chart and a check.
2 minutes 24 seconds.

3
00:00:12,758 --> 00:00:18,074
Four agents, the same four jobs,
at the same time: 35 seconds.

4
00:00:22,000 --> 00:00:25,449
AI for Research Efficiency.

5
00:00:25,499 --> 00:00:28,005
Episode 8: Many agents at once.

6
00:00:31,500 --> 00:00:35,803
Last time: tokens, and the one
allowance every agent draws on.

7
00:00:36,528 --> 00:00:40,316
In this episode:
run several agents at once, safely,

8
00:00:40,527 --> 00:00:44,315
and ask for parallel work in
words every tool understands.

9
00:00:46,100 --> 00:00:48,326
One: two ways to scale.

10
00:00:49,139 --> 00:00:53,406
Open more terminals, and start one
agent in each, with its own task.

11
00:00:54,564 --> 00:00:58,488
Or ask one agent to split the work
and run helpers in parallel.

12
00:00:59,039 --> 00:01:02,313
In episode 3,
one agent ran 17 of them:

13
00:01:02,704 --> 00:01:06,347
8 readers at once,
then 8 checkers, then a writer.

14
00:01:10,100 --> 00:01:12,410
Two: tabs and panes.

15
00:01:13,196 --> 00:01:16,823
In Windows Terminal,
Ctrl+Shift+T opens a new tab,

16
00:01:17,073 --> 00:01:20,659
and Alt+Shift+D splits the
window into a second pane.

17
00:01:22,347 --> 00:01:24,849
Alt and the arrow keys
move between panes;

18
00:01:25,059 --> 00:01:29,922
with Shift, the arrows resize them.
Ctrl+Shift+W closes one.

19
00:01:31,632 --> 00:01:35,541
A new tab or pane starts in your
home folder, not the one you were in.

20
00:01:35,913 --> 00:01:39,200
So go to your project folder again,
then start the agent.

21
00:01:40,740 --> 00:01:46,571
On a Mac, Command+T opens a new tab;
or put two Terminal windows side by side.

22
00:01:48,500 --> 00:01:50,586
Three: the one rule.

23
00:01:51,329 --> 00:01:54,031
Two agents must never
edit the same file.

24
00:01:54,462 --> 00:01:58,464
Let them read the same files, and
give each one its own file to write.

25
00:01:59,805 --> 00:02:02,229
That's how these four worked:
one folder,

26
00:02:02,420 --> 00:02:06,046
four agents, four new files,
and nothing overwritten.

27
00:02:07,546 --> 00:02:11,916
If they must change the same files,
every vendor's answer is a worktree:

28
00:02:12,368 --> 00:02:15,815
a second working copy of the project,
on its own branch.

29
00:02:16,981 --> 00:02:21,608
Claude Code starts one with -w,
Codex with --worktree,

30
00:02:21,838 --> 00:02:24,071
and Antigravity can give
its helpers their own.

31
00:02:24,562 --> 00:02:27,846
Each needs a repository,
like the one from episode 5.

32
00:02:31,700 --> 00:02:34,745
Four: ask one agent to fan out.

33
00:02:35,548 --> 00:02:37,013
No special words are needed.

34
00:02:37,345 --> 00:02:41,018
Say how to split the work, whether
to wait, and what to bring back.

35
00:02:42,172 --> 00:02:45,257
For example:
split this into independent parts,

36
00:02:45,348 --> 00:02:50,206
and run one subagent per part in
parallel. Each writes only its own file.

37
00:02:50,597 --> 00:02:54,783
Wait for all of them, then combine the
results, and list anything that failed.

38
00:02:56,464 --> 00:02:59,589
Claude Code started three helpers,
one per paper,

39
00:02:59,840 --> 00:03:02,394
and combined their findings
when all three were back.

40
00:03:02,945 --> 00:03:05,969
Codex and Antigravity did
the same with their own.

41
00:03:10,100 --> 00:03:15,373
Five: each tool's own words, because
the same word can mean different things.

42
00:03:16,374 --> 00:03:20,404
In Claude Code, ultracode starts
a workflow of many subagents,

43
00:03:20,595 --> 00:03:24,344
while ultrathink only means
deeper reasoning, on one turn.

44
00:03:25,471 --> 00:03:28,537
In Codex, Ultra is the
highest reasoning effort,

45
00:03:28,688 --> 00:03:31,012
and it splits the
work across subagents.

46
00:03:32,013 --> 00:03:35,635
Antigravity calls its
versions teamwork and boost.

47
00:03:36,844 --> 00:03:39,287
So name the tool along with the word.

48
00:03:39,678 --> 00:03:43,904
The full list, with each term's nearest
match, is on the companion page.

49
00:03:48,500 --> 00:03:51,097
Six: how far it scales.

50
00:03:52,019 --> 00:03:55,763
Every agent draws on the same
allowance, from episode 7.

51
00:03:56,697 --> 00:03:58,359
And there are built-in ceilings:

52
00:03:58,669 --> 00:04:01,872
Claude Code runs up
to 20 subagents at once.

53
00:04:03,072 --> 00:04:07,895
And every result still needs checking.
Run only as many as you can check.

54
00:04:10,100 --> 00:04:15,606
Pause here, and try it: two panes,
two tasks, each writing its own file.

55
00:04:19,700 --> 00:04:24,871
So: split the work, give each agent its
own file, and check what comes back.

56
00:04:26,700 --> 00:04:30,771
Next: your data,
your keys, your campus.