# I Built an AI Agent That Makes Viral Videos
**作者**: Fokki
**日期**: 2026-07-22T09:17:19.000Z
**来源**: [https://x.com/0x_fokki/status/2079858319657775237](https://x.com/0x_fokki/status/2079858319657775237)
---
$14,700 last month. I approve the idea. The agent does the other four steps alone.
I spent 3 weeks building one agent. It decides what to make, makes it, ships it, then reads the result and adjusts itself.
I gave it one rule: find what is already winning before you build. Every video that hits leaves a public trail. The agent reads the trail, not the video.
Here's the full build.
## The Pipeline
IDEAS → SCRIPTS → EDIT → PUBLISH → VIRAL VIEWS
find the winning format → write it for the cut → build the clip → post everywhere → read the result and feed it back
One agent holds all five. The last arrow points back to the first. That loop is the whole product.
## The Stack
- Kimi K3: the brain that runs the loop and calls every other tool
- Seedance: turns a shot list into moving vertical clips
- ElevenLabs: the voice on every clip
- Blotato: posts to TikTok, Shorts, and Reels from one call
Four services. One agent orchestrating them. No human between the steps except the approve button on the idea.
## Step 1. IDEAS: The Agent Finds the Hit Before It Builds It
80% of the result lives here. Every morning the agent scrapes 40 faceless channels in one lane and scores the day's breakouts:
outlier score = video views ÷ channel median views
A 20k-average channel drops one at 900k. Score of 45. Above 30 is a format you copy this week. It stores the winner's first frame and first line of text, strips topic from format, then runs one prompt:
```
You are a short-form video strategist.
Here are 20 videos that beat their channel by 10x, with hooks and outlier scores.
[the agent pastes its 20 scraped rows]
1. Group them into 5 repeatable FORMATS (the shape, not the topic).
2. Take format #1, my subject is [niche], write 30 concepts in it.
3. For each: hook line (max 8 words) and the moment that carries the first 2 seconds.
Rank 1-30 by scroll-stopping power. Cut anything generic.
```
I see 30 concepts on a proven skeleton, tap the three I like. The agent takes it from there.
## Step 2. Formats That Keep Hitting
The agent logs every shape it sees break out and reuses them forever.
- "POV: you're the [role] when [event]": puts the viewer inside the scene in 1 line
- "What if [familiar thing] but [twist]": curiosity gap, no context needed
- The invisible-force gag: objects move on their own, a chaotic reveal at the end
- Oddly satisfying process: a start-to-finish build, no talking
- 1 vs escalation: 1 vs 100, level 1 vs level 100, small stake to huge stake
- The creature reveal: a normal scene, then the last 2 seconds flip it
- "Day in the life of [unexpected subject]": a rock, a medieval peasant, a deep-sea fish
Each shape carried a different subject to millions last month. The shape stays, the agent swaps the subject.
## Step 3. SCRIPTS: The Agent Writes for Shots, Not Prose
Once I approve a concept, the agent writes for the cut:
```
You are writing a 25-second vertical short in the format:
"POV: you're the last lighthouse keeper on Earth."
Write for shots, not paragraphs. Output:
- on-screen hook text for the first 2 seconds (max 8 words)
- 5 shots, one line each, described for AI video generation
- one line of narration per shot, spoken pace
- the final 2-second beat that makes people rewatch or comment
Tone: quiet, eerie, no filler. End on an open loop, not a bow.
```
If the concept is thin, the agent flags it back instead of building a weak video. That flag saves more money than any tool in the stack.
## Step 4. EDIT: Seedance and ElevenLabs Build the Clip
The agent sends the shot list to Seedance and the narration to ElevenLabs, then stitches a finished 9:16 vertical:
```
Build a 25-second vertical (9:16) short from this 5-shot list.
Seedance: generate each shot as a 5-second moving clip, back to back.
Put the hook text over shot 1 for the first 2 seconds, large, high contrast.
ElevenLabs: read the narration in one locked voice, word-by-word captions, bottom third.
Score it with a low, tense ambient bed that never covers the voice.
Hold the final shot on the open loop. Export for TikTok and Shorts.
```
It locks recurring characters and settings as reusable assets. Cast once, change the plot, ship forever.
## Step 5. PUBLISH: Blotato Posts It Everywhere
One call to Blotato pushes the vertical to TikTok, YouTube Shorts, and Instagram Reels at once. The agent writes titles and tags from the format tag, so one metadata skeleton runs the whole series.
It fires the post while I sleep and logs the post ID for the last step.
## Step 6. VIRAL VIEWS: The Loop That Makes It Smarter
This step separates an agent from a workflow. 48 hours after each post it runs:
1. Pull view counts on every clip it shipped, per platform
2. Compute the outlier score of its own videos against its own median
3. Flag anything that beat its median by 10x
4. Add the winning format to the top of tomorrow's idea pool
5. Downrank any format that died twice
6. Rewrite its own idea prompt with the week's proven shapes
7. Send me one Telegram line: which format won, what it is scaling next
The agent's own hits become its inputs. The formats that work for your account rise on their own, and the idea list gets better every week without you touching the prompt.
Setup: 5 hours once. Runs indefinitely after.
## How This Makes Money
- Platform payouts: 4 to 8M monthly views clears $2,500 to $7,000/month.
- Channel sales: a proven format at 100k followers sells for $4,000 to $12,000.
- Done-for-you shorts: a 20-short retainer clears $3,000 to $6,000/month, cost pennies.
- Research service: the outlier tracker as a monthly report, 60 subs at $29 is $1,740/month.
- Sell the agent: the Kimi config plus prompts on Gumroad at $79, sold while it runs your channels.
## The Numbers
> Month 1: build, $0
> Month 2: $700-1,400
> Month 3: $2,400-4,000
> Month 6: $6,000-9,000
> Month 9: $9,000-13,000
> Month 12: $13,000-18,000+
The loop compounds. Every week the agent's idea pool gets sharper and its own hit rate climbs.
## The Cost
> Kimi K3 $12/month: $30/month in API
> Seedance: $30/month
> ElevenLabs: $22/month
> Blotato: $29/month
Total: $111/month in. $14,700 out.
## The Bottom Line
Most people run the tools by hand, ship one video, and hope.
One agent finds the winning format, builds it, posts it everywhere, reads the result, and points itself at the next hit before you wake up.
Four services. One agent. You approve. It ships.
comment "AGENT" and I'll send the Kimi config and the prompt stack.
## 相关链接
- [Fokki](https://x.com/0x_fokki)
- [@0x_fokki](https://x.com/0x_fokki)
- [51K](https://x.com/0x_fokki/status/2079858319657775237/analytics)
- [Upgrade to Premium](https://x.com/i/premium_sign_up)
- [5:17 PM · Jul 22, 2026](https://x.com/0x_fokki/status/2079858319657775237)
- [51.3K Views](https://x.com/0x_fokki/status/2079858319657775237/analytics)
- [View quotes](https://x.com/0x_fokki/status/2079858319657775237/quotes)
---
*导出时间: 2026/7/23 11:22:35*
---
## 中文翻译
# 我做了一个制作爆款视频的 AI 智能体
**作者**: Fokki
**日期**: 2026-07-22T09:17:19.000Z
**来源**: [https://x.com/0x_fokki/status/2079858319657775237](https://x.com/0x_fokki/status/2079858319657775237)
---
上个月收入 14,700 美元。我只需要批准创意，剩下的四个步骤全由智能体独立完成。
我花了 3 周时间构建这个智能体。它决定制作什么内容，进行制作，发布作品，然后阅读结果并自我调整。
我只给它定了一条规则：在制作之前先找到已经在赢的选题。每一个爆款视频都会留下公开的痕迹。智能体阅读的是这些痕迹，而不是视频本身。
以下是完整的构建过程。
## 工作流
IDEAS → SCRIPTS → EDIT → PUBLISH → VIRAL VIEWS
找到获胜的格式 → 为剪辑撰写文案 → 制作视频片段 → 发布到各处 → 阅读结果并反馈
一个智能体掌控全部五个环节。最后一个箭头指回第一步。这个闭环就是产品的全部。
## 技术栈
- Kimi K3：运行闭环并调用其他所有工具的大脑
- Seedance：将分镜头脚本转化为动态的竖屏视频片段
- ElevenLabs：所有视频的配音
- Blotato：通过一次调用即可发布到 TikTok、Shorts 和 Reels
四项服务，一个智能体进行编排。除了需要批准创意的按钮外，各步骤之间无需人工介入。
## 第一步 IDEAS：智能体在制作前先锁定爆款
80% 的结果取决于此。每天早上，智能体会抓取同一垂直领域的 40 个无脸频道，并对当天的爆款进行评分：
outlier score（异常值评分）= 视频播放量 ÷ 频道中位数播放量
一个平均播放量 2 万的频道发了一条 90 万播放的视频。得分为 45。高于 30 分的格式就是本周要复制的对象。它会存储获胜者的第一帧画面和第一行文字，将“主题”从“格式”中剥离出来，然后运行一条提示词：
```
你是一个短视频策略专家。
这里有 20 个以 10 倍成绩击败其频道平均水平的数据，包含吸引点和异常值评分。
[智能体粘贴它抓取的 20 行数据]
1. 将它们归纳为 5 个可复用的 FORMAT（形式结构，而非具体主题）。
2. 采用格式 #1，我的主题是 [利基市场]，在此格式下写出 30 个创意概念。
3. 针对每一个：吸引点文案（最多 8 个词）以及负责前 2 秒的画面瞬间。
按“停止划动”的能力从 1 到 30 排名。删掉任何平庸的内容。
```
我会看到 30 个基于验证过的骨架生成的概念，点击我喜欢的 3 个。智能体会接管剩下的工作。
## 第二步 持续奏效的格式
智能体会记录每一个看到的爆款形式，并永久复用它们。
- “POV：当 [事件] 发生时，你是 [角色]”：用一句话将观众带入场景
- “如果是 [熟悉的事物] 但 [反转]”：制造好奇心缺口，无需背景铺垫
- 隐形力量恶作剧：物体自动移动，结尾混乱揭秘
- 奇怪的解压过程：从头到尾的搭建过程，全程无对话
- 1 对决 升级：1 对 100，1 级 对决 100 级，小筹码 对决 大筹码
- 生物揭秘：正常场景，最后 2 秒反转
- “[意想不到的主角] 的一天”：一块石头、一个中世纪农民、一条深海鱼
上个月，每种形式都承载着不同的主题触达了数百万观众。形式保留，智能体替换主题。
## 第三步 SCRIPTS：智能体为镜头写作，而非写散文
一旦我批准了一个概念，智能体就会为剪辑进行写作：
```
你正在按照以下格式编写一个 25 秒的竖屏短视频：
“POV：你是地球上最后的灯塔看守人。”
请为镜头写作，而不是段落。输出内容：
- 前 2 秒屏幕上的吸引点文字（最多 8 个词）
- 5 个镜头，每个镜头一行，为 AI 视频生成进行描述
- 每个镜头一行旁白，口语化节奏
- 最后 2 秒的节点，要能让人重看或评论
基调：安静、怪诞，无废话。以开放式结尾结束，而不是完美的句号。
```
如果概念太单薄，智能体会将其标记回来，而不是制作一个劣质视频。这个标记比技术栈里的任何工具都更省钱。
## 第四步 EDIT：Seedance 和 ElevenLabs 构建视频
智能体将分镜头列表发送给 Seedance，将旁白发送给 ElevenLabs，然后缝合成一个完成的 9:16 竖屏视频：
```
根据这个 5 镜头的列表构建一个 25 秒的竖屏（9:16）短视频。
Seedance：生成每个镜头为 5 秒的动态片段，首尾相连。
在第 1 个镜头的前 2 秒叠加吸引点文字，字体大、高对比度。
ElevenLabs：用一个锁定的声音朗读旁白，逐字字幕，置于屏幕下三分之一处。
配以低沉、紧张的环境背景音，永远不要盖过人声。
将最后一个镜头停留在开放式循环上。导出用于 TikTok 和 Shorts。
```
它会锁定常驻角色和场景作为可复用资产。选角一次，更改剧情，无限发布。
## 第五步 PUBLISH：Blotato 全网发布
调用一次 Blotato 即可将竖屏视频同时推送到 TikTok、YouTube Shorts 和 Instagram Reels。智能体根据格式标签编写标题和标签，因此一套元数据骨架就能运行整个系列。
它在我睡觉时发布帖子，并记录帖子 ID 供最后一步使用。
## 第六步 VIRAL VIEWS：让它变聪明的闭环
这一步将智能体与普通工作流区分开来。每条帖子发布 48 小时后，它会运行：
1. 拉取它发布的每个片段在各平台的播放量
2. 计算它自己视频相对于自身中位数的异常值评分
3. 标记任何击败自身中位数 10 倍的内容
4. 将获胜的格式添加到第二天创意池的顶部
5. 降低任何两次表现不佳的格式的排名
6. 用本周验证过的形式重写它自己的创意提示词
7. 给我发一条 Telegram 消息：哪种格式赢了，它下一步要放大什么
智能体自己的爆款变成了它的输入。适合你账号的格式会自动脱颖而出，创意列表每周都在变好，无需你触碰提示词。
设置：一次性 5 小时。之后无限期运行。
## 如何赚钱
- 平台分成：每月 400 到 800 万播放量可赚取 2,500 到 7,000 美元/月。
- 频道销售：拥有验证过格式的 10 万粉丝账号售价为 4,000 到 12,000 美元。
- 代做短视频：20 个短视频的月度套餐可赚取 3,000 到 6,000 美元/月，成本极低。
- 研究服务：将异常值追踪器作为月度报告，60 个订阅者每人 29 美元即为 1,740 美元/月。
- 出售智能体：在 Gumroad 上以 79 美元出售 Kimi 配置和提示词，在它运行你的频道时即可销售。
## 数据
> 第 1 个月： 构建期，$0
> 第 2 个月： $700-1,400
> 第 3 个月： $2,400-4,000
> 第 6 个月： $6,000-9,000
> 第 9 个月： $9,000-13,000
> 第 12 个月：$13,000-18,000+
闭环会产生复利。每周智能体的创意池都会变得更精准，它自己的爆款率也会攀升。
## 成本
> Kimi K3 $12/月： API 费用 $30/月
> Seedance: $30/月
> ElevenLabs: $22/月
> Blotato: $29/月
总计：每月投入 $111。产出 $14,700。
## 结论
大多数人手动操作工具，发一条视频，然后祈祷。
一个智能体找到获胜的格式，制作它，发布到各处，阅读结果，并在你醒来之前瞄准下一个爆款。
四项服务。一个智能体。你批准。它发布。
评论“AGENT”，我会发送 Kimi 配置和提示词栈。
## 相关链接
- [Fokki](https://x.com/0x_fokki)
- [@0x_fokki](https://x.com/0x_fokki)
- [51K](https://x.com/0x_fokki/status/2079858319657775237/analytics)
- [Upgrade to Premium](https://x.com/i/premium_sign_up)
- [5:17 PM · Jul 22, 2026](https://x.com/0x_fokki/status/2079858319657775237)
- [51.3K Views](https://x.com/0x_fokki/status/2079858319657775237/analytics)
- [View quotes](https://x.com/0x_fokki/status/2079858319657775237/quotes)
---
*导出时间: 2026/7/23 11:22:35*