{"slug": "from-sanity-to-madness", "title": "From Sanity to Madness", "summary": "A developer used an AI production team of 12 role-based agents to script the third episode of a satirical video series, then documented how client feedback pushed each draft from mild workplace humor into absurdist \"madness.\" The final scripts escalate Zuckerberg from testing logos to testing a boiling kettle, Gates from page numbers to the fourth character on page 42, and Nadella from connecting with competitors to connecting with a mosquito.", "body_md": "📝 Originally published (in Japanese) at [forge.workstyle.tech](https://forge.workstyle.tech/blog/push-the-comedy-to-madness/?utm_source=devto&utm_medium=crosspost&utm_campaign=push-the-comedy-to-madness).\n\nIn a series of satirical videos, I had an AI production team (a planning meeting of 12 roles) write the scripts for the third episode. After reviewing the finished video, the client sent back the following feedback:\n\nMark Zuckerberg doesn't just test things when he's unsure; he tests everything. We should emphasize \"trying everything\" in the copy, right? Otherwise, the content feels like, \"Wait, you're testing that?\"\n\nWhere in the video is the part about Bill Gates' \"obsessive close reading\"? The humor comes from the idea that he over-reads too much, so the content and copy should reflect that absurdity, like, \"Wait, you read that too and are concerned about it?\"\n\nTurn inability to make up your mind into madness.\n\nThe evolution of the Zuckerberg version went like this:\n\n**Initial Draft (Me)**\n\n```\nSam     Which one do you prefer?\nZuck    Both.\nSam     I need to make a decision.\nZuck    Already shipped it.\nSam     How about B?\nZuck    Marginal difference. We already have a million users.\n```\n\n**Final Script by the Production Team**\n\n```\nSam     Which one do you prefer?\nZuck    Let's try both.\nSam     We already tried.\nZuck     Next up: deciding.\nSam     Deciding?\nZuck    Let's try that too.\n```\n\nThe team cut the \"1 million users\" line because it implied unauthorized large-scale user experimentation. What remained was a coherent story contained entirely within the boardroom: \"Let's test the decision-making process too.\"\n\n**It was enough for a smart person to say something slightly different**; there was no insanity involved.\n\nHere is the idea the client pitched:\n\nTouching a boiling kettle while saying, \"Huh? It's hot? Let's test it.\" But because that's completely normal for him, his expression doesn't change.\n\nThen, they added this:\n\nWhat if at the end, he gets burned and his hand swells up as big as his face?\n\nHere is how the dialogue turned out in the final draft:\n\n```\nSam       Which logo?\nZack      Put out both.\nSam       That kettle is hot, you know.\nZack      Hot?\nZack      Let's test it.\n          (Screen flashes to \"Post-Test\" for a split second)\nZack      It was hot.        ← Visual of swollen hand appears\nSam       Told you so.\nZack      Hearing about it and testing it aren't the same thing.\n```\n\nFrom comparing logos to a steaming kettle. **The subject of verification leaps straight from work to his own body.** He doesn't bat an eye. And with that final line, you realize that in his own mind, it makes complete sense.\n\n**The Gates episode.** The first draft only had the document page numbers jumping from 128 → 3 → 1. The madness of the deep dive wasn't showing through yet. The client's instructions were this:\n\nPack it in up to the fourth character on page 42.\n\n```\nSam      How's the document looking?\nGates    The footnote on page 17.\nSam      What about the main text?\nGates    The source is from 2019.\nSam      ...What about the main text?\nGates    The fourth character on page 42 has a different font.\n```\n\nI hadn't even mentioned the main text once. I wasn't even looking at pages; I was looking at individual characters.\n\n**The Nadella episode.** At first, it ended on a good note: \"Let's connect with our competitors.\"\n\nEven with enemies, we want to collaborate. The punchline was: \"Ah, a mosquito!\" \"A mosquito? Let's connect.\"\n\n```\nSam      Competitors are using the same features.\nNadella    Let's connect.\nSam      They're coming to crush us.\nNadella    Even more so, let's connect.\nSam      ...Ah, a mosquito.\nNadella    A mosquito?\nNadella    Let's connect.\n```\n\nThe right side of the collaboration diagram changes from \"Competitors\" to \"Mosquito.\"\n\nReading the team's meeting logs makes the reasons clear.\n\nAll of these are valid points. However, when everyone insists on what is \"correct,\" the conversation converges on a safe middle ground that offends no one and contains no contradictions. **Madness can only be born by shattering that consistency.**\n\nHere is the setup that worked best:\n\nFor the kettle episode, the team proposed skipping ahead to the instant \"after the test,\" bypassing the touch scene entirely. When image generation models couldn't properly draw a swollen hand, we had another AI generate it as an SVG. When it came to turning creative leaps into concrete realities, the AI did an exceptional job.", "url": "https://wpnews.pro/news/from-sanity-to-madness", "canonical_source": "https://dev.to/orca_forge/from-sanity-to-madness-128d", "published_at": "2026-09-30 00:28:48+00:00", "updated_at": "2026-09-30 00:46:53.655526+00:00", "lang": "en", "topics": ["ai-agents", "generative-ai", "ai-tools"], "entities": ["Mark Zuckerberg", "Bill Gates", "Satya Nadella", "Sam"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/from-sanity-to-madness", "markdown": "https://wpnews.pro/news/from-sanity-to-madness.md", "text": "https://wpnews.pro/news/from-sanity-to-madness.txt", "jsonld": "https://wpnews.pro/news/from-sanity-to-madness.jsonld"}}