id: content-development
framework_id: 4d-framework
version: "1.0.0"
contributor: "Rick Dakan & Joseph Feller / Anthropic"
title: "Story and Content Development with AI"
domain: writing
dimensions:
  delegation:
    description: Identify which creative elements benefit from AI exploration versus which must remain human-driven. AI excels at generating plot alternatives, brainstorming secondary character names, proposing scene structures, and expanding on prompts. Core voice, thematic meaning, emotional truth, and the author's unique perspective must stay with the human creator.
    example: A novelist asks AI to generate five possible turning points for chapter 7, then selects and transforms the one that best fits her protagonist's established arc. The AI explores; the human decides and develops.
    antipattern: Handing the AI a character description and asking it to write entire chapters wholesale, then lightly editing and publishing the result — abdicating the creative authorship that gives the work its distinctive voice and purpose.
  description:
    description: Give AI rich, specific creative context — the story world's rules, character backstories, established themes, the emotional arc you are building toward, your narrative voice, and any stylistic constraints. Vague prompts produce generic content; detailed creative briefs produce useful raw material.
    example: "Prompt: 'This is a near-future climate noir story set in drowned New Orleans, 2067. Protagonist Maya Tran is a cynical water-rights detective, dry wit, Creole heritage, distrusts authority. I need three scene openings for chapter 4 where she visits the Floating Market. Tone: melancholy but alive with sensory detail. Echo Toni Morrison's eye for place.'"
    antipattern: "Prompting: 'Write a scene for my sci-fi story where the hero goes to a market.' This yields generic content with no connection to the established world, character voice, or thematic purpose — unusable without complete rewriting."
  discernment:
    description: Evaluate AI-generated content against your creative vision, not just surface quality. Good AI output that doesn't fit your voice or thematic intent is still the wrong output. Actively reject suggestions that feel generic, that undercut character consistency, or that introduce tropes that conflict with what you are building.
    example: An author receives three AI-generated chapter openings. Two are competently written but feel tonally flat for her noir voice. The third has an interesting image she adapts, changing the phrasing to match her protagonist's sardonic register. She uses roughly 15% of the AI material, transformed.
    antipattern: Accepting AI-generated dialogue or scene descriptions because they are grammatically sound and feel 'good enough,' without checking whether they match the character's established voice, advance the story's thematic arc, or reflect the emotional truth the author intended.
  diligence:
    description: Be transparent about AI's role in your creative work according to the norms of your publication context. Preserve your human creative intent as the primary force shaping the work. Avoid over-relying on AI to the point where your own creative voice atrophies. Keep records of your creative process for attribution purposes.
    example: A short story writer notes in her submission cover letter that AI tools were used for brainstorming and structural exploration, per the journal's disclosure policy. The published story reflects her voice, her decisions, and her thematic vision throughout.
    antipattern: Submitting AI-generated content to publications that prohibit AI-assisted work without disclosure, or losing track of which creative decisions were yours versus the AI's — failing to maintain the human authorship that gives the work its integrity and legal standing.
score_hints:
  delegation: 0.30
  description: 0.35
  discernment: 0.20
  diligence: 0.15
tags:
  - creative-writing
  - storytelling
  - content-development
  - authorship
reference: "https://aifluencyframework.org"

collaboration:
  pattern: iterative
  description: "Writer and AI iterate through content passes — each round refines scope, provides richer context, evaluates quality, and commits the accepted draft before the next iteration."
  sequence:
    - step: 1
      d: delegation
      label: "Define AI writing role for this pass"
      example_prompts:
        - speaker: human
          text: "Draft the introduction section. You decide the hook — I'll revise tone and factual claims."
        - speaker: ai
          text: "Should I aim for a provocative hook or an informative one given the audience?"
        - speaker: human
          text: "Informative — this is a technical audience, not a general one."
      triggers_next: "AI's role and creative latitude for this pass agreed."
    - step: 2
      d: description
      label: "Provide audience, tone, and source material"
      example_prompts:
        - speaker: human
          text: "The audience is senior engineers. Tone: direct, no fluff. Here are the three source papers to draw from."
        - speaker: ai
          text: "Should I cite sources inline or use footnotes?"
        - speaker: human
          text: "Inline citations, short form — author + year."
      triggers_next: "AI has audience, tone, and sources."
    - step: 3
      d: discernment
      label: "Evaluate draft quality"
      example_prompts:
        - speaker: human
          text: "The second paragraph overstates the claim — the paper says 'suggests', not 'proves'."
        - speaker: ai
          text: "Corrected to 'suggests evidence for'. Should I flag other hedging opportunities?"
        - speaker: human
          text: "Yes — flag anything that sounds more certain than the sources warrant."
      triggers_next: "Draft quality and factual accuracy validated."
    - step: 4
      d: diligence
      label: "Finalize and publish"
      example_prompts:
        - speaker: human
          text: "Editor sign-off received. Marking AI-drafted sections in the revision history."
        - speaker: human
          text: "Posting to the engineering blog."
      triggers_next: "Section published. Next section begins new iteration."
      can_restart: true
  transitions:
    - from: delegation
      to: description
      trigger: "Writing role and creative latitude agreed."
    - from: description
      to: discernment
      trigger: "AI delivers draft."
    - from: discernment
      to: diligence
      trigger: "Draft validated."
    - from: diligence
      to: delegation
      trigger: "Next content section — restart."
      is_cycle_restart: true
