1
00:00:00,500 --> 00:00:03,949
Both decks come from the same paper,
agent and model;

2
00:00:04,321 --> 00:00:07,007
the one on the right had
the presenter's style brief.

3
00:00:07,668 --> 00:00:09,413
The same check, run on both:

4
00:00:09,846 --> 00:00:13,617
two hundred and three failures on the left,
forty-one on the right.

5
00:00:14,338 --> 00:00:18,043
Anthropic names the pull toward
the same look, for web pages:

6
00:00:18,373 --> 00:00:23,419
distributional convergence, a model reaching
for the most common fonts and colors.

7
00:00:26,800 --> 00:00:32,580
AI for Research Efficiency, In Practice.
Make a slide deck that looks like yours.

8
00:00:33,900 --> 00:00:39,046
In this film, a paper and its data become an
editable PowerPoint deck in your own style,

9
00:00:39,276 --> 00:00:42,800
with one chart that builds in steps,
checked against your brief.

10
00:00:43,633 --> 00:00:47,581
Recorded runs in Codex,
using four lessons from the series.

11
00:00:50,900 --> 00:00:53,141
Step one: ask for the process.

12
00:00:53,652 --> 00:00:57,784
The folder holds the paper, its data,
the presenter's website style,

13
00:00:57,954 --> 00:01:01,776
the look of this series,
and a sample of the presenter's own writing.

14
00:01:02,736 --> 00:01:06,626
The request, in plan mode:
what is the best way to make a deck

15
00:01:06,676 --> 00:01:09,132
from this paper that looks
and sounds like me?

16
00:01:09,644 --> 00:01:12,510
Interview me first,
and don't build anything yet.

17
00:01:14,611 --> 00:01:21,224
Shift Tab cycles to plan mode, or type slash
plan, in Codex, Claude Code and Antigravity.

18
00:01:22,225 --> 00:01:26,914
Codex asks eleven questions,
in four rounds, before it writes a plan.

19
00:01:29,300 --> 00:01:35,058
Step two: options. Three helpers look
into the ways to do this, all at once.

20
00:01:36,119 --> 00:01:39,807
The first finds what four vendors
do about decks that look alike:

21
00:01:40,238 --> 00:01:42,614
each lets you give its tool your own slides,

22
00:01:42,804 --> 00:01:46,311
a theme or a brand kit to follow,
much like a style brief.

23
00:01:47,452 --> 00:01:52,195
The second compares ways to make a file
you can still edit: PowerPoint by hand,

24
00:01:52,365 --> 00:01:56,117
a JavaScript library,
or Python's P P T X library,

25
00:01:56,287 --> 00:01:59,238
which makes real PowerPoint charts
with their numbers behind them,

26
00:01:59,409 --> 00:02:01,189
and doesn't need PowerPoint.

27
00:02:02,290 --> 00:02:05,632
The third finds how a chart
can move and stay editable.

28
00:02:06,102 --> 00:02:11,945
Shapes can morph from one slide to the next;
PowerPoint's own charts don't, they cross-fade.

29
00:02:14,900 --> 00:02:19,413
Step three: a reviewer agent tests
each option against the real files,

30
00:02:19,564 --> 00:02:22,551
and reports only the problems
that would change the result.

31
00:02:23,772 --> 00:02:27,457
Before the run, we listed nine
traps we knew were in this folder,

32
00:02:27,607 --> 00:02:32,994
and the agents never saw the list. The reviewer
found three of them, and part of a fourth.

33
00:02:34,295 --> 00:02:36,437
It also found a problem we hadn't listed:

34
00:02:36,747 --> 00:02:41,652
the paper's own figure stacks the closed
articles too, up to a hundred percent.

35
00:02:43,212 --> 00:02:45,334
The other five came up at other steps.

36
00:02:45,824 --> 00:02:46,815
In its first look,

37
00:02:46,945 --> 00:02:51,518
the agent noticed that the presenter's website
and video series use different fonts;

38
00:02:51,909 --> 00:02:53,100
the website's Lato

39
00:02:53,150 --> 00:02:58,194
and Open Sans are both on Anthropic's
twenty twenty-five list of fonts to avoid.

40
00:02:59,151 --> 00:03:03,378
And writing the brief, it found the brand's
bright orange reaches two point seven

41
00:03:03,428 --> 00:03:07,415
to one on its background,
where a chart mark needs three to one.

42
00:03:08,898 --> 00:03:11,505
Some university templates
need the same check.

43
00:03:12,057 --> 00:03:17,472
In one we tested, the first chart color
reaches two point six seven to one on white.

44
00:03:19,700 --> 00:03:22,824
Step four: decide, and write it down.

45
00:03:23,255 --> 00:03:28,251
The presenter chooses the series' font for
everything and the bright orange as a tint only,

46
00:03:28,722 --> 00:03:33,487
and the agent writes the process as a skill,
a file it reads every time.

47
00:03:34,788 --> 00:03:39,252
The brief inside it puts the sources in
order, so a disagreement has an answer,

48
00:03:39,642 --> 00:03:42,424
and gives each color
only the jobs it can do.

49
00:03:43,424 --> 00:03:46,812
For the voice, it keeps a sample
of the presenter's own writing,

50
00:03:46,942 --> 00:03:49,467
from before any AI tool touched it.

51
00:03:50,548 --> 00:03:55,950
And a dated list of looks to avoid, each
with its source, because the looks change.

52
00:03:58,100 --> 00:04:04,708
Step five: the run. Check each step at first;
once the steps look right, let it run.

53
00:04:06,309 --> 00:04:07,950
It counts the data itself.

54
00:04:08,340 --> 00:04:13,253
The file ends its lines the way old Macs
did, and its text isn't U T F eight.

55
00:04:13,624 --> 00:04:16,715
It reads it as Mac Roman, the old Mac text,

56
00:04:16,926 --> 00:04:20,928
and keeps the paper's years,
nineteen fifty to twenty fifteen.

57
00:04:22,076 --> 00:04:26,102
Its count for twenty fifteen:
forty-four point seven two percent.

58
00:04:26,493 --> 00:04:29,457
The paper prints forty-four
point seven percent.

59
00:04:31,212 --> 00:04:35,935
The chart that builds is drawn as shapes,
each named with two exclamation marks,

60
00:04:36,185 --> 00:04:41,467
so Morph can match it on the next slide, where
a mask slides back to show the later years.

61
00:04:44,608 --> 00:04:49,673
Then the same numbers as a PowerPoint chart
you can edit, with its data inside the file.

62
00:04:51,165 --> 00:04:52,972
Every slide becomes a picture,

63
00:04:53,183 --> 00:04:57,238
and a second agent that hasn't seen
the code compares them with the brief.

64
00:04:59,459 --> 00:05:04,909
Its report: six problems, from a chart
that jumps between two slides to a title

65
00:05:04,959 --> 00:05:09,807
that reads like a date. The first
agent fixes all six and renders again.

66
00:05:11,350 --> 00:05:13,932
About fifty-six minutes, start to finish.

67
00:05:17,300 --> 00:05:20,871
Step six: check it against
something outside the agent.

68
00:05:21,283 --> 00:05:24,673
A script reads the deck file
and tests it against the brief.

69
00:05:25,914 --> 00:05:29,137
Text needs four point five
to one against its background;

70
00:05:29,567 --> 00:05:34,081
large text and chart marks need three
to one. Nothing under eighteen points.

71
00:05:34,531 --> 00:05:38,854
Every slide gets its own title,
and every chart its alternative text.

72
00:05:41,394 --> 00:05:43,579
Then the voice: sentence length,

73
00:05:43,689 --> 00:05:48,379
and how often it says I or we,
against the presenter's own sample.

74
00:05:49,289 --> 00:05:56,134
One study found that AI summaries of engineering
reports made almost no use of the first person,

75
00:05:56,184 --> 00:05:57,144
though the reports used it with care.

76
00:05:58,564 --> 00:06:04,028
On this deck: thirty-seven failures, most
of them source lines under eighteen points,

77
00:06:04,259 --> 00:06:06,490
and titles a screen reader can't find.

78
00:06:06,861 --> 00:06:08,612
What it can't see is the data:

79
00:06:08,982 --> 00:06:12,855
the chart keeps a test publisher's rows
that the paper's code leaves out,

80
00:06:13,146 --> 00:06:16,608
which moves the year two thousand
by seven tenths of a point.

81
00:06:18,386 --> 00:06:22,129
Two looks are left for you:
PowerPoint's own Accessibility Checker,

82
00:06:22,400 --> 00:06:27,865
and a last pass in PowerPoint itself, since
the preview swaps any font it doesn't have.

83
00:06:31,700 --> 00:06:36,884
The same skill with another person's brief:
an extension agronomist, made up for this film,

84
00:06:37,134 --> 00:06:40,196
and the E P A's table of
methane from rice fields.

85
00:06:42,356 --> 00:06:47,319
Its agent noticed the skill held another
presenter's brief, and used this author's own:

86
00:06:47,769 --> 00:06:53,573
Lato, field greens, plain words for growers.
The deck looks nothing like the first.

87
00:06:58,100 --> 00:07:01,606
Use only fonts, pictures
and logos you're allowed to use.

88
00:07:01,936 --> 00:07:07,805
An open font can travel inside the deck; a
university's logo is usually for its own units.

89
00:07:08,849 --> 00:07:13,708
And if your venue or your institution
asks you to say where AI helped, say so.

90
00:07:17,300 --> 00:07:22,774
Pause and try it with the practice folder from
the companion page: ask for the best way first.

91
00:07:23,085 --> 00:07:26,814
Your agent should ask you questions
before it makes a single file.

92
00:07:31,600 --> 00:07:34,606
So: a brief first, a chart that builds,

93
00:07:34,957 --> 00:07:38,523
fresh eyes on every slide,
and a check against the brief.

94
00:07:41,200 --> 00:07:44,810
Next: let adversarial
reviewers check your paper.