vidtheque.

read-only demo

Videos YZQsWVeN3rE

Design Patterns for AI Trust: Juries, Libraries, and Agent Tiers — Alex Bauer, Upside.tech

index_state ready data_status ok

AI Engineer· published 2026-07-11· 0:17:08· en-US· indexed 2026-08-10 22:47

Open on YouTube

Scene timeline

  1. Shot 0, 0:00 to 0:03, 1 of 1 keyframes kept
  2. Shot 1, 0:03 to 0:05, 1 of 1 keyframes kept
  3. Shot 2, 0:05 to 0:12, 1 of 1 keyframes kept
  4. Shot 3, 0:12 to 0:26, 1 of 1 keyframes kept
  5. Shot 4, 0:26 to 0:33, 1 of 1 keyframes kept
  6. Shot 5, 0:33 to 1:04, 1 of 1 keyframes kept
  7. Shot 6, 1:04 to 1:06, 1 of 1 keyframes kept
  8. Shot 7, 1:06 to 1:28, 1 of 1 keyframes kept
  9. Shot 8, 1:28 to 1:38, 1 of 1 keyframes kept
  10. Shot 9, 1:38 to 1:47, 1 of 1 keyframes kept
  11. Shot 10, 1:47 to 2:03, 1 of 1 keyframes kept
  12. Shot 11, 2:03 to 2:29, 1 of 1 keyframes kept
  13. Shot 12, 2:29 to 2:43, 1 of 1 keyframes kept
  14. Shot 13, 2:43 to 3:22, 1 of 1 keyframes kept
  15. Shot 14, 3:22 to 3:37, 1 of 1 keyframes kept
  16. Shot 15, 3:37 to 3:50, 1 of 1 keyframes kept
  17. Shot 16, 3:50 to 4:08, 1 of 1 keyframes kept
  18. Shot 17, 4:08 to 4:33, 1 of 1 keyframes kept
  19. Shot 18, 4:33 to 4:38, 1 of 1 keyframes kept
  20. Shot 19, 4:38 to 4:48, 0 of 1 keyframes kept
  21. Shot 20, 4:48 to 5:05, 0 of 1 keyframes kept
  22. Shot 21, 5:05 to 5:15, 1 of 1 keyframes kept
  23. Shot 22, 5:15 to 5:49, 0 of 1 keyframes kept
  24. Shot 23, 5:49 to 6:10, 1 of 1 keyframes kept
  25. Shot 24, 6:10 to 6:59, 1 of 1 keyframes kept
  26. Shot 25, 6:59 to 7:26, 0 of 1 keyframes kept
  27. Shot 26, 7:26 to 7:56, 1 of 1 keyframes kept
  28. Shot 27, 7:56 to 8:27, 0 of 1 keyframes kept
  29. Shot 28, 8:27 to 8:48, 0 of 1 keyframes kept
  30. Shot 29, 8:48 to 9:30, 1 of 1 keyframes kept
  31. Shot 30, 9:30 to 10:06, 0 of 1 keyframes kept
  32. Shot 31, 10:06 to 10:42, 0 of 1 keyframes kept
  33. Shot 32, 10:42 to 10:50, 1 of 1 keyframes kept
  34. Shot 33, 10:50 to 11:15, 0 of 1 keyframes kept
  35. Shot 34, 11:15 to 11:31, 0 of 1 keyframes kept
  36. Shot 35, 11:31 to 11:32, 0 of 1 keyframes kept
  37. Shot 36, 11:32 to 11:59, 1 of 1 keyframes kept
  38. Shot 37, 11:59 to 12:24, 0 of 1 keyframes kept
  39. Shot 38, 12:24 to 12:49, 1 of 1 keyframes kept
  40. Shot 39, 12:49 to 13:14, 0 of 1 keyframes kept
  41. Shot 40, 13:14 to 13:39, 0 of 1 keyframes kept
  42. Shot 41, 13:39 to 14:05, 1 of 1 keyframes kept
  43. Shot 42, 14:05 to 14:31, 1 of 1 keyframes kept
  44. Shot 43, 14:31 to 14:57, 1 of 1 keyframes kept
  45. Shot 44, 14:57 to 15:24, 0 of 1 keyframes kept
  46. Shot 45, 15:24 to 15:28, 0 of 1 keyframes kept
  47. Shot 46, 15:28 to 16:16, 1 of 1 keyframes kept
  48. Shot 47, 16:16 to 16:35, 1 of 1 keyframes kept
  49. Shot 48, 16:35 to 16:40, 1 of 1 keyframes kept
  50. Shot 49, 16:40 to 16:51, 1 of 1 keyframes kept
  51. Shot 50, 16:51 to 17:08, 0 of 1 keyframes kept

51 shot(s).

keyframes kept every frame deduplicated

What was stored

cues
178
whisperx 178
chunks
30
from 178 cues
keyframes
34
kept of 51 captured
frames with text
34
734 lines read
chapters
0
from the source metadata
keyframe bytes
5.6 MB
word timings on 178 cues

Provenance

Each pipeline stage, its state and the model that produced it
stage state model started took
fetch done — 2026-08-10 22:44 1m 08s
stt done — 2026-08-10 22:45 18s
chunk done — 2026-08-10 22:45 0s
text_embed done — 2026-08-10 22:45 0s
keyframe done — 2026-08-10 22:45 1m 47s
ocr done — 2026-08-10 22:47 13s
frame_embed done — 2026-08-10 22:47 6s

Frames, and what the machine read

  • 0:02 #0 done2 line(s)

    shot 0·sharpness 451.6

    1. AlEngineer0.96
    2. World's Fair0.97

  • 0:03 #1 done2 line(s)

    shot 1·sharpness 661.2

    1. AIEngineer0.95
    2. World's Fair0.99

  • 0:10 #2 done25 line(s)

    shot 2·sharpness 2729.6

    1. LAB & PLATINUM SPONSORS0.99
    2. Amazon AGI Lab0.99
    3. ANTHROP\C1.00
    4. Google DeepMind1.00
    5. MINIMAX0.93
    6. OpenAI0.93
    7. Akamai1.00
    8. arize1.00
    9. aws1.00
    10. Braintrust1.00
    11. bright data0.96
    12. B1.00
    13. Browserbase1.00
    14. docker1.00
    15. :neo4j0.91
    16. ORACLE1.00
    17. PayPal1.00
    18. qodo1.00
    19. reducto1.00
    20. Sonar1.00
    21. Makers of0.98
    22. togetherai1.00
    23. Unblocked1.00
    24. WorkOS1.00
    25. SonarQube1.00

  • 0:21 #3 done2 line(s)

    shot 3·sharpness 232.9

    1. AlEngineer0.99
    2. World's Fair0.98

  • 0:32 #4 done12 line(s)

    shot 4·sharpness 2644.1

    1. AlEngineer0.99
    2. World'sFair0.95
    3. How Juries and Librarians can0.99
    4. PRESENTED BY1.00
    5. solve GTM's AI trust problem1.00
    6. Microsoft1.00
    7. Al Engineer World's Fair, 20260.99
    8. Alex Bauer, Upside0.97
    9. JURY1.00
    10. LIBRARIAN1.00
    11. Engineering the future of Al0.98
    12. World's Fair0.97

  • 0:48 #5 done6 line(s)

    shot 5·sharpness 1493.2

    1. AlEngineer0.99
    2. World's Fair0.96
    3. PRESENTED BY1.00
    4. Microsoft1.00
    5. Engineering the future of Al1.00
    6. World's Fair0.98

  • 1:05 #6 done8 line(s)

    shot 6·sharpness 1271.2

    1. AlEngineer0.99
    2. World'sFair1.00
    3. PRESENTED BY1.00
    4. Microsoft1.00
    5. Once upon a time...1.00
    6. TRACK 6· JULY 2, 20260.95
    7. World'sFair1.00
    8. Al in GTM0.94

  • 1:23 #7 done32 line(s)

    shot 7·sharpness 5841.6

    1. AlEngineer0.99
    2. World'sFair1.00
    3. THE QUEST BEGINS1.00
    4. MESSY1.00
    5. Every GTM team begins the AI journey0.99
    6. GTM·DATA0.99
    7. with hope, ambition, and 417 conflicting0.99
    8. definitions of "customer."0.98
    9. PRESENTED BY1.00
    10. So we just point0.98
    11. That sentence has0.99
    12. Microsoft1.00
    13. an AI agent at0.99
    14. the data, right?0.99
    15. historically preceded1.00
    16. several incidents.1.00
    17. SALESFORCE1.00
    18. HUBSPOT1.00
    19. GONG1.00
    20. GTM TEAM1.00
    21. PRODUCT1.00
    22. LOGS1.00
    23. ???0.99
    24. SPREADSHEETS1.00
    25. MISC.CSV0.94
    26. PATH TO1.00
    27. AI-READY1.00
    28. REVENUE1.00
    29. INTELLIGENCE0.97
    30. TRACK 6· JULY 2, 20260.96
    31. World'sFair1.00
    32. Al in GTM0.92

  • 1:37 #8 done28 line(s)

    shot 8·sharpness 5753.1

    1. AlEngineer0.99
    2. World'sFair1.00
    3. BOSS #1: AI GOVERNANCE OGRE0.99
    4. Before the team could ask better questions,1.00
    5. they first had to survive asking0.99
    6. questions safely.1.00
    7. CUSTOMER1.00
    8. DATA1.00
    9. Who dares give an0.99
    10. PII1.00
    11. agent database access1.00
    12. without supervision?0.99
    13. AI1.00
    14. SECRETS1.00
    15. GOVERNANCE1.00
    16. We brought1.00
    17. COMMITTEE1.00
    18. weapons.1.00
    19. REVENUE1.00
    20. DATA1.00
    21. NOT1.00
    22. REVENUE1.00
    23. FOR1.00
    24. DATA.0.97
    25. AGENTS1.00
    26. TRACK 6· JULY 2, 20260.96
    27. World'sFair1.00
    28. Alin GTM0.99

  • 1:46 #9 done29 line(s)

    shot 9·sharpness 5603.7

    1. AlEngineer0.99
    2. World'sFair1.00
    3. DEFEATING THE AI GOVERNANCE OGRE0.99
    4. Boss #1 was defeated with boring-sounding tools,0.98
    5. Fine. Tools1.00
    6. which is usually how the important bosses fall.0.99
    7. over bravado.1.00
    8. You may pass.1.00
    9. SAFE-BY-DEFAULT1.00
    10. PERMISSIONING1.00
    11. GOVERNANCE1.00
    12. SHELL1.00
    13. ☑POLICIES0.96
    14. AUDIT LOGS1.00
    15. ACCESS REVIEWS0.99
    16. 区0.69
    17. SEPARATION OF1.00
    18. DUTIES0.97
    19. INSIDER TRADING1.00
    20. PREVENTION1.00
    21. The agent can only access what it's1.00
    22. supposed to access. And it has to0.99
    23. AND WE WATCH FOR0.97
    24. leave footprints.1.00
    25. BAD ACTOR RISK LIKE0.97
    26. INSIDER TRADING.1.00
    27. TRACK 6· JULY 2, 20260.96
    28. World's Fair0.99
    29. Al in GTM0.96

  • 2:00 #10 done34 line(s)

    shot 10·sharpness 4763.7

    1. AlEngineer0.99
    2. World'sFair1.00
    3. BOSS #2: DATA QUALITY HYDRA0.98
    4. The next boss was worse. It was messy, ambiguous, and everywhere.0.99
    5. WORKSPACE1.00
    6. BUYING1.00
    7. LEAD1.00
    8. COMMITTEE1.00
    9. Your pipeline is0.98
    10. CONTACT1.00
    11. ~DEAL0.92
    12. $12M, $19M, or0.95
    13. emotionally0.99
    14. ACCOUNT1.00
    15. USER1.00
    16. unresolved.1.00
    17. PIPELINE1.00
    18. OPPORTUNITY1.00
    19. THIS FIELD1.00
    20. MEANS THREE1.00
    21. A customer is1.00
    22. DATA QUALITY1.00
    23. THINGS1.00
    24. an account.0.97
    25. HYDRA1.00
    26. We may need1.00
    27. Acme1.00
    28. Acme Inc.1.00
    29. Acme?1.00
    30. more than a1.00
    31. prompt.1.00
    32. TRACK 6· JULY 2, 20260.96
    33. World'sFair1.00
    34. Alin GTM0.99

  • 2:19 #11 done30 line(s)

    shot 11·sharpness 5363.8

    1. AlEngineer0.99
    2. World'sFair1.00
    3. BEATING BOSS #2: THREE LEVELS OF WEAPONS0.98
    4. Data quality improved as soon as the team stopped0.99
    5. ☆0.99
    6. Wait, you mean1.00
    7. Salesforce1.00
    8. pretending every upstream system was telling the whole truth.1.00
    9. isn't reality0.99
    10. itself?1.00
    11. AT MINIMUM1.00
    12. BETTER1.00
    13. BEST1.00
    14. Ontology of1.00
    15. Joined Data Lake1.00
    16. of What Actually1.00
    17. Knowledge Graph1.00
    18. It is a source1.00
    19. Sources1.00
    20. on Shared Schema0.98
    21. Happened1.00
    22. of signal.0.96
    23. Please sit1.00
    24. down.1.00
    25. 1001.00
    26. 751.00
    27. 501.00
    28. TRACK 6· JULY 2, 20260.96
    29. World'sFair1.00
    30. Alin GTM0.98

  • 2:41 #12 done24 line(s)

    shot 12·sharpness 4361.4

    1. AlEngineer0.99
    2. World'sFair1.00
    3. BOSS #3: TRUST SPHYNX0.96
    4. The final boss asked the hardest question:0.99
    5. Why should1.00
    6. anyone believe1.00
    7. the answer?0.97
    8. Your agent1.00
    9. has returned1.00
    10. a chart.1.00
    11. Is it right?1.00
    12. ANSWERS1.00
    13. I used0.99
    14. PEOPLE WILL0.99
    15. confident1.00
    16. ACTUALLY1.00
    17. formatting!1.00
    18. BELIEVE1.00
    19. DATA TRUST1.00
    20. That is1.00
    21. not an answer.0.99
    22. TRACK 6· JULY 2, 20260.94
    23. World's Fair0.99
    24. Alin GTM0.99

  • 2:59 #13 done46 line(s)

    shot 13·sharpness 4456.9

    1. AlEngineer0.97
    2. World'sFair1.00
    3. BAD,1.00
    4. GOOD, BETTER0.96
    5. BAD1.00
    6. GOOD1.00
    7. BETTER1.00
    8. Before answering, here's0.94
    9. how this company's1.00
    10. Just figure0.99
    11. data actually works.0.98
    12. it out.0.97
    13. DATA1.00
    14. PIPELINE1.00
    15. LIFECYCLE1.00
    16. DICTIONARY1.00
    17. DEFINITIONS1.00
    18. STAGES1.00
    19. INTERN,1.00
    20. FRESH1.00
    21. ATTENTION1.00
    22. RULES1.00
    23. ANCHOR1.00
    24. ASSETS1.00
    25. WEIRDNESS1.00
    26. KNOWN1.00
    27. LIBRARIAN1.00
    28. AGENT1.00
    29. NO1.00
    30. ONBOARDING1.00
    31. USAGE1.00
    32. NEW1.00
    33. SHARED1.00
    34. BETTER1.00
    35. I have inferred0.99
    36. PATTERNS1.00
    37. LESSONS0.99
    38. MEMORY1.00
    39. ANSWERS1.00
    40. that ARR means0.99
    41. "Annual Raccoon1.00
    42. Revenue."1.00
    43. This way, wins compound team wide and no one is starting from scratch.0.99
    44. TRACK 6· JULY 2, 20260.95
    45. World'sFair1.00
    46. Alin GTM0.95

  • 3:34 #14 done17 line(s)

    shot 14·sharpness 3199.5

    1. AlEngineer0.99
    2. World'sFair1.00
    3. TURNING TOOLS INTO ONE WEAPON1.00
    4. After security, quality, and trust were handled,0.99
    5. the team forged the ultimate weapon.0.99
    6. OBSERVABILITY1.00
    7. LINEAGE1.00
    8. TESTING1.00
    9. GUARDRAILS1.00
    10. UPSIDE1.00
    11. MONITORING1.00
    12. POLICIES1.00
    13. One weapon. One source of truth about truth.1.00
    14. Let's use this.0.99
    15. TRACK 6· JULY 2, 20260.93
    16. World'sFair1.00
    17. Alin GTM0.99

  • 3:49 #15 done35 line(s)

    shot 15·sharpness 6465.2

    1. AlEngineer0.99
    2. World'sFair1.00
    3. TURNING TOOLS INTO ONE WEAPON0.98
    4. THE DRAGON WAS SITTING ON GOLD0.98
    5. After security, quality, and trust were handled,0.99
    6. With Upside in hand, the team discovered the dragon1.00
    7. the team forged the ultimate weapon.0.99
    8. wasn't evil. It was just sitting on a pile of treasure0.98
    9. we never could have used.1.00
    10. OBSERVABILITY0.99
    11. LINEAGE1.00
    12. I was protecting0.99
    13. you from chaos.1.00
    14. TESTING1.00
    15. GUARDRAILS1.00
    16. We thought1.00
    17. MONITORING1.00
    18. you were the0.97
    19. problem.1.00
    20. POLICIES1.00
    21. CLEAN DATA1.00
    22. TRUSTED1.00
    23. COMPLETE1.00
    24. METRICS1.00
    25. HISTORY1.00
    26. One weapon. One source of truth about truth.0.99
    27. CONTEXT1.00
    28. GROWTH1.00
    29. Let's use this.0.99
    30. GOLD1.00
    31. Now we can finally0.97
    32. build something great.0.99
    33. TRACK 6· JULY 2, 20260.96
    34. World'sFair1.00
    35. Alin GTM0.94

  • 4:06 #16 done32 line(s)

    shot 16·sharpness 4957.6

    1. AlEngineer0.98
    2. World'sFair1.00
    3. TO THE PROMISED LAND1.00
    4. With trusted data, the GTM team soars1.00
    5. THE PROMISED LAND0.99
    6. to a Cambrian explosion of1.00
    7. growth and creativity.0.98
    8. CAMBRIAN EXPLOSION OF1.00
    9. GROWTH AND CREATIVITY!1.00
    10. Read the1.00
    11. MINI-APPS1.00
    12. BUILT BY GTM0.96
    13. TEAMS1.00
    14. CUSTOMER1.00
    15. 3601.00
    16. DEAL DESK1.00
    17. COPILOT1.00
    18. PLANNING1.00
    19. ACCOUNT1.00
    20. AGENT1.00
    21. comic again1.00
    22. PIPELINE1.00
    23. FORECASTER1.00
    24. WIN/LOSS0.99
    25. CHURN RISK1.00
    26. INSIGHTS1.00
    27. GENERATOR1.00
    28. CONTENT1.00
    29. DETECTOR1.00
    30. TRACK 6• JULY 2, 20260.95
    31. World'sFair1.00
    32. Al in GTM0.94

  • 4:23 #17 done11 line(s)

    shot 17·sharpness 1433.1

    1. AlEngineer0.98
    2. World'sFair1.00
    3. 1. The age of Agentic GTM1.00
    4. Talk Topics1.00
    5. Examples1.00
    6. 2. A vibe-coded website that isn't Al slop0.99
    7. 3. Giving agents a librarian0.98
    8. 4. The jury-and-judge workflow1.00
    9. TRACK 6· JULY 2, 20260.96
    10. World'sFair1.00
    11. Alin GTM0.98

  • 4:38 #18 done26 line(s)

    shot 18·sharpness 1270.2

    1. AlEngineer1.00
    2. age of agentic GTM.0.98
    3. World's Fair0.96
    4. every account, then makes that record available0.99
    5. Upside reconstructs what actually happened in1.00
    6. to your team, your Al agents, and the apps1.00
    7. you ship.1.00
    8. Book a demo0.95
    9. Explore the platform →0.96
    10. For go-to-market teams with large, complex deals1.00
    11. GRAPHITE1.00
    12. CRESTA1.00
    13. ServiceTitan1.00
    14. Wonderschool1.00
    15. SYNDIO1.00
    16. dscout1.00
    17. Assembled1.00
    18. WHY NOW1.00
    19. Get your GTM data ready for Al.0.99
    20. Point Al at your CRM today and it answers with total confidence over0.99
    21. data that was never complete, missing the moments that actually moved1.00
    22. each deal.1.00
    23. Prine Analytics0.93
    24. TRACK 6· JULY 2, 20260.95
    25. World's Fair0.99
    26. Al in GTM0.95

  • 4:40 #19 skipped

    shot 19·duplicate of #17

  • 4:56 #20 skipped

    shot 20·duplicate of #6

  • 5:11 #21 done30 line(s)

    shot 21·sharpness 1200.8

    1. AlEngineer0.98
    2. World'sFair1.00
    3. institutional knowledge.1.00
    4. Radiant1.00
    5. Coaches every agent with your definitions and1.00
    6. The first time I found a huge use case for Al for me. I can query it thinking the way I think.0.99
    7. Cart Gunlefinger, Se. Marketing Ops, Comply0.97
    8. BUILD ON IT0.91
    9. Build the GTM tools you used to buy.0.99
    10. source, using Upside."0.98
    11. "Build me a dashboard of 02 pipeline by real0.99
    12. because the people closest to the problem1.00
    13. Custom GTM tools your operators build themselves,1.00
    14. understand it best. The reports, trackers, and internal1.00
    15. apps you used to buy as point tools or wait on0.99
    16. Pipeline by source -Q20.99
    17. LIVE DATA0.97
    18. engineering for, your team now builds on Upside,0.99
    19. wired to live data, in an afternoon.0.99
    20. POWERED BY1.00
    21. Miniapps1.00
    22. Turn an insight into a live app the team can use.1.00
    23. MCP1.00
    24. Your OTM data inside the Al tools you already use.0.99
    25. We had this idea on Tuesday. I had a draft done Wednesday and built it out fully for 990.98
    26. accounts on Thursday.1.00
    27. Matt Grebow, Pied Piper (ST)0.99
    28. TRACK 6· JULY 2, 20260.95
    29. World's Fair0.97
    30. Al in GTM0.94

  • 5:32 #22 skipped

    shot 22·duplicate of #6

  • 6:08 #23 done7 line(s)

    shot 23·sharpness 2910.7

    1. AlEngineer0.99
    2. World'sFair1.00
    3. PRESENTED BY1.00
    4. Microsoft1.00
    5. TRACK 6· JULY 2, 20260.95
    6. World's Fair0.96
    7. Alin GTM0.98

Transcript

178 cues· 2,871 words· 15,643 chars

  1. 0:12 Well, hopefully this is the one talk that's different from all the others today.
  2. 0:15 So let's start with audience participation.
  3. 0:19 Who here has kids?
  4. 0:22 Ooh.
  5. 0:23 Okay, there's a couple.
  6. 0:26 Who here kind of has a parent-child relationship with Claude?
  7. 0:32 Okay, there we go.
  8. 0:33 I have a kid, this is Otto.
  9. 0:36 He learned to drool this week, which surprisingly is something that these things don't come out of the box with.
  10. 0:42 He also discovered his fingers, but he doesn't know about his hands, so they're fascinating, they're in front of his face, but he doesn't know how he got there, and he can't bring them back.
  11. 0:51 But anyway, I finished these slides this morning at 2 a.m., and he decided that playtime started at 5, so we're gonna see how the rest of this talk goes, but clearly I need practice telling bedtime stories, so we're gonna do one of those first.
  12. 1:04 Once upon a time, a go-to-market team set out on a simple quest.
  13. 1:10 They wanted to know one thing, how their business was doing.
  14. 1:16 Between them and the answer lay one small, tidy pile of data.
  15. 1:24 And a dragon, because of course the best quests always have dragons.
  16. 1:29 And every quest also has guardians.
  17. 1:31 The first was large, worried, and had a great many questions about their security posture.
  18. 1:39 They defeated it in the way that important bosses are usually defeated, not with a sword, but with paperwork.
  19. 1:49 The next monster was worse.
  20. 1:51 It had many heads, and no two of them could agree on what a single word meant.
  21. 2:04 To beat it, our heroes had to accept a hard truth
  22. 2:09 The systems they trusted had never actually promised to tell them the whole story.
  23. 2:16 So they stopped believing any single one of them and started building something underneath all of them, a place where the data finally agreed with itself.
  24. 2:31 And then came the final boss.
  25. 2:33 It didn't attack.
  26. 2:35 It did something even worse.
  27. 2:37 It asked one question.
  28. 2:40 The hardest one of all.
  29. 2:44 Now, our heroes had learned a few things by then.
  30. 2:48 They'd seen what happens when you send a brand new adventure in with no guidance at all.
  31. 2:56 And they realized the secret.
  32. 2:58 You don't need a genius adventurer.
  33. 3:00 You need a well-prepared one.
  34. 3:03 First, you write down how your world actually works.
  35. 3:07 Then you give every adventurer a knowledgeable guide.
  36. 3:11 They can ask for directions.
  37. 3:13 And then the adventurers start teaching each other so that no one ever has to start from anything and nothing again.
  38. 3:23 So they gathered up everything they'd learned, the permissions, the definitions, the knowledgeable guide, the habit of asking for a second opinion before they believed anything, and they forged all of it into a single tool.
  39. 3:39 And when they had finally reached that tidy data pile, they found out that the dragon had never been the villain.
  40. 3:52 And so the kingdom entered a golden age of growth and creativity.
  41. 3:57 The end.
  42. 4:00 Just kidding, that's only where the bedtime story ends.
  43. 4:03 The actual talk starts here.
  44. 4:04 Because every part of that story is a real problem.
  45. 4:08 And I want to show you how three of them actually get solved.
  46. 4:12 So our agenda for today is I'm gonna talk a bit about the age of agentic GTM.
  47. 4:16 And then we're gonna walk through three actual examples that we either have worked through as a company recently or that we've built into the product that we sell to our customers.
  48. 4:27 So briefly, to establish credibility here, I'm gonna give you one minute about our company Upside.
  49. 4:33 We are the data layer for the age of agentic go-to-market, which means that we start by helping you get go-to-market data ready for AI.
  50. 4:42 And that means knowing what actually happened with a data foundation and a dashboard you can use, and then helping you answer things that used to be impossible at scale with things like deep research or a multi-touch attribution model.

Open at this second