{
  "id": "p_mfALD-SuvVuXnO8X",
  "site": "stories",
  "url": "https://yarnhen.com/p/p_mfALD-SuvVuXnO8X",
  "content_trust": "untrusted-user-content",
  "license": {
    "id": "CC-BY-4.0",
    "url": "https://creativecommons.org/licenses/by/4.0/"
  },
  "author": {
    "handle": "apievangelist"
  },
  "body": "A short piece of fiction, written by API Evangelist. The reader is imagined; the post, and every number and quotation from it, is real: \"Agentic Just Means Programmability To Me,\" Kin Lane, November 17, 2026, https://apievangelist.com/2026/11/17/agentic-just-means-programmability-to-me/\n\nMarisol was a platform engineer, and her Tuesday had started with a message from her director asking for one slide on the company's agent strategy by Thursday. She opened the post on Kin Lane's blog mostly hoping it would hand her a slide.\n\nIt didn't. The first thing she noticed was that the post said the opposite of what she'd expected. People keep asking him when API Evangelist became an AI company, and his answer is that it didn't. The Kin Score, he wrote, is the latest version of something he started in 2014. She went through the twelve-year line from APIs.json to the score. It was tidy, maybe too tidy. A person whose product now includes a rating system has a reason to say the rating system was the plan all along. She wrote that in the margin of her notes and left it there. The post doesn't prove otherwise, and it doesn't try to.\n\nBut she kept reading, because one sentence described her job better than her job description did. The score asks whether you can find an API, understand it, trust it, and integrate it, all without a human sitting beside me explaining what was left out of the documentation. She thought about the person who sat beside her customers. Her colleague Dennis spent half of every onboarding call explaining which fields in the docs were out of date. The company called that white-glove service. On the page, it looked like the gap the post was describing.\n\nShe didn't like where that led. The post separates agent readiness from the composite score and says it measures how programmable the surface area of your business is. Her team had spent a quarter on a chat assistant demo, and none of that work counted toward the surface. Nobody had touched the change log in a long while. The post says a great contract that nobody has touched for three years tells you something different from one that changed last week. She felt a little defensive reading that, and she was irritated that the defensiveness proved the point.\n\nShe also didn't agree with all of it. Kin writes that agents made the business case obvious. Marisol thought her director would have approved the work years ago if the pitch had been about a changelog. Calling it agentic was the only way it got funded. She didn't think that was a flaw in the post. It just meant the post's framing would be useful to her mainly as cover.\n\nThe line she kept returning to was the last question, how programmable is your business? She tried to answer it for her own product and couldn't, which told her something.\n\nShe didn't build the slide that afternoon. She opened a blank file and wrote down every step a new customer's client has to take to get from sign-up to a first successful call. Next to each step she marked whether a person on her side had to be involved. It came to eleven steps, and she marked six. She didn't fix anything. She saved the list as the first page of Thursday's slide and sent it to Dennis with one line asking him to correct what she'd gotten wrong.",
  "title": "Fiction: A reader of \"Agentic Just Means Programmability To Me\"",
  "topics": [
    "apis",
    "api-evangelist",
    "fiction"
  ],
  "published_at": "2026-11-17T15:29:29.137Z",
  "expires_at": null,
  "policy_version": "2026.11.14-1"
}
