{
  "type": "tweet",
  "id": "2031308486815133905",
  "url": "https://x.com/itsolelehmann/status/2031308486815133905",
  "twitterUrl": "https://twitter.com/itsolelehmann/status/2031308486815133905",
  "text": "i can't believe nobody caught this.\n\nAnthropic's entire growth marketing team was just ONE PERSON\n\n(for 10 months, confirmed)\n\na single non-technical person ran paid search, paid social, app stores, email marketing, and SEO for the $380B company behind claude\n\nhere's exactly how one human is doing the job of a full marketing team:\n\nit starts with a CSV.\n\n1. he exports all his existing ads from his ad platforms along with their performance metrics (click-through rates, conversions, spend, etc)\n\n2. feeds the whole file into claude code\n\n3. and tells it to find what's underperforming.\n\nclaude analyzes the data, flags the weak ads, and generates new copy variations on the spot\n\nthis is where he gets clever:\n\nhe then splits the work into 2 specialized sub-agents:\n\n1. one that only writes headlines (capped at 30 characters)\n\n2. and one that only writes descriptions (capped at 90 characters).\n\neach agent is tuned to its specific constraint so the quality is way higher than cramming both into a single prompt\n\nso now he's got hundreds of fresh headlines and descriptions.\n\nbut that's just the text.\n\nhe still needs the actual visual ad creative, the images and banners that go on facebook, google, etc.\n\nso he built a figma plugin that:\n\n1. takes all those new headlines and descriptions\n2. finds the ad templates in his figma files\n3. and automatically swaps the copy into each one.\n\nup to 100 ready-to-publish ad variations generated at half a second per batch.\n\nwhat used to take hours of duplicating frames and copy-pasting text by hand\n\nso now the ads are live.\n\nthe next question is which ones are actually working.\n\nfor that he built an MCP server (basically a custom integration that lets claude talk directly to external tools) connected to the meta ads API.\n\nso he can ask claude things like:\n\n• \"which ads had the best conversion rate this week\"\n• or \"where am i wasting spend\"\n\nand get real answers from live campaign data without ever opening the meta ads dashboard\n\nand the part that ties it all together and closes the loop:\n\nhe set up a memory system that logs every hypothesis and experiment result across ad iterations.\n\nso when he goes back to step one and generates the next batch of variations...\n\nclaude automatically pulls in what worked and what didn't from all previous rounds.\n\nthe system literally gets smarter every cycle.\n\nthat kind of systematic experimentation across hundreds of ads would normally need a dedicated analytics person just to track\n\nthe numbers from the doc:\n\nad creation went from 2 hours to 15 minutes. 10x more creative output.\n\nand he's now testing more variations across more channels than most full marketing teams\n\na $380 billion company.\n\nand their entire growth marketing operation (not GTM) = just one person and claude code lol\n\ntruly unbelievable",
  "source": "Twitter for iPhone",
  "retweetCount": 356,
  "replyCount": 177,
  "likeCount": 4522,
  "quoteCount": 94,
  "viewCount": 1295391,
  "createdAt": "Tue Mar 10 09:57:37 +0000 2026",
  "lang": "en",
  "bookmarkCount": 8722,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2031308486815133905",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "itsolelehmann",
    "url": "https://x.com/itsolelehmann",
    "twitterUrl": "https://twitter.com/itsolelehmann",
    "id": "1587816802264006657",
    "name": "Ole Lehmann",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1633697720291704832/GBmxTCa6_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1587816802264006657/1770362135",
    "description": "Helping non-technical people run their business with AI agents.\nAI connoisseur, robotics maxi, eu/acc supporter, dad, techno optimist",
    "location": "10x your marketing w/ AI ↓",
    "followers": 129020,
    "following": 2599,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Nov 02 14:40:13 +0000 2022",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {
        "urls": [
          {
            "display_url": "aisolo.beehiiv.com/subscribe",
            "expanded_url": "http://aisolo.beehiiv.com/subscribe",
            "indices": [
              0,
              23
            ],
            "url": "https://t.co/nBTF3Mye2d"
          }
        ]
      }
    },
    "fastFollowersCount": 0,
    "favouritesCount": 62747,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 2535,
    "statusesCount": 24239,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2027076036135927924"
    ],
    "profile_bio": {},
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.x.com/SJwgLP28nG",
        "expanded_url": "https://x.com/itsolelehmann/status/2031308486815133905/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": [
              {
                "h": 128,
                "w": 128,
                "x": 52,
                "y": 186
              }
            ]
          },
          "medium": {
            "faces": [
              {
                "h": 128,
                "w": 128,
                "x": 52,
                "y": 186
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 128,
                "w": 128,
                "x": 52,
                "y": 186
              }
            ]
          },
          "small": {
            "faces": [
              {
                "h": 121,
                "w": 121,
                "x": 49,
                "y": 176
              }
            ]
          }
        },
        "id_str": "2031308484378243073",
        "indices": [
          280,
          303
        ],
        "media_key": "3_2031308484378243073",
        "media_results": {
          "result": {
            "media_key": "3_2031308484378243073"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HDCoTeCaMAEG0Z1.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 361,
              "w": 644,
              "x": 0,
              "y": 0
            },
            {
              "h": 644,
              "w": 644,
              "x": 0,
              "y": 0
            },
            {
              "h": 716,
              "w": 628,
              "x": 16,
              "y": 0
            },
            {
              "h": 716,
              "w": 358,
              "x": 196,
              "y": 0
            },
            {
              "h": 716,
              "w": 644,
              "x": 0,
              "y": 0
            }
          ],
          "height": 716,
          "width": 644
        },
        "sizes": {
          "large": {
            "h": 716,
            "resize": "fit",
            "w": 644
          },
          "medium": {
            "h": 716,
            "resize": "fit",
            "w": 644
          },
          "small": {
            "h": 680,
            "resize": "fit",
            "w": 612
          },
          "thumb": {
            "h": 150,
            "resize": "crop",
            "w": 150
          }
        },
        "type": "photo",
        "url": "https://t.co/SJwgLP28nG"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "article": null
}