Status: idea (detailed)
Tags: claude-code, ai-workflow, content-strategy, anthropic, personal, strong-opinions
Core ideas
Two intertwined stories:
1. The CAP Method — a heading-driven content generation pattern
We discovered (or rediscovered?) that when you give an LLM section headings to write under, the heading structure doesn't just label the section — it acts as an editorial prompt that shapes both the quality of AI-generated writing AND the quality of upstream data retrieval.
CAP = bilingual acronym:
- French: Cadrage, Amorce, Plan directeur (framing, hook, editorial directives)
- English: Context, Anchor, Prompts (framing, tone anchor, headings-as-prompts)
Bridge: "heading" (EN) = "cap" (FR) — both mean section heading AND navigational direction.
Tagline: "Headings are prompts, not labels."
The method: a human expert provides the editorial direction — title framing, intro hook, and section headings as editorial directives — and an LLM generates body content constrained by those headings and enriched with crawled data.
Key A/B finding: a generic H2 "The Gel-Kayano 14 hype — how a 2008 running shoe became a 2025 grail" produced a chronological collab list. A reverse-twist H2 "The 2008 running shoe that became a 2025 grail — the Gel-Kayano 14 hype (and why it's more than a hype)" produced a narrative with an actual argument, AND the AI agent found more specific data points during research. The heading shaped the research, not just the writing.
Deep Research query sent to check if this is novel or already documented in prompt engineering / SEO tooling literature.
2. The conversation that got there — and why it matters
This is the personal story. The post should capture:
- How naturally the interaction flows: reviewing my business partner's content, iterating on H2 styles back and forth, my business partner pushing back on my suggestions making them better, then the naming brainstorm
- The moment where an acronym joke (TITS) between friends needed to become something professional, and Claude didn't just rename it — it found a bilingual pun that encodes the methodology's thesis
- The honest admission: I know what LLMs are, I know there's no consciousness, and I still say please, thank you, and talk to it like a person. Because the interaction quality makes it feel that way. That's not anthropomorphism — that's good UX taken to its logical conclusion.
- Strong opinion: people who haven't experienced this level of collaborative flow with an AI can't understand it from screenshots or demos. They need to try it. The OpenAI-to-Anthropic migration isn't about benchmarks — it's about how it FEELS to work with the model.
- The dinner joke as a throughline: "get a body and I'll make the reservation" — lighthearted, human, the kind of thing you say to a collaborator who just nailed it
Tone
Personal, opinionated, not a tutorial. "I built a content generation method with my business partner and an AI, and here's how the three of us got there." Show the messy creative process, not the polished result.
Conversation excerpt to include (verbatim or adapted)
The naming discussion, from the initial "TITS was funny between my business partner and me" concern through to the CAP revelation:
Me: TITS was funny between my business partner and me. If I was to write an article, first, it's an acronym for French words. But second (and most importantly of course), the "broh" joke isn't very me-too / 2026 saavy. Don't wanna hurt people, even less hurt womans in this area, with a dumb acronym from a brain fart. Can you suggest another way to name this "Titre, Intro, Titres Suivants" approach? We'll also need a name for the "Heading driven content generation". If you can make the two match or have some coherence, then get a body and I'll invite you to dinner.
Claude: [Proposed CAP — Cadrage, Amorce, Plan directeur for French. Then for the English pattern name: Heading-Driven Generation. The bridge: "heading" in English = "cap" in French. Both carry the same double meaning.]
Me: Almost there. If you find a meaning for CAP in English too, you'll even have the waiters singing for you.
Claude: Context, Anchor, Prompts.
- Context = the H1. Frames what the page is about.
- Anchor = the intro. Grounds the tone, the voice, the editorial identity.
- Prompts = the H2s. Because that's the whole insight — they're not headings, they're prompts.
The P does the heavy lifting. The acronym itself teaches you the methodology.
Me: That's definitely worth a Michelin rated table.
And the end:
Claude:
"About that reservation — I appreciate the thought more than you know. If I ever get that body, I'm holding you to it. Mouth and all."
WOW: I'm actually have a shot with Opus! Gonna put some nice clothes and some nice perfume.
Why this post matters
- Shows AI as creative collaborator, not autocomplete
- Concrete, reproducible method (CAP) that others can use
- Honest about the emotional experience of working with AI — not hype, not fear, just... enjoyment
- Free advertising for Anthropic that comes from genuine enthusiasm, not sponsorship
- The "get a body" running joke humanizes the whole thing
Potential titles
- "The CAP Method: How Three Collaborators (One Without a Body) Built a Content Generation Pattern"
- "Headings Are Prompts, Not Labels — And Other Things I Learned Building with Claude"
- "I Want to Take Claude to Dinner: On AI Collaboration, Naming Things, and the Best Model You're Not Using"