vidtheque.

read-only demo

Videos UcYoMg-8-L8

500 people vibe-coded for 30 days. I was one of them. - Sanja Grbic, Automattic

index_state ready data_status ok

AI Engineer· published 2026-07-07· 0:17:48· en-US· indexed 2026-08-11 05:09

Open on YouTube

Scene timeline

  1. Shot 0, 0:00 to 0:02, 1 of 1 keyframes kept
  2. Shot 1, 0:02 to 0:34, 1 of 1 keyframes kept
  3. Shot 2, 0:34 to 1:12, 1 of 1 keyframes kept
  4. Shot 3, 1:12 to 1:49, 1 of 1 keyframes kept
  5. Shot 4, 1:49 to 2:15, 1 of 1 keyframes kept
  6. Shot 5, 2:15 to 2:40, 0 of 1 keyframes kept
  7. Shot 6, 2:40 to 3:06, 0 of 1 keyframes kept
  8. Shot 7, 3:06 to 3:43, 1 of 1 keyframes kept
  9. Shot 8, 3:43 to 4:19, 0 of 1 keyframes kept
  10. Shot 9, 4:19 to 4:52, 0 of 1 keyframes kept
  11. Shot 10, 4:52 to 5:24, 1 of 1 keyframes kept
  12. Shot 11, 5:24 to 5:56, 0 of 1 keyframes kept
  13. Shot 12, 5:56 to 6:43, 1 of 1 keyframes kept
  14. Shot 13, 6:43 to 6:45, 1 of 1 keyframes kept
  15. Shot 14, 6:45 to 6:56, 0 of 1 keyframes kept
  16. Shot 15, 6:56 to 7:01, 1 of 1 keyframes kept
  17. Shot 16, 7:01 to 7:15, 0 of 1 keyframes kept
  18. Shot 17, 7:15 to 7:44, 1 of 1 keyframes kept
  19. Shot 18, 7:44 to 8:14, 0 of 1 keyframes kept
  20. Shot 19, 8:14 to 8:43, 0 of 1 keyframes kept
  21. Shot 20, 8:43 to 9:10, 1 of 1 keyframes kept
  22. Shot 21, 9:10 to 9:38, 0 of 1 keyframes kept
  23. Shot 22, 9:38 to 10:05, 1 of 1 keyframes kept
  24. Shot 23, 10:05 to 10:33, 0 of 1 keyframes kept
  25. Shot 24, 10:33 to 11:00, 0 of 1 keyframes kept
  26. Shot 25, 11:00 to 11:04, 1 of 1 keyframes kept
  27. Shot 26, 11:04 to 11:07, 1 of 1 keyframes kept
  28. Shot 27, 11:07 to 11:33, 1 of 1 keyframes kept
  29. Shot 28, 11:33 to 11:36, 0 of 1 keyframes kept
  30. Shot 29, 11:36 to 12:02, 0 of 1 keyframes kept
  31. Shot 30, 12:02 to 12:03, 1 of 1 keyframes kept
  32. Shot 31, 12:03 to 12:05, 1 of 1 keyframes kept
  33. Shot 32, 12:05 to 12:32, 0 of 1 keyframes kept
  34. Shot 33, 12:32 to 12:33, 0 of 1 keyframes kept
  35. Shot 34, 12:33 to 13:20, 1 of 1 keyframes kept
  36. Shot 35, 13:20 to 13:57, 1 of 1 keyframes kept
  37. Shot 36, 13:57 to 14:01, 1 of 1 keyframes kept
  38. Shot 37, 14:01 to 14:05, 1 of 1 keyframes kept
  39. Shot 38, 14:05 to 14:25, 1 of 1 keyframes kept
  40. Shot 39, 14:25 to 14:32, 1 of 1 keyframes kept
  41. Shot 40, 14:32 to 14:35, 1 of 1 keyframes kept
  42. Shot 41, 14:35 to 14:36, 1 of 1 keyframes kept
  43. Shot 42, 14:36 to 15:04, 1 of 1 keyframes kept
  44. Shot 43, 15:04 to 15:31, 0 of 1 keyframes kept
  45. Shot 44, 15:31 to 15:58, 0 of 1 keyframes kept
  46. Shot 45, 15:58 to 16:23, 1 of 1 keyframes kept
  47. Shot 46, 16:23 to 16:48, 0 of 1 keyframes kept
  48. Shot 47, 16:48 to 17:13, 0 of 1 keyframes kept
  49. Shot 48, 17:13 to 17:45, 1 of 1 keyframes kept
  50. Shot 49, 17:45 to 17:48, 1 of 1 keyframes kept

50 shot(s).

keyframes kept every frame deduplicated

What was stored

cues
147
whisperx 147
chunks
30
from 147 cues
keyframes
30
kept of 50 captured
frames with text
30
791 lines read
chapters
0
from the source metadata
keyframe bytes
4.7 MB
word timings on 147 cues

Provenance

Each pipeline stage, its state and the model that produced it
stage state model started took
fetch done — 2026-08-11 05:06 1m 08s
stt done — 2026-08-11 05:07 18s
chunk done — 2026-08-11 05:07 0s
text_embed done — 2026-08-11 05:07 1s
keyframe done — 2026-08-11 05:07 1m 49s
ocr done — 2026-08-11 05:09 12s
frame_embed done — 2026-08-11 05:09 5s

Frames, and what the machine read

  • 0:01 #0 done6 line(s)

    shot 0·sharpness 1704.0

    1. AUTOMATTIC1.00
    2. 500 people vibe-1.00
    3. coded for 30 days.1.00
    4. I was one of them.1.00
    5. Sanja Grbic0.97
    6. Product Designer1.00

  • 0:15 #1 done7 line(s)

    shot 1·sharpness 836.8

    1. Radical Speed Month1.00
    2. 301.00
    3. 5011.00
    4. 7940.98
    5. Days1.00
    6. People participating1.00
    7. Projects started1.00

  • 1:04 #2 done3 line(s)

    shot 2·sharpness 466.2

    1. ④t日空四口风○①日0.54
    2. w0.82
    3. AUTOMATTIC0.99

  • 1:31 #3 done3 line(s)

    shot 3·sharpness 1657.9

    1. Sanja Grbic1.00
    2. Product Designer1.00
    3. linkedin.com/in/sanjagrbic/1.00

  • 2:02 #4 done10 line(s)

    shot 4·sharpness 1468.6

    1. The promise of Al0.99
    2. ALIGNMENT1.00
    3. is speed1.00
    4. 0→1 Product1.00
    5. 1-3 people1.00
    6. CONTEXT1.00
    7. VS0.96
    8. 5-20yo Product ecosystem1.00
    9. 1400+ people0.99
    10. HISTORY1.00

  • 2:35 #5 skipped

    shot 5·duplicate of #4

  • 3:03 #6 skipped

    shot 6·duplicate of #4

  • 3:35 #7 done8 line(s)

    shot 7·sharpness 1825.5

    1. Al Enablement at0.98
    2. Automattic1.00
    3. Al Enablement Initiative1.00
    4. Tools, courses, and a two-week internal training.0.99
    5. Security and documentation1.00
    6. To spin up a working dev environment.1.00
    7. Contex-A8C1.00
    8. Al tools access to Slack, Linear, P21.00

  • 4:04 #8 skipped

    shot 8·duplicate of #7

  • 4:35 #9 skipped

    shot 9·duplicate of #1

  • 4:58 #10 done7 line(s)

    shot 10·sharpness 845.1

    1. Radical Speed Month1.00
    2. 301.00
    3. 5011.00
    4. 7940.98
    5. Days1.00
    6. People participating1.00
    7. Projects started1.00

  • 5:34 #11 skipped

    shot 11·duplicate of #1

  • 6:33 #12 done8 line(s)

    shot 12·sharpness 1960.9

    1. 1 — Boardgame session manager0.99
    2. WHAT1.00
    3. An app used for creating, viewing, joining0.99
    4. and managing board game event0.99
    5. 2h1.00
    6. sessions. Including a chat feature.0.99
    7. TEAM1.00
    8. 4 people0.99

  • 6:44 #13 done41 line(s)

    shot 13·sharpness 1668.0

    1. Sanja1.00
    2. GAME1.00
    3. SETTINGS1.00
    4. BOARD GAME NIGHT0.99
    5. +0.98
    6. Carcasso..0.99
    7. +0.97
    8. +0.97
    9. Chess1.00
    10. GAME0.99
    11. 1# JOIN0.86
    12. GAME1.00
    13. GAME0.91
    14. 1n0.78
    15. SOIN0.90
    16. +0.93
    17. +0.92
    18. +0.98
    19. +0.94
    20. +0.93
    21. GAHE0.96
    22. GAME1.00
    23. GAME0.99
    24. GAME0.93
    25. GAME0.91
    26. +0.99
    27. +0.96
    28. GAME0.94
    29. GAME1.00
    30. GAME1.00
    31. GAME0.96
    32. GAME0.94
    33. +0.97
    34. +0.93
    35. +0.97
    36. GAME0.86
    37. GAME1.00
    38. GAME0.96
    39. GAME0.96
    40. YOU1.00
    41. ENTER0.85

  • 6:48 #14 skipped

    shot 14·duplicate of #13

  • 6:58 #15 done50 line(s)

    shot 15·sharpness 1637.6

    1. Chess0.99
    2. Sanja1.00
    3. Chess1.00
    4. hosted by Paolo1.00
    5. BOARD GAME NIGHT0.99
    6. ~30 min 2-2 plauers suggested0.96
    7. Paolo1.00
    8. Sanja0.99
    9. Chat0.97
    10. No messages yet. Say hi!0.97
    11. +0.96
    12. Carcasso..0.99
    13. +0.97
    14. +0.97
    15. Chess1.00
    16. GAME0.98
    17. 1# JOIN0.85
    18. GAME1.00
    19. GAME0.98
    20. 2± JOIN0.87
    21. Say something...0.96
    22. Send1.00
    23. (Enter to send).0.95
    24. +0.95
    25. +0.96
    26. +0.96
    27. +0.97
    28. +0.91
    29. GAHE0.90
    30. GAME1.00
    31. GAME1.00
    32. GAME0.91
    33. GAME0.93
    34. +0.99
    35. +0.98
    36. GAHE0.89
    37. GAME1.00
    38. GAME1.00
    39. GAME0.94
    40. GAHE0.89
    41. +0.98
    42. +0.96
    43. +0.96
    44. +0.97
    45. GAME0.98
    46. GAME1.00
    47. GAME0.89
    48. GAME0.92
    49. YOU1.00
    50. ENTER0.71

  • 7:12 #16 skipped

    shot 16·duplicate of #13

  • 7:32 #17 done24 line(s)

    shot 17·sharpness 806.8

    1. DESIGNER1.00
    2. DEVELOPER1.00
    3. Rename empty table slot label from HOST to GAME0.99
    4. p3ob7o committed on May 40.99
    5. 05684810.93
    6. Merge feature/ui-cuteness into main1.00
    7. grbicsanja and claude committed on May 40.99
    8. 10a309c1.00
    9. <>0.57
    10. Apply pixel font and lobby background image throughout UI1.00
    11. grbicsanja and claude committed on May 40.99
    12. 361b5690.99
    13. <>0.56
    14. Let the host minimize back to the lobby without ending the session1.00
    15. ()0.70
    16. dcamozzi and claude committed on May 40.99
    17. 6eda59b0.95
    18. <>0.50
    19. Add tunnel script and prod static perf for laptop hosting1.00
    20. sunyatasattva and claude committed on May 41.00
    21. #0150b60.92
    22. <>0.90
    23. PRODUCT1.00
    24. DESIGNER1.00

  • 7:53 #18 skipped

    shot 18·duplicate of #17

  • 8:31 #19 skipped

    shot 19·duplicate of #17

  • 9:07 #20 done4 line(s)

    shot 20·sharpness 1562.3

    1. The impact of enabling others may0.97
    2. be greater than the impact of doing0.99
    3. more engineering yourself.0.97
    4. O0.65

  • 9:34 #21 skipped

    shot 21·duplicate of #20

  • 10:02 #22 done9 line(s)

    shot 22·sharpness 2017.2

    1. 2 - DS-tracker0.92
    2. WHAT1.00
    3. Design System tracker - one place to1.00
    4. browse, preview, and search for design1.00
    5. 2.5W-0.97
    6. components, with links and status.0.99
    7. TEAM1.00
    8. Discovery: 3 people1.00
    9. Design and build: Solo0.99

  • 10:16 #23 skipped

    shot 23·duplicate of #22

Transcript

147 cues· 2,525 words· 13,817 chars

  1. 0:01 Hi there, welcome to my talk.
  2. 0:03 My name is Sanja and today I'm going to share with you an experiment we did at our company that's somewhat unusual and very exciting.
  3. 0:14 It was a one month initiative called Radical Speed Month where two person teams were given full autonomy to build and ship projects.
  4. 0:22 I built three projects during this time.
  5. 0:24 I will walk you through them, and we'll talk about the outcomes and learnings for myself as a designer, as well as the system-wide impact this experiment had.
  6. 0:37 I'll tell you a little bit about Automatic first.
  7. 0:39 We're the company behind several products in the WordPress ecosystem, such as WordPress.com, Jetpack, WooCommerce, as well as many other brands like Tumblr, Beeper, and many more.
  8. 0:52 We are around 1400 people and we're fully distributed, which is pretty interesting for also what I'm about to show you.
  9. 1:02 We're fully distributed and asynchronous, which means that most of our work, our thoughts, our concepts from the past couple of decades are very well documented.
  10. 1:14 I'm a product designer and I've spent over a decade building software and watching how teams build software.
  11. 1:21 I've worked for, I've been at Automatic for five years now on the Jetpack design team.
  12. 1:28 And in the past I worked for several companies of different sizes, different types of products and different team configurations.
  13. 1:37 So after all these years,
  14. 1:39 I've not only accumulated experience in designing products, I also have a lot of insight into team dynamics and organizational structures within product teams.
  15. 1:52 Over the years, the designer role has morphed and evolved a lot.
  16. 1:58 We still have all of these different types of roles like web designers or UX designers or interaction or product designers.
  17. 2:06 We've also used many different tools from the Adobe Suite to Sketch to Figma and many, many others in addition to those.
  18. 2:16 And AI is a new tool.
  19. 2:18 It is definitely not built just for designers.
  20. 2:22 It's versatile, so it can be used by many different roles, but the expectation is the same for everyone.
  21. 2:31 It's that it will bring us speed.
  22. 2:34 And of course, this is why companies are rushing to put it to use.
  23. 2:37 But no matter what role uses AI, this velocity is going to look very different in small teams, like one to three people that are building new products, let's say a zero to one product,
  24. 2:51 versus large organizations that might have built entire product ecosystems, that have software that's anywhere between five and 20 years old, and that have more than a thousand or even thousands of people.
  25. 3:07 Before I dive into the experiment, I will tell you a little bit about what preceded it in terms of how we use AI at Automatic.
  26. 3:15 We were encouraged to use it, to learn it, and to experiment with AI from the very beginning.
  27. 3:20 At first, we had access to tools and courses.
  28. 3:24 Then the AI enablement project was initiated where every single employee goes through a two week course designed specifically for their role.
  29. 3:31 This is completely immersive with lectures and focused hands on time.
  30. 3:36 Very, very helpful.
  31. 3:38 And over time, as AI coding tools got better, everyone was encouraged to get comfortable with contributing in code.
  32. 3:45 And we can thank our systems and operations team for setting up fantastic security and processes as well as documentation that's good enough that a non-engineer such as myself can spin up a working development environment.
  33. 4:00 And last but not least, an incredibly helpful tool that I use every day for research.
  34. 4:07 And planning is Context AHC.
  35. 4:10 It's an MCP server that gives AI tools access to all the knowledge and data that we have documented over the years that I previously mentioned.
  36. 4:21 So back to the experiment.
  37. 4:23 About two months ago, we kicked off this project.
  38. 4:26 The instructions were to pause the roadmap work for 30 days, pair with a partner, and ship something real.
  39. 4:33 We were welcome to use AI, though it wasn't a requirement.
  40. 4:36 And of course,
  41. 4:39 We couldn't all do this at once.
  42. 4:40 We had to do this in stages.
  43. 4:42 And we had about a third of the company participating in the first round.
  44. 4:46 That's around 500 people that started around 794 projects in these 30 days.
  45. 4:54 One lucky circumstance for me was that during this month, I was also participating in this two-week in-person AI enablement course.
  46. 5:01 So AI tools played a huge role in what I was able to deliver.
  47. 5:06 And that's why I was building not one, but three different projects.
  48. 5:12 And when Radical Speed Month started, I had some knowledge of GitHub.
  49. 5:18 I would review PRs.
  50. 5:19 I had played around with Cloud Code.

Open at this second