vidtheque.

read-only demo

Videos sJ2jc7leKBk

I Gave an AI Agent the Keys to My Life (Here's What Happened) — Radek Sienkiewicz (@velvetshark-com)

index_state ready data_status ok

AI Engineer· published 2026-05-02· 0:19:33· en-US· indexed 2026-08-10 22:36

Open on YouTube

Scene timeline

  1. Shot 0, 0:00 to 0:05, 1 of 1 keyframes kept
  2. Shot 1, 0:05 to 0:09, 1 of 1 keyframes kept
  3. Shot 2, 0:09 to 0:14, 1 of 1 keyframes kept
  4. Shot 3, 0:14 to 0:20, 1 of 1 keyframes kept
  5. Shot 4, 0:20 to 0:27, 1 of 1 keyframes kept
  6. Shot 5, 0:27 to 0:33, 1 of 1 keyframes kept
  7. Shot 6, 0:33 to 0:43, 1 of 1 keyframes kept
  8. Shot 7, 0:43 to 1:04, 1 of 1 keyframes kept
  9. Shot 8, 1:04 to 1:12, 1 of 1 keyframes kept
  10. Shot 9, 1:12 to 1:15, 1 of 1 keyframes kept
  11. Shot 10, 1:15 to 1:32, 1 of 1 keyframes kept
  12. Shot 11, 1:32 to 1:44, 1 of 1 keyframes kept
  13. Shot 12, 1:44 to 1:52, 1 of 1 keyframes kept
  14. Shot 13, 1:52 to 2:18, 1 of 1 keyframes kept
  15. Shot 14, 2:18 to 2:43, 1 of 1 keyframes kept
  16. Shot 15, 2:43 to 3:08, 0 of 1 keyframes kept
  17. Shot 16, 3:08 to 3:10, 1 of 1 keyframes kept
  18. Shot 17, 3:10 to 3:32, 1 of 1 keyframes kept
  19. Shot 18, 3:32 to 3:48, 1 of 1 keyframes kept
  20. Shot 19, 3:48 to 3:57, 1 of 1 keyframes kept
  21. Shot 20, 3:57 to 4:46, 1 of 1 keyframes kept
  22. Shot 21, 4:46 to 4:48, 1 of 1 keyframes kept
  23. Shot 22, 4:48 to 4:57, 1 of 1 keyframes kept
  24. Shot 23, 4:57 to 5:10, 1 of 1 keyframes kept
  25. Shot 24, 5:10 to 5:12, 1 of 1 keyframes kept
  26. Shot 25, 5:12 to 5:47, 1 of 1 keyframes kept
  27. Shot 26, 5:47 to 6:02, 1 of 1 keyframes kept
  28. Shot 27, 6:02 to 6:12, 0 of 1 keyframes kept
  29. Shot 28, 6:12 to 6:30, 1 of 1 keyframes kept
  30. Shot 29, 6:30 to 6:57, 1 of 1 keyframes kept
  31. Shot 30, 6:57 to 7:07, 1 of 1 keyframes kept
  32. Shot 31, 7:07 to 7:09, 1 of 1 keyframes kept
  33. Shot 32, 7:09 to 7:42, 1 of 1 keyframes kept
  34. Shot 33, 7:42 to 7:54, 1 of 1 keyframes kept
  35. Shot 34, 7:54 to 8:32, 1 of 1 keyframes kept
  36. Shot 35, 8:32 to 8:52, 1 of 1 keyframes kept
  37. Shot 36, 8:52 to 9:09, 1 of 1 keyframes kept
  38. Shot 37, 9:09 to 9:12, 1 of 1 keyframes kept
  39. Shot 38, 9:12 to 9:17, 1 of 1 keyframes kept
  40. Shot 39, 9:17 to 9:32, 1 of 1 keyframes kept
  41. Shot 40, 9:32 to 9:51, 1 of 1 keyframes kept
  42. Shot 41, 9:51 to 10:08, 1 of 1 keyframes kept
  43. Shot 42, 10:08 to 10:12, 0 of 1 keyframes kept
  44. Shot 43, 10:12 to 10:13, 0 of 1 keyframes kept
  45. Shot 44, 10:13 to 10:20, 1 of 1 keyframes kept
  46. Shot 45, 10:20 to 10:27, 1 of 1 keyframes kept
  47. Shot 46, 10:27 to 10:37, 1 of 1 keyframes kept
  48. Shot 47, 10:37 to 10:49, 1 of 1 keyframes kept
  49. Shot 48, 10:49 to 11:07, 1 of 1 keyframes kept
  50. Shot 49, 11:07 to 11:11, 1 of 1 keyframes kept
  51. Shot 50, 11:11 to 11:15, 1 of 1 keyframes kept
  52. Shot 51, 11:15 to 11:51, 1 of 1 keyframes kept
  53. Shot 52, 11:51 to 11:57, 1 of 1 keyframes kept
  54. Shot 53, 11:57 to 12:03, 1 of 1 keyframes kept
  55. Shot 54, 12:03 to 12:12, 1 of 1 keyframes kept
  56. Shot 55, 12:12 to 12:23, 1 of 1 keyframes kept
  57. Shot 56, 12:23 to 12:32, 1 of 1 keyframes kept
  58. Shot 57, 12:32 to 12:58, 1 of 1 keyframes kept
  59. Shot 58, 12:58 to 13:27, 1 of 1 keyframes kept
  60. Shot 59, 13:27 to 13:36, 0 of 1 keyframes kept
  61. Shot 60, 13:36 to 14:04, 0 of 1 keyframes kept
  62. Shot 61, 14:04 to 14:44, 1 of 1 keyframes kept
  63. Shot 62, 14:44 to 14:49, 1 of 1 keyframes kept
  64. Shot 63, 14:49 to 14:50, 1 of 1 keyframes kept
  65. Shot 64, 14:50 to 15:07, 1 of 1 keyframes kept
  66. Shot 65, 15:07 to 15:12, 1 of 1 keyframes kept
  67. Shot 66, 15:12 to 15:17, 1 of 1 keyframes kept
  68. Shot 67, 15:17 to 15:26, 1 of 1 keyframes kept
  69. Shot 68, 15:26 to 15:32, 1 of 1 keyframes kept
  70. Shot 69, 15:32 to 15:39, 1 of 1 keyframes kept
  71. Shot 70, 15:39 to 15:44, 1 of 1 keyframes kept
  72. Shot 71, 15:44 to 16:05, 1 of 1 keyframes kept
  73. Shot 72, 16:05 to 16:12, 1 of 1 keyframes kept
  74. Shot 73, 16:12 to 16:23, 1 of 1 keyframes kept
  75. Shot 74, 16:23 to 16:32, 1 of 1 keyframes kept
  76. Shot 75, 16:32 to 16:41, 1 of 1 keyframes kept
  77. Shot 76, 16:41 to 17:09, 1 of 1 keyframes kept
  78. Shot 77, 17:09 to 17:12, 1 of 1 keyframes kept
  79. Shot 78, 17:12 to 17:32, 1 of 1 keyframes kept
  80. Shot 79, 17:32 to 17:35, 1 of 1 keyframes kept
  81. Shot 80, 17:35 to 17:54, 1 of 1 keyframes kept
  82. Shot 81, 17:54 to 17:56, 1 of 1 keyframes kept
  83. Shot 82, 17:56 to 18:18, 1 of 1 keyframes kept
  84. Shot 83, 18:18 to 19:03, 1 of 1 keyframes kept
  85. Shot 84, 19:03 to 19:17, 0 of 1 keyframes kept
  86. Shot 85, 19:17 to 19:18, 1 of 1 keyframes kept
  87. Shot 86, 19:18 to 19:33, 1 of 1 keyframes kept
  88. Shot 87, 19:33 to 19:33, 0 of 1 keyframes kept

88 shot(s).

keyframes kept every frame deduplicated

What was stored

cues
174
whisperx 174
chunks
34
from 174 cues
keyframes
80
kept of 88 captured
frames with text
80
2,451 lines read
chapters
10
from the source metadata
keyframe bytes
10.5 MB
word timings on 174 cues

Provenance

Each pipeline stage, its state and the model that produced it
stage state model started took
fetch done — 2026-08-10 22:30 1m 48s
stt done — 2026-08-10 22:32 19s
chunk done — 2026-08-10 22:33 0s
text_embed done — 2026-08-10 22:33 0s
keyframe done — 2026-08-10 22:33 2m 22s
ocr done — 2026-08-10 22:35 36s
frame_embed done — 2026-08-10 22:36 13s

Frames, and what the machine read

  • 0:02 #0 done2 line(s)

    shot 0·sharpness 668.7

    1. Al Engineer0.93
    2. EUROPE1.00

  • 0:06 #1 done2 line(s)

    shot 1·sharpness 819.1

    1. PRESENTING SPONSOR0.99
    2. Google DeepMind1.00

  • 0:11 #2 done3 line(s)

    shot 2·sharpness 939.2

    1. PLATINUM SPONSORS0.98
    2. # Braintrust0.95
    3. WorkOS OpenAI0.96

  • 0:17 #3 done33 line(s)

    shot 3·sharpness 990.7

    1. EUROPE1.00
    2. raintrust1.00
    3. AlEngineer0.97
    4. EUROPE1.00
    5. essl1.00
    6. ineer1.00
    7. ner0.99
    8. AlEngineer0.96
    9. Braintrust1.00
    10. ROPE1.00
    11. EUROPE1.00
    12. norkel0.99
    13. AlEng0.92
    14. OpenAI0.92
    15. AlEngineer0.98
    16. Goo1.00
    17. EUROPE1.00
    18. EUROPE1.00
    19. AIEngineer0.97
    20. EUROPE1.00
    21. RESENTED BY1.00
    22. neer1.00
    23. SENT1.00
    24. AIEngineer0.95
    25. Microsoft1.00
    26. ogle DeepMind0.95
    27. EUROPE1.00
    28. ,onar0.95
    29. AlEngine0.98
    30. Modal1.00
    31. AlEngineer0.98
    32. EUROPE1.00
    33. EUROPE1.00

  • 0:21 #4 done9 line(s)

    shot 4·sharpness 1196.2

    1. I Gave an AI Agent0.99
    2. I Gave an AI Agent0.95
    3. the Keys to My Life1.00
    4. the Keys to My Life1.00
    5. AlEngineer0.96
    6. Zed1.00
    7. EUROPE1.00
    8. Braintrust0.97
    9. arize0.99

  • 0:28 #5 done28 line(s)

    shot 5·sharpness 924.6

    1. AIEngineer0.98
    2. Braintrust1.00
    3. AlEngineer0.97
    4. EUROPE1.00
    5. EUROPE1.00
    6. Tes1.00
    7. AlEngineer0.96
    8. neo4j0.98
    9. AIEngineer0.95
    10. EUROPE1.00
    11. EUROPE1.00
    12. Snorkel0.93
    13. AlEngineer0.99
    14. OpenAI0.92
    15. EUROPE1.00
    16. AlEngineer0.98
    17. EUROPE1.00
    18. PRESENTED BY0.99
    19. AlEngineer0.98
    20. SENTRY1.00
    21. AlEngineer0.97
    22. Google DeepMind1.00
    23. EUROPE1.00
    24. EUROPE1.00
    25. Sonar1.00
    26. AlEngineer0.99
    27. Modal0.92
    28. EUROPE1.00

  • 0:38 #6 done20 line(s)

    shot 6·sharpness 1519.6

    1. IEnging0.84
    2. Braintrus1.00
    3. EUROPE1.00
    4. AI ENGINEER EUROPE 20260.97
    5. I Gave an AI Agent0.98
    6. AlEngineer0.98
    7. EUROPE1.00
    8. the Keys to My Life0.98
    9. Snorkel0.99
    10. How a simple setup quietly became life infrastructure0.99
    11. AlEngineer1.00
    12. EUROPE1.00
    13. PRESENTED BY1.00
    14. AlEngineer0.99
    15. Google DeepMind1.00
    16. EUROPE1.00
    17. Sonar1.00
    18. Google DeepMind1.00
    19. AlEngineer0.98
    20. EUROPE1.00

  • 0:52 #7 done27 line(s)

    shot 7·sharpness 1683.5

    1. AIEngineer0.98
    2. Braintri0.96
    3. EUROPE1.00
    4. SURFACE AREA1.00
    5. What “keys to my0.98
    6. Tess0.96
    7. ngineel0.94
    8. UROPE1.00
    9. life" actually means0.99
    10. Snork1.00
    11. • notes0.98
    12. • files0.98
    13. AlEngineer0.99
    14. • reminders0.95
    15. • calendar0.97
    16. EUROPE1.00
    17. PRESENTED BY1.00
    18. AlEngineer0.96
    19. • monitoring0.97
    20. • automations0.95
    21. Google DeepMind1.00
    22. EUROPE1.00
    23. • memory0.93
    24. Sonc0.94
    25. Google DeepMind1.00
    26. AlEngineer0.99
    27. EUROPE1.00

  • 1:10 #8 done20 line(s)

    shot 8·sharpness 1412.6

    1. FUR1.00
    2. SURFACE AREA1.00
    3. What “keys to my0.99
    4. life" actually means1.00
    5. ngin0.99
    6. Brai1.00
    7. • notes0.98
    8. • files0.97
    9. UROPE1.00
    10. • reminders0.94
    11. • calendar0.97
    12. • monitoring0.99
    13. • automations0.96
    14. • memory0.98
    15. er1.00
    16. AlEngineer0.98
    17. # Braintrust0.98
    18. WorkOS1.00
    19. OpenAl0.95
    20. EUROPE1.00

  • 1:13 #9 done17 line(s)

    shot 9·sharpness 1288.5

    1. EUROI0.97
    2. SURFACE AREA1.00
    3. What “keys to my0.98
    4. life" actually means0.99
    5. Braint0.99
    6. • notes0.99
    7. • files0.97
    8. • reminders0.96
    9. • calendar0.98
    10. • monitoring0.99
    11. • automations0.95
    12. • memory0.98
    13. VEngin0.97
    14. EUROP0.84
    15. Engineering the future of Al1.00
    16. AlEngineer0.99
    17. EUROPE1.00

  • 1:24 #10 done23 line(s)

    shot 10·sharpness 1655.2

    1. EUI1.00
    2. THE TURN1.00
    3. This would be reckless1.00
    4. if you did it all at once0.99
    5. Op1.00
    6. The system only became trustworthy because it grew in small, useful1.00
    7. Er0.99
    8. steps.1.00
    9. EU0.99
    10. One giant leap1.00
    11. One permission at a time0.98
    12. – full access immediately0.98
    13. - one workflow at a time0.96
    14. – no track record of good behavior1.00
    15. - one permission at a time0.99
    16. – no time to learn boundaries0.99
    17. - one reason to trust it0.98
    18. eD1.00
    19. AIE1.00
    20. Engine1.00
    21. Engineering the future of Al0.98
    22. AlEngineer0.99
    23. EUROPE1.00

  • 1:41 #11 done22 line(s)

    shot 11·sharpness 1825.3

    1. One permissioniat a time0.92
    2. one woridowtatine0.77
    3. -one pemision ata time0.83
    4. THE TURN0.99
    5. -one reson to tustit0.83
    6. This would be reckless1.00
    7. if you did it all at once1.00
    8. Alngirer0.88
    9. The system only became trustworthy because it grew in small, useful0.99
    10. steps.1.00
    11. Google DeepMind0.92
    12. One giant leap1.00
    13. One permission at a time0.99
    14. – full access immediately0.98
    15. - one workflow at a time0.97
    16. – no track record of good behavior0.98
    17. - one permission at a time0.99
    18. – no time to learn boundaries0.99
    19. - one reason to trust it0.98
    20. Google DeepMind1.00
    21. AlEngineer0.98
    22. EUROPE1.00

  • 1:49 #12 done26 line(s)

    shot 12·sharpness 1985.0

    1. ROPE1.00
    2. THE TURN1.00
    3. This would be reckless1.00
    4. if you did it all at once1.00
    5. enAl0.97
    6. neer1.00
    7. The system only became trustworthy because it grew in small, useful0.99
    8. steps.1.00
    9. One giant leap1.00
    10. One permission at a time0.99
    11. rkO0.76
    12. - full access immediately0.96
    13. - one workflow at a time0.95
    14. ngineer1.00
    15. – no track record of good behavior0.99
    16. - one permission at a time0.99
    17. UROPE0.99
    18. – no time to learn boundaries0.99
    19. - one reason to trust it0.98
    20. AlEngineer1.00
    21. EUROPE1.00
    22. PRESENTED BY1.00
    23. Google DeepMi1.00
    24. Google DeepMind1.00
    25. AlEngineer0.98
    26. EUROPE1.00

  • 2:02 #13 done34 line(s)

    shot 13·sharpness 1997.2

    1. penAl0.97
    2. AlEngineer0.98
    3. EUROPE1.00
    4. THE TURN1.00
    5. This would be reckless1.00
    6. IEnginee0.96
    7. EUROPE1.00
    8. A.SAFE0.83
    9. LIGENCE1.00
    10. if you did it all at once1.00
    11. The system only became trustworthy because it grew in small, useful1.00
    12. Sonc0.86
    13. AlEngineer0.98
    14. steps.1.00
    15. EUROPE1.00
    16. One giant leap1.00
    17. One permission at a time0.99
    18. IEngineer0.96
    19. bright data1.00
    20. - full access immediately0.98
    21. - one workflow at a time0.98
    22. EUROPE1.00
    23. – no track record of good behavior1.00
    24. - one permission at a time0.99
    25. – no time to learn boundaries0.99
    26. - one reason to trust it0.98
    27. Snorkel0.97
    28. AlEngineer0.96
    29. EUROPE1.00
    30. AlEngineer0.99
    31. # Braintrust0.97
    32. WorkOS1.00
    33. OpenAl0.96
    34. EUROPE1.00

  • 2:40 #14 done31 line(s)

    shot 14·sharpness 2058.7

    1. AIEngineer0.97
    2. EUROPE1.00
    3. THE TURN0.94
    4. This would be reckless0.97
    5. SAFI0.87
    6. AlEngineer0.99
    7. INTELLIGEI0.91
    8. EUROPE1.00
    9. if you did it all at once1.00
    10. The system only became trustworthy because it grew in small, useful0.99
    11. AIEngineel0.91
    12. DeepM0.97
    13. steps.1.00
    14. EUROPE1.00
    15. One giant leap1.00
    16. One permission at a time0.99
    17. ight dat0.99
    18. AlEngineer0.99
    19. - full access immediately0.96
    20. - one workflow at a time0.98
    21. EUROPE1.00
    22. – no track record of good behavior1.00
    23. - one permission at a time0.99
    24. – no time to learn boundaries0.99
    25. - one reason to trust it0.95
    26. AlEngineer0.96
    27. 2NCORD0.98
    28. EUROPE1.00
    29. Google DeepMind1.00
    30. AlEngineer0.99
    31. EUROPE1.00

  • 2:51 #15 skipped

    shot 15·duplicate of #14

  • 3:08 #16 done36 line(s)

    shot 16·sharpness 2133.7

    1. Oper0.99
    2. AlEngineer0.97
    3. EUROPE1.00
    4. ORIGIN STORY1.00
    5. From tiny setup to serious system0.98
    6. AIEngi0.90
    7. SAFE1.00
    8. INTELLIGENC1.00
    9. e1 I did not architect a giant life OS on day one.0.98
    10. AlEngineer0.97
    11. o2 I started from a fresh, simple setup and solved one useful problem.0.97
    12. EUROPE0.93
    13. e3 Then another. Then another. Memory, tools, schedules, and permissions0.99
    14. accumulated.1.00
    15. AlEngir0.95
    16. bright dat0.98
    17. EUROPE1.00
    18. 04 Eventually I looked up and realized I had something bigger than an0.99
    19. assistant. I had infrastructure.1.00
    20. Snor0.99
    21. AlEngineer0.99
    22. START1.00
    23. USEFUL1.00
    24. TRUSTED1.00
    25. NOW1.00
    26. EUROPE1.00
    27. fresh setup0.99
    28. one recurring pain solved1.00
    29. more context, more1.00
    30. quiet infrastructure0.99
    31. permissions1.00
    32. AlEngineer0.98
    33. Braintrust1.00
    34. WorkOS1.00
    35. OpenAl0.94
    36. EUROPE1.00

  • 3:19 #17 done29 line(s)

    shot 17·sharpness 1956.3

    1. OPE0.96
    2. ORIGIN STORY1.00
    3. From tiny setup to serious system0.99
    4. eepM0.87
    5. Engineer1.00
    6. 01 I did not architect a giant life OS on day one.0.99
    7. EUROPE0.99
    8. o2 I started from a fresh, simple setup and solved one useful problem.0.98
    9. e3 Then another. Then another. Memory, tools, schedules, and permissions0.98
    10. accumulated.1.00
    11. neer1.00
    12. 04 Eventually I looked up and realized I had something bigger than an0.99
    13. assistant.I had infrastructure.0.98
    14. AlEngineer0.97
    15. fresh setup1.00
    16. START1.00
    17. USEFUL1.00
    18. one recurring pain solved1.00
    19. more context, more1.00
    20. TRUSTED1.00
    21. NOW1.00
    22. quiet infrastructure0.99
    23. EUROPE1.00
    24. permissions1.00
    25. PRESENTED BY1.00
    26. Google DeepMind1.00
    27. Engineering the future of Al0.99
    28. AlEngineer0.99
    29. EUROPE1.00

  • 3:34 #18 done29 line(s)

    shot 18·sharpness 2164.8

    1. AlEngi0.94
    2. EUROI0.99
    3. ORIGIN STORY1.00
    4. From tiny setup to serious system0.99
    5. AI0.82
    6. e1 I did not architect a giant life OS on day one.0.98
    7. o2 I started from a fresh, simple setup and solved one useful problem.0.98
    8. e3 Then another. Then another. Memory, tools, schedules, and permissions0.97
    9. accumulated.1.00
    10. AlEngi0.97
    11. 04 Eventually I looked up and realized I had something bigger than an0.98
    12. EUROI0.98
    13. assistant.I had infrastructure.1.00
    14. AlEngineer1.00
    15. fresh setup1.00
    16. START1.00
    17. USEFUL1.00
    18. one recurring pain solved1.00
    19. more context, more1.00
    20. TRUSTED1.00
    21. NOW1.00
    22. quiet infrastructure0.99
    23. EUROPE1.00
    24. permissions0.98
    25. PRESENTED BY1.00
    26. Google DeepMind0.98
    27. Google DeepMind1.00
    28. AlEngineer0.97
    29. EUROPE1.00

  • 3:49 #19 done30 line(s)

    shot 19·sharpness 2255.1

    1. Zed0.98
    2. AlEngineer0.94
    3. IIEle0.92
    4. AlEngineer0.96
    5. WorkOs0.92
    6. ORIGIN STORY1.00
    7. From tiny setup to serious system1.00
    8. 8日0.65
    9. 01 I did not architect a giant life OS on day one.0.99
    10. AIE0.95
    11. o2 I started from a fresh, simple setup and solved one useful problem.0.98
    12. neo4j0.90
    13. ATri0.90
    14. e3 Then another. Then another. Memory, tools, schedules, and permissions0.98
    15. accumulated.1.00
    16. AlEngineer0.99
    17. 04 Eventually I looked up and realized I had something bigger than an0.99
    18. assistant.I had infrastructure.0.99
    19. START1.00
    20. USEFUL1.00
    21. TRUSTED1.00
    22. NOW1.00
    23. fresh setup1.00
    24. one recurring pain solved1.00
    25. more context, more1.00
    26. quiet infrastructure1.00
    27. permissions1.00
    28. Google DeepMind1.00
    29. AlEngineer0.98
    30. EUROPE1.00

  • 4:40 #20 done33 line(s)

    shot 20·sharpness 2174.0

    1. EUROPE1.00
    2. ORIGIN STORY1.00
    3. From tiny setup to serious system1.00
    4. Engineer1.00
    5. DeepMi1.00
    6. EUROPE1.00
    7. 01 I did not architect a giant life OS on day one.0.98
    8. Microsc0.92
    9. jineer0.98
    10. o2 I started from a fresh, simple setup and solved one useful problem.0.99
    11. ROPE0.93
    12. e3 Then another. Then another. Memory, tools, schedules, and permissions0.98
    13. accumulated.1.00
    14. Engineer1.00
    15. VorkOS0.98
    16. EUROPE1.00
    17. 04 Eventually I looked up and realized I had something bigger than an0.98
    18. assistant.I had infrastructure.1.00
    19. tailscal1.00
    20. Engineer1.00
    21. START1.00
    22. USEFUL1.00
    23. TRUSTED1.00
    24. NOW1.00
    25. EUROPE1.00
    26. fresh setup0.96
    27. one recurring pain solved1.00
    28. more context, more1.00
    29. quiet infrastructure0.99
    30. permissions1.00
    31. Google DeepMind1.00
    32. AlEngineer0.98
    33. EUROPE1.00

  • 4:47 #21 done27 line(s)

    shot 21·sharpness 2091.7

    1. OPE1.00
    2. ORIGIN STORY1.00
    3. From tiny setup to serious system0.99
    4. DeepMinc0.85
    5. 01 I did not architect a giant life OS on day one.0.99
    6. o2 I started from a fresh, simple setup and solved one useful problem.0.98
    7. e3 Then another. Then another. Memory, tools, schedules, and permissions0.98
    8. accumulated.1.00
    9. D4i0.79
    10. 04 Eventually I looked up and realized I had something bigger than an0.98
    11. assistant.I had infrastructure.0.99
    12. AlEngineer0.98
    13. fresh setup1.00
    14. START1.00
    15. USEFUL1.00
    16. one recurring pain solved1.00
    17. more context, more1.00
    18. TRUSTED1.00
    19. NOW1.00
    20. quiet infrastructure0.99
    21. permissions0.96
    22. EUROPE1.00
    23. PRESENTED BY1.00
    24. Google DeepMin0.99
    25. Google DeepMind1.00
    26. AlEngineer0.97
    27. EUROPE1.00

  • 4:55 #22 done37 line(s)

    shot 22·sharpness 2208.9

    1. EUROPE1.00
    2. KNOWLEDGE BASE1.00
    3. The knowledge base is1.00
    4. what makes this useful1.00
    5. Google D0.97
    6. AIE0.99
    7. 2,9841.00
    8. VAULT SNAPSHOT1.00
    9. It can start in the0.96
    10. WHAT CHANGES0.99
    11. middle.1.00
    12. Years of notes, drafts, meetings,0.99
    13. AlEngin0.91
    14. and half-finished thoughts are al0.99
    15. there when I ask for help.0.97
    16. EUROPE0.97
    17. markdown notes in this vault today,1.00
    18. spanning journals, plans, calls, articles,0.99
    19. research, and personal context1.00
    20. WHY IT COMPOUNDS0.99
    21. AIEI0.90
    22. daily journals1.00
    23. project plans1.00
    24. call notes1.00
    25. searchable1.00
    26. article drafts0.97
    27. clippings1.00
    28. linked1.00
    29. PRES1.00
    30. already part of the work itself1.00
    31. Google1.00
    32. getting richer every week1.00
    33. AlEngineer0.99
    34. # Braintrust0.96
    35. WorkOS1.00
    36. OpenAl0.94
    37. EUROPE1.00

  • 5:09 #23 done29 line(s)

    shot 23·sharpness 2056.6

    1. KNOWLEDGE BASE1.00
    2. The knowledge base is1.00
    3. what makes this useful1.00
    4. 2,9841.00
    5. VAULT SNAPSHOT1.00
    6. It can start in the0.97
    7. WHAT CHANGES0.99
    8. middle.0.96
    9. Years of notes, drafts, meetings,1.00
    10. and half-finished thoughts are al0.99
    11. markdown notes in this vault today,1.00
    12. there when I ask for help.0.96
    13. spanning journals, plans, calls, articles,0.99
    14. research, and personal context1.00
    15. WHY IT COMPOUNDS0.99
    16. daily journals1.00
    17. project plans1.00
    18. call notes1.00
    19. searchable1.00
    20. article drafts1.00
    21. clippings1.00
    22. linked1.00
    23. already part of the work itself1.00
    24. getting richer every week1.00
    25. AlEngineer0.99
    26. Braintrust1.00
    27. WorkOS1.00
    28. OpenAl0.94
    29. EUROPE1.00

Transcript

174 cues· 2,502 words· 13,082 chars

  1. 0:15 Ready to go?
  2. 0:16 All good, yeah.
  3. 0:16 Please welcome Radek, everybody.
  4. 0:18 Cool.
  5. 0:20 Hey, I'm Radek.
  6. 0:22 I'm one of the OpenClaw maintainers.
  7. 0:26 And I want to talk what happens in my life with OpenClaw when I practically gave the keys to my life to OpenClaw.
  8. 0:40 And it's almost literally.
  9. 0:43 And what that actually means.
  10. 0:46 So this happens step by step.
  11. 0:48 It wasn't all at the same time.
  12. 0:50 But it can access my emails.
  13. 0:52 It can access my notes, files, calendars, tools, my operating system, so automations.
  14. 1:01 And it builds on top of memory of everything that I do at the computer.
  15. 1:09 So it can do anything with it that is possible to do with a computer.
  16. 1:17 But it didn't all happen in one big leap.
  17. 1:23 So I install OpenClaw, and now it just controls my life and does everything for me.
  18. 1:32 That would be silly to do, or even silly to expect that this could even work.
  19. 1:39 So what happened is that I tried installing just like everybody does, just like with one channel.
  20. 1:50 I think at the beginning it was just WhatsApp.
  21. 1:54 Then I migrated to Telegram.
  22. 1:57 Now I'm on Discord.
  23. 1:58 But it was just WhatsApp, just one ability to do to just like chat.
  24. 2:04 Okay, so we are there.
  25. 2:06 What's next that we can do?
  26. 2:09 Let's do some like one simple workflow or one very simple task that you can do.
  27. 2:14 Once we are there, let's go to the next step.
  28. 2:16 So this is how it happened where I am today, where I used to think that
  29. 2:25 I have quite a simple setup with my Open Claw and what it does, because I never did any big change, but when I
  30. 2:35 encounter different, I don't know, Twitter threads, YouTube videos, or talking to other people how they have it set up.
  31. 2:45 I see that like my setup has everything that they have, more on top of that, and most also is just like more sophisticated than what I see out there.
  32. 2:57 which was really surprising to me because I felt that it's just like one small step at a time.
  33. 3:02 I have a pretty simple setup, works for me, but
  34. 3:08 That's what I want to show how that happened and how it looks like today.
  35. 3:14 So you already had a lot of talks about how the sausage is made, how we are making it better.
  36. 3:22 You'll have more talks about the insides of the OpenClaw.
  37. 3:28 I want to show how it looks from the other side, from the first, the simple user, then the power user.
  38. 3:36 Now I'm also a maintainer.
  39. 3:39 you don't have to go to the maintainer route, but when I was playing with one of the workflows, I just encountered some errors and just submitted first PR, then the second PR, then just looked into Discord, and then just got involved, now I'm a maintainer there.
  40. 3:58 So it also was just one step at a time.
  41. 4:05 So these are the steps that it usually happens that I see the need, I solve it in a very simple way, and then I add more steps to it.
  42. 4:17 And this is also why I usually don't have
  43. 4:21 big issues that people have that okay now it broke my computer or it just like completely bricked during the update because I have all these small steps that I take if something breaks and just like step take one small step back fix it see what doesn't work understand it why it didn't work have a setup that it never happens again and just like take one step further again so
  44. 4:50 Where it started being more and more helpful and kind of like running my life is when I gave it my knowledge base.
  45. 5:00 So I had a lot of stuff in my Obsidian, which I built up for years.
  46. 5:09 So right now I have like about 3,000 pages or notes, markdown files in my Obsidian.
  47. 5:18 And this is everything.
  48. 5:19 This is work stuff, personal stuff, tasks, projects, research.
  49. 5:30 What else?
  50. 5:30 Articles.

Chapters

  1. 0:00 <Untitled Chapter 1>
  2. 0:15 Radek's path to OpenClaw
  3. 2:17 The philosophy of incremental growth and system updates
  4. 4:51 Integrating the Obsidian knowledge base
  5. 8:59 Ambient operations and overnight automation
  6. 11:02 Core job types for the AI agent (Ambient Operations, Attention Filtering, Execution)
  7. 13:03 Deep dive into specific Discord integration channels
  8. 14:54 System architecture: LLMs, scripts, and memory management
  9. 16:28 Challenges: Bad memory, brittle automations, and noisy nodes
  10. 17:19 Conclusion: Optimizing for the future self

Open at this second