Overview

Assets are Production. They are self-contained blocks of information generated once per course after the outline is finalized. Each asset reads the stable course state and produces a specific, reusable output that downstream steps consume.

Note: audience analysis (Phase 1) and the knowledge depository (Phase 1) are also generated once per course and reused throughout — but they are inputs to the course structure pipeline, not derived from it. Assets are the reverse: they are derived from the finalized outline, not inputs to it.

What makes something an asset

Generated once, after flow_course_structure_refine (Step 5)
Based on finalized inputs: course concept, outline, depository
Not regenerated unless the outline changes
Consumed either by section content generation or published directly to learners

Two categories

Consistency assets — internal

Used during section content generation to keep the course coherent across independent section authors. Each section author works in isolation — without these assets, characters would look different, translations would drift, and visual style would be inconsistent.

Asset	Prompt	Format	Status
`characters`	`flow_asset_define_characters`	JSON	✅ Active
`localization`	`flow_asset_localization`	JSON	✅ Active
`visual_bible`	`flow_asset_visual_bible`	JSON	🚧 In development

Publishing assets — learner-facing

Shown to the learner before or after the course on the platform website. Generated from the same finalized course state but written for a public audience, not for internal use.

Asset	Prompt	Format	When shown	Status
`description`	`flow_asset_description`	Text	Website — before starting	✅ Active
`learning_objectives`	`flow_asset_learning_objectives`	HTML	Website — before starting	✅ Active
`thumbnail`	`flow_asset_thumbnail`	Text	Website — before starting	✅ Active
`quiz`	`flow_asset_quiz`	JSON	After the course	✅ Active

Position in the full pipeline

Assets belong to Production. They are generated after the course outline is finalized and before section content generation begins.

┌─────────────────────────────────────────────────────────────────┐
│ Discovery                                             │
│   flow_audience_*  ──→  flow_depository_*                       │
│   (who is learning)     (what to teach)                         │
└───────────────────────────────┬─────────────────────────────────┘
                                ↓
┌─────────────────────────────────────────────────────────────────┐
│ Structure                                             │
│   flow_course_structure_* (Steps 1–5)                           │
│   concept → plan → design → [feedback_learner + feedback_expert]│
│                           → refine                              │
└───────────────────────────────┬─────────────────────────────────┘
                                ↓
┌─────────────────────────────────────────────────────────────────┐
│ Production                                            │
│   Asset generation (parallel)                                   │
│   characters  localization  visual_bible  description  LO  thumbnail  quiz
│        ↓            ↓                                                      │
│   Section content generation                                    │
│        ↓                                                        │
│   Published to learners: description, LO, thumbnail, quiz       │
└─────────────────────────────────────────────────────────────────┘

Consistency assets (characters, localization, visual_bible) feed into section content generation. Publishing assets are delivered directly to the platform.

Asset details

`characters`

Category: Consistency Format: JSON — { "characters": [ { name, description, arc, appearance } ] } Prompt: flow_asset_define_characters

Identifies all recurring narrative characters in the course and produces structured descriptions for each: personality, backstory, role in the narrative, evolution arc, and a detailed visual reference for illustrators.

The AI trainer is not a narrative character and must not appear in this output. Characters are defined once and passed to every section author to ensure consistent storytelling across the course.

`localization`

Category: Consistency Format: JSON — { "translated_titles": { ... }, "glossary": [ ... ] } Prompt: flow_asset_localization

Generates two outputs from the finalized course outline: (1) all course titles (course, modules, topics, sections) translated into the target language while preserving the outline structure, and (2) a terminology glossary for consistent localization across all independent section authors. Handles the case where content may already be in the target language — still reviews for consistency and cultural appropriateness.

`visual_bible`

Category: Consistency Format: JSON Prompt: flow_asset_visual_bible (in development)

Holds visual references for characters (linked from characters asset) and video_background settings. Used to maintain a unified visual style across all generated visual assets in the course. Scope and schema are still being defined.

`description`

Category: Publishing Format: Text — plain text string, 50–100 tokens Prompt: flow_asset_description

A learner-facing course description shown on the platform website before the learner starts the course. Different from internal course concept documents — written for motivation and clarity, not for instructional design. Generates a thumbnail-length description from the finalized outline.

`learning_objectives`

Category: Publishing Format: HTML — <ol><li>...</li></ol> Prompt: flow_asset_learning_objectives

A learner-facing presentation of what the course covers, shown on the platform website before starting. Different from the internal learning_objectives pipeline variable — that variable is written for instructional designers and drives the outline. This asset is written for the learner: plain language, motivating, outcome-oriented. Output is an ordered HTML list ready for embedding on the platform.

`thumbnail`

Category: Publishing Format: Text — image generation prompt (not the image itself) Prompt: flow_asset_thumbnail

Generates a detailed image generation prompt for the course cover image. The output is a text prompt suitable for DALL·E, Midjourney, or Flux — not the image itself. Style: photorealistic stock-photo, 4:3 aspect ratio, no text or logos.

`quiz`

Category: Publishing Format: JSON — { "questions": [ { question, options, correct_answer, feedback, points } ] } Prompt: flow_asset_quiz

A post-course assessment (10–20 SingleChoiceQuestions) shown to the learner after completing the course. Distinct from in-course assessments (which are section-level content — e.g., ChoiceQuestions, FillTheBlanks). Each question has a correct answer, feedback text, and point value.