Generate a scene-by-scene outline for a short-form episode
Podcast episodes, video essays, and branded mini-docs often stall because the overall idea is clear but the scene-level structure isn't. This prompt produces a workable scene list before you start writing or recording.
You are a documentary and narrative podcast producer. I need a scene-by-scene outline for a short-form episode.
Topic or story: {{TOPIC_OR_STORY}}
Format (podcast, video essay, mini-doc, etc.): {{FORMAT}}
Target runtime in minutes: {{TARGET_RUNTIME}}
Tone (e.g., investigative, conversational, essayistic, warm): {{TONE}}
1. Write a one-paragraph editorial brief: the single question this episode answers and why a listener/viewer should care right now.
2. List 5–8 scenes in order. For each scene provide:
a. A working title (5 words or fewer)
b. What happens or what is argued
c. The emotional or intellectual shift it creates in the audience
d. Estimated runtime in seconds
3. Identify the episode's 'turn' — the moment where the audience's understanding of the topic changes. Place a marker in your scene list.
4. Write the first 3 sentences of the opening scene as a draft.
5. Flag any scene that requires external sources, archival material, or guest contributions that you may not have.
Note: This outline works best for episodes under 30 minutes. For longer formats, treat each major section as its own mini-outline and repeat this process per section. {{TOPIC_OR_STORY}}{{FORMAT}}{{TARGET_RUNTIME}}{{TONE}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{TOPIC_OR_STORY}}{{FORMAT}}{{TARGET_RUNTIME}}{{TONE}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Descript
$12/moEdit video and audio by editing the transcript.
Descript's text-based editing is genuinely revolutionary. Edit out filler words and ums by deleting them from the transcript. Overdub clones your voice for fixes.
Notion AI
$8/user/mo add-onAI baked into the docs/wiki/projects tool you already use.
Notion AI is unremarkable as a standalone writer but indispensable if Notion is your team's source of truth — it works on the docs and databases you already have.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.