Publishing Assets

Publishing assets are learner-facing blocks shown on the platform website before or after the course. They are generated from the same finalized course state as consistency assets, but written for a public audience, not for internal use during section generation.

For the general asset definition and the full three-category taxonomy (discovery, consistency, publishing), see Consistency assets.


Overview

AssetPromptFormatWhen shownStatus
descriptionflow_asset_descriptionTextWebsite — before starting✅ Active
learning_objectivesflow_asset_learning_objectivesHTMLWebsite — before starting✅ Active
thumbnailflow_asset_thumbnailTextWebsite — before starting✅ Active
quizflow_asset_quizJSONAfter the course✅ Active

Where publishing assets live in the course JSON

Publishing assets are stored as top-level fields on the course object:

AssetCourse fieldType
descriptioncourse.descriptionstring
learning_objectivescourse.objectivesstring (HTML)
thumbnailcourse.thumbnail{ content_type, base64 }
quizcourse.quizQuizQuestion[]

See Section schema for the full course object structure.


description

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.

When localizing an existing course copy, use flow_asset_localize_description to regenerate this block in the target language from the source outline plus the localization glossary.


learning_objectives

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. Phrase the objectives as outcome statements rather than imperatives or questions. Output is an ordered HTML list ready for embedding on the platform.

When localizing an existing course copy, use flow_asset_localize_learning_objectives to regenerate this block in the target language from the source objectives, source outline, and localization glossary.


thumbnail

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

Format: JSON — { "questions": [ { type, question, possible_answers: [ { text, correct, feedback_text } ] } ] } Prompt: flow_asset_quizflow_asset_quiz_distractors

A post-course assessment (10–16 SingleChoiceQuestions) shown to the learner after completing the course. Distinct from in-course assessments (which are section-level content — e.g., ChoiceQuestions, FillTheBlanks). Generated in two steps: flow_asset_quiz produces questions with correct answers; flow_asset_quiz_distractors generates distractors in a dedicated pass. Each answer option includes correctness and its own feedback_text. At least one distractor per question must be longer than the correct answer so length is not a selection cue.