vidtheque.

read-only demo

Videos spNAUEgq_A8

The Future Is Domain-Specific Agents - Justin Schroeder, StandardAgents

index_state ready data_status ok

AI Engineer· published 2026-06-29· 0:30:38· en-US· indexed 2026-08-10 19:50

Open on YouTube

Scene timeline

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

68 shot(s).

keyframes kept every frame deduplicated

What was stored

cues
368
whisperx 368
chunks
55
from 368 cues
keyframes
53
kept of 68 captured
frames with text
48
743 lines read
chapters
0
from the source metadata
keyframe bytes
6.0 MB
word timings on 368 cues

Provenance

Each pipeline stage, its state and the model that produced it
stage state model started took
fetch done — 2026-08-10 13:47 1m 57s
stt done — 2026-08-10 13:49 33s
chunk done — 2026-08-10 13:50 0s
text_embed done — 2026-08-10 19:50 1s
keyframe done — 2026-08-10 13:50 2m 47s
ocr done — 2026-08-10 13:52 14s
frame_embed done — 2026-08-10 19:50 9s

Frames, and what the machine read

  • 0:14 #0 done3 line(s)

    shot 0·sharpness 414.7

    1. The Future Is1.00
    2. Domain-Specific Agents1.00
    3. X@jpschroeder0.97

  • 0:43 #1 done14 line(s)

    shot 1·sharpness 1967.9

    1. StandardAgents1.00
    2. Justin Schroeder1.00
    3. X @jpschroeder0.95
    4. dmux1.00
    5. arrowJs0.95
    6. {...}0.99
    7. jsonreader1.00
    8. ZODOWN0.96
    9. FormKit1.00
    10. _AutoAnimate0.99
    11. DRAG0.99
    12. TEMPO0.98
    13. DROP0.93
    14. X@jpschroeder1.00

  • 0:59 #2 empty

    shot 2·sharpness 72.0

  • 1:47 #3 done1 line(s)

    shot 3·sharpness 598.8

    1. We'll harness intelligence with agents.1.00

  • 2:18 #4 done2 line(s)

    shot 4·sharpness 632.8

    1. What is an agent?1.00
    2. X@jpschroeder0.99

  • 2:52 #5 done5 line(s)

    shot 5·sharpness 2216.2

    1. Harnesses1.00
    2. Agents are deterministic software that harnesses the0.99
    3. non-deterministic results produced by models in1.00
    4. pursuit of a desired objective.0.99
    5. X@jpschroeder1.00

  • 3:21 #6 done3 line(s)

    shot 6·sharpness 1128.5

    1. Claude1.00
    2. N0.99
    3. X@jpschroeder0.99

  • 4:02 #7 done2 line(s)

    shot 7·sharpness 1035.4

    1. But everyone is1.00
    2. building agent1.00

  • 4:56 #8 done2 line(s)

    shot 8·sharpness 490.4

    1. Integration1.00
    2. X@jpschroeder0.99

  • 5:29 #9 done3 line(s)

    shot 9·sharpness 876.2

    1. Agents are hard1.00
    2. Agentic loop orchestration1.00
    3. Provider abstraction1.00

  • 6:01 #10 done31 line(s)

    shot 10·sharpness 6499.0

    1. Agents are hard1.00
    2. • Agentic loop orchestration1.00
    3. • Real-time log streaming1.00
    4. Sub-prompt chaining1.00
    5. Provider abstraction0.98
    6. • Memory-efficient image processing0.99
    7. Graceful execution abort1.00
    8. Durable execution1.00
    9. • Large file chunking0.99
    10. Serial tool execution0.99
    11. • Tool call validation0.99
    12. • Automatic image optimization1.00
    13. Retry with backoff1.00
    14. • Stop conditions0.95
    15. • Zero-config discovery0.99
    16. • Unified response format0.99
    17. Multi-agent turn coordination1.00
    18. • Message lifecycle hooks0.99
    19. • HTTP streaming for long execution0.98
    20. • Persistent thread state0.99
    21. • Tool lifecycle hooks0.99
    22. • WebSocket0.99
    23. Message hierarchy (sub-prompts)1.00
    24. Framework-agnostic client1.00
    25. Execution1.00
    26. Context window management1.00
    27. • Workblock transformation0.98
    28. • Namespa0.99
    29. Parallel tool execution0.99
    30. • Agent packaging & distribution0.99
    31. • Hallucinate0.94

  • 6:20 #11 done3 line(s)

    shot 11·sharpness 1262.8

    1. It's a mess out there1.00
    2. • Building robust agents is hard.0.99
    3. • There is no defined way to do it.1.00

  • 6:52 #12 skipped

    shot 12·duplicate of #11

  • 7:27 #13 done6 line(s)

    shot 13·sharpness 2346.2

    1. It's a mess out there0.99
    2. • Building robust agents is hard.1.00
    3. • There is no defined way to do it.1.00
    4. • Telemetry/observability is hard.1.00
    5. • Agents are not portable.1.00
    6. • Agents are not composable.1.00

  • 7:38 #14 done1 line(s)

    shot 14·sharpness 224.7

    1. Agents1.00

  • 8:07 #15 done5 line(s)

    shot 15·sharpness 1217.4

    1. Agents1.00
    2. Model Context Protocol0.99
    3. 2Zillow0.94
    4. American1.00
    5. Airlines1.00

  • 8:20 #16 done119 line(s)

    shot 16·sharpness 2128.8

    1. Client1.00
    2. Resources0.99
    3. Prompts1.00
    4. Tools1.00
    5. Discovery1.00
    6. Sampling1.00
    7. Roots1.00
    8. Elicitation1.00
    9. Instructions1.00
    10. 5ire0.94
    11. ×0.85
    12. ×0.62
    13. ?0.89
    14. ×0.74
    15. ×0.58
    16. ?0.78
    17. ?0.82
    18. AgentAl0.99
    19. ×0.86
    20. ×0.71
    21. 00.51
    22. ?0.70
    23. ×0.72
    24. ×0.86
    25. ?0.84
    26. ?0.72
    27. AgenticFlow1.00
    28. 00.50
    29. 00.76
    30. ×0.66
    31. ×0.64
    32. ?0.79
    33. ?0.93
    34. AIQL TUUI1.00
    35. 00.50
    36. ×0.65
    37. 00.54
    38. ?0.86
    39. Amazon Q CLI1.00
    40. ×0.79
    41. ?0.89
    42. ×0.59
    43. ×0.78
    44. ?0.87
    45. ?0.90
    46. Amazon Q IDE1.00
    47. ×0.69
    48. ×0.66
    49. 00.69
    50. ×0.75
    51. ×0.64
    52. ?0.90
    53. ?0.88
    54. Amp1.00
    55. 00.57
    56. 00.57
    57. ×0.72
    58. 00.60
    59. ×0.58
    60. ?0.80
    61. ?0.89
    62. Apify MCP1.00
    63. x0.50
    64. V0.56
    65. ×0.50
    66. ×0.52
    67. ?0.89
    68. ?0.86
    69. Tester1.00
    70. Augment Code1.00
    71. ×0.71
    72. ×0.81
    73. ×0.85
    74. ×0.83
    75. ×0.78
    76. ?0.83
    77. ?0.83
    78. Avatar Shell0.98
    79. ×0.77
    80. 00.58
    81. ×0.81
    82. ×0.73
    83. ×0.75
    84. ?0.59
    85. ?0.93
    86. BeeAl0.96
    87. ×0.64
    88. ×0.68
    89. ×0.81
    90. ×0.71
    91. ×0.62
    92. Framework1.00
    93. BoltAl0.99
    94. ×0.59
    95. ×0.76
    96. ?0.79
    97. ×0.65
    98. ×0.73
    99. Call Chirp0.97
    100. ×0.66
    101. x0.56
    102. x0.51
    103. Chatbox1.00
    104. ×0.92
    105. ×0.83
    106. 00.59
    107. ×0.82
    108. ×0.71
    109. ×0.60
    110. ChatFrame0.95
    111. ×0.88
    112. ×0.90
    113. ×0.84
    114. ×0.85
    115. ×0.73
    116. ChatGPT1.00
    117. X0.51
    118. X0.55
    119. ?0.93

  • 8:27 #17 done101 line(s)

    shot 17·sharpness 1967.2

    1. Client1.00
    2. Resources1.00
    3. Prompts1.00
    4. Tools1.00
    5. Discovery1.00
    6. Sampling0.96
    7. Roots1.00
    8. Elicitation1.00
    9. Instructions1.00
    10. HyperAgent1.00
    11. ×0.68
    12. ×0.65
    13. ?0.83
    14. ×0.58
    15. ×0.69
    16. ?0.94
    17. ?0.91
    18. Jenova1.00
    19. ×0.56
    20. ×0.75
    21. ×0.65
    22. ×0.69
    23. ?0.90
    24. ?0.89
    25. JetBrains Al1.00
    26. ×0.74
    27. ×0.67
    28. ×0.53
    29. ×0.73
    30. ?0.89
    31. ?0.94
    32. Assistant1.00
    33. JetBrains Junie1.00
    34. ×0.58
    35. ×0.60
    36. ×0.57
    37. ×0.61
    38. ×0.68
    39. ×0.60
    40. ?0.89
    41. Kilo Code1.00
    42. ×0.53
    43. ?0.89
    44. ?0.92
    45. Klavis Al0.97
    46. ×0.55
    47. ?0.90
    48. ×0.62
    49. ×0.75
    50. ?0.95
    51. Slack/Discord/1.00
    52. Web1.00
    53. Langflow1.00
    54. ×0.72
    55. 00.50
    56. ?0.92
    57. ×0.72
    58. ×0.75
    59. ?0.89
    60. ?0.94
    61. LibreChat1.00
    62. x0.65
    63. ×0.70
    64. ?0.92
    65. ×0.82
    66. ×0.78
    67. ?0.90
    68. LM-Kit.NET1.00
    69. ×0.66
    70. ×0.70
    71. ×0.72
    72. ×0.78
    73. ×0.73
    74. ×0.61
    75. ?0.92
    76. LM Studio0.96
    77. ×0.67
    78. ?0.89
    79. ×0.77
    80. ×0.77
    81. Lutra1.00
    82. 00.69
    83. V0.54
    84. ?0.89
    85. MCP Bundler1.00
    86. 00.53
    87. ×0.53
    88. ×0.57
    89. ×0.51
    90. for MacOS1.00
    91. mcp-agent1.00
    92. ?0.88
    93. A0.87
    94. mcp-client-1.00
    95. ×0.58
    96. ×0.55
    97. V0.60
    98. ×0.71
    99. ×0.54
    100. ×0.58
    101. chatbot1.00

  • 8:31 #18 done107 line(s)

    shot 18·sharpness 1872.5

    1. Client0.99
    2. Resources1.00
    3. Prompts1.00
    4. Tools1.00
    5. Discovery1.00
    6. Sampling1.00
    7. Roots1.00
    8. Elicitation1.00
    9. Instructions1.00
    10. Smithery1.00
    11. 00.62
    12. V0.87
    13. ×0.71
    14. ?0.92
    15. ?0.87
    16. Playground1.00
    17. SpinAl0.96
    18. ×0.64
    19. ×0.54
    20. V0.79
    21. 20.50
    22. ×0.58
    23. x0.65
    24. ?0.93
    25. ?0.93
    26. Superinterface1.00
    27. ×0.61
    28. ×0.78
    29. 70.51
    30. 20.58
    31. ×0.63
    32. 20.70
    33. ?0.87
    34. Superjoin1.00
    35. ×0.61
    36. ?0.65
    37. ×0.66
    38. ×0.63
    39. ?0.91
    40. ?0.89
    41. Swarms1.00
    42. ×0.59
    43. ×0.70
    44. V0.77
    45. ×0.74
    46. ×0.56
    47. ?0.91
    48. ?0.92
    49. systemprompt1.00
    50. V0.67
    51. ?0.92
    52. ×0.56
    53. ?0.91
    54. ?0.88
    55. Tambo1.00
    56. ×0.62
    57. V0.60
    58. ×0.64
    59. ?0.76
    60. Tencent1.00
    61. ×0.66
    62. ×0.57
    63. V0.64
    64. ?0.95
    65. ×0.74
    66. ×0.58
    67. ?0.95
    68. ?0.94
    69. CloudBase Al1.00
    70. DevKit1.00
    71. TheiaAl/TheialD1.00
    72. ×0.63
    73. ×0.50
    74. V0.85
    75. ?0.97
    76. ×0.77
    77. ?0.97
    78. ?0.98
    79. E0.97
    80. Tome1.00
    81. ×0.62
    82. ×0.64
    83. V0.86
    84. ?0.66
    85. ×0.69
    86. ×0.61
    87. TypingMind1.00
    88. ×0.55
    89. ×0.54
    90. V0.93
    91. 20.60
    92. ×0.76
    93. x0.72
    94. App1.00
    95. VS Code GitHub0.99
    96. V0.57
    97. V0.55
    98. V0.60
    99. V0.75
    100. V0.60
    101. Copilot1.00
    102. VT Code1.00
    103. V0.85
    104. V0.77
    105. A0.99
    106. V0.77
    107. ?0.90

  • 8:57 #19 done1 line(s)

    shot 19·sharpness 602.1

    1. Tools are not enough.1.00

  • 9:08 #20 empty

    shot 20·sharpness 3441.0

  • 9:12 #21 done2 line(s)

    shot 21·sharpness 193.5

    1. MCP0.98
    2. 00.85

  • 9:34 #22 done17 line(s)

    shot 22·sharpness 1268.5

    1. MCP0.94
    2. IVT0.85
    3. Agent Skills0.99
    4. my-skill/skill root0.99
    5. SKILL.mdrequired Frontmatter + instructions0.99
    6. scripts/optional Executable code for agents0.98
    7. extract.py1.00
    8. process.sh1.00
    9. transform.js1.00
    10. references/ optional Docs loaded on demand0.97
    11. REFERENCE.md1.00
    12. FORMS.md0.99
    13. domain-guide.md1.00
    14. assets/optional Static resou0.98
    15. template.json1.00
    16. diagram.png1.00
    17. schema.yaml1.00

  • 9:49 #23 empty

    shot 23·sharpness 3620.0

Transcript

368 cues· 4,986 words· 26,713 chars

  1. 0:03 Okay, so I'm gonna be talking about domain-specific agents and why I really think that they are going to play an unbelievably important role in the future of AI and in the future of how we build agents.
  2. 0:16 To get started real quick, my name is Justin Schrader.
  3. 0:19 You can find me on xatjpschrader.
  4. 0:23 And I work at a small company called Standard Agents, which nobody's heard of right now because we're still kind of in stealth mode.
  5. 0:30 After this talk, if you're interested, feel free to reach out to me and I can let you know a little bit more.
  6. 0:37 Mostly, I'm known for doing a lot of different open source projects.
  7. 0:41 DMUX, which is a great multiplexer for all of your coding agents.
  8. 0:45 Arrow.js, which is sort of like a UI framework, sort of like React for
  9. 0:50 The agentic era a bunch more that I won't get into but you know, maybe check them out if you're interested
  10. 0:56 Okay.
  11. 0:57 I think we can all agree that the moment in time that we are in is very similar to the industrial revolution.
  12. 1:04 In fact, it might be like an accelerated industrial revolution.
  13. 1:07 Maybe it's a bigger deal, but it's certainly not smaller.
  14. 1:10 I probably don't need to convince you of that if you're listening to one of these talks.
  15. 1:14 But that is the moment we find ourselves in.
  16. 1:17 So I actually think it's helpful to go back and sort of look at what was the key catalyst
  17. 1:23 of the Industrial Revolution.
  18. 1:24 And ultimately it was that we learned how to harness energy with machines.
  19. 1:30 We learned how to harness energy with machines.
  20. 1:32 And what's interesting is that in this next era, we are essentially learning to harness intelligence with agents.
  21. 1:41 And agents, I think, can be thought of a little bit like the machine of yesteryear.
  22. 1:46 It's the thing that is going to use the intelligence.
  23. 1:50 Not so much us, but the agents.
  24. 1:55 What's interesting about that is I bet if I was in an actual room with you guys and we all put up our hands, I bet a lot of you, when I say what is an agent, instantly have examples that pop into mind, but also probably can't pull out a definition immediately.
  25. 2:10 Some of you maybe can, but the reality is that we haven't even coalesced on a definition of what an agent is, even though we're well into the agentic era at this point.
  26. 2:23 And I think that's kind of interesting.
  27. 2:25 Here's my definition.
  28. 2:26 You can feel free to agree with it or not, but agents are deterministic software that harness the non-deterministic results produced by models in pursuit of some desired objective.
  29. 2:41 Deterministic software might make you think more like a harness.
  30. 2:46 And I actually think the distinction between an agent and a harness is really pedantic, not very helpful.
  31. 2:52 And for the most part, in most cases, you can just conflate the two.
  32. 2:56 A harness is an agent and an agent is a harness, okay?
  33. 2:59 And for the purposes of this talk, we're gonna go ahead and just move forward with that.
  34. 3:03 I think you could probably make some good arguments for why one is the other and vice versa, but really not important right now.
  35. 3:11 Now, if you did have some examples pop to mind, they might have been like Claude or Codex, you know, OpenClaw, Hermes.
  36. 3:20 But you know what's interesting is I bet if you went out onto, you know, the streets of corporate America in any city, maybe not San Francisco, but any city in America, and you asked somebody just in an office building, could you name an agent by name?
  37. 3:39 I think some people are going to get Claude.
  38. 3:43 Some people might get Codex.
  39. 3:45 And that's about it.
  40. 3:46 I don't think hardly anybody's going to be getting OpenClaw or Hermes.
  41. 3:51 And really, even Claude, I don't know that people would even know that that's an agent.
  42. 3:55 These things are not well understood.
  43. 3:58 And yet what's so crazy is everybody is building agents.
  44. 4:03 I have a real estate agency down the street that's building agents.
  45. 4:07 I know like independent private insurance brokers building their own agents.
  46. 4:13 I know Fortune 500 companies, lots of them building their own custom agents.
  47. 4:17 Everybody is trying to build their own custom agents.
  48. 4:22 And I know people don't believe me,
  49. 4:24 But go talk to them.
  50. 4:25 Just go talk to people.

Open at this second