"Let's create a punchy sizzle reel from your video. Start by selecting your file:"

asset_add_file()

assetId

video_create_quick_cut

requires a CC asset URN (

assetId

), not

presignedAssetUrl

.

"Got it — [filename] is ready. Now let's set up your cut."

"Got it — [cut type], [style] vibe. Creating 3 variations at that length — let me preview them for you."

⚠️ The

user_prompt

is the primary lever for output quality — it does more work than

target_duration

. Pass the prompts below verbatim — abbreviating them weakens the output. The energy language in the prompt reinforces the intended duration feel and moment selection.

"Fast, punchy, hype, high energy. Hit hard and fast. Quick cuts, peak moments only, adrenaline rush from start to finish. No slow moments, no breathing room. Pure intensity."

"Polished, commercial, confident. Smooth pacing with deliberate rhythm. Each moment feels intentional and curated. Moderate energy — impressive but controlled. Professional and refined."

"Documentary, cinematic, immersive. Let moments breathe and unfold naturally. Build a story arc with texture and depth. Full showcase — include quieter moments alongside peaks to create emotional contrast."

"Create the most engaging highlight reel from the best moments in the video. Balance energy and pacing naturally."

// Variation A
video_create_quick_cut({
  assetIds: [assetId],
  target_duration: <mapped_seconds>,
  user_prompt: "<mapped style prompt>"
}) // → statusId_A

// Variation B
video_create_quick_cut({
  assetIds: [assetId],
  target_duration: <mapped_seconds>,
  user_prompt: "<mapped style prompt>"
}) // → statusId_B

// Variation C
video_create_quick_cut({
  assetIds: [assetId],
  target_duration: <mapped_seconds>,
  user_prompt: "<mapped style prompt>"
}) // → statusId_C

quickCutPoll(statusId)

jobStatus: "completed"

• url_A

  — Variation A presignedAssetUrl

• url_B

  — Variation B presignedAssetUrl

• url_C

  — Variation C presignedAssetUrl

✅ 3 variations ready — same length, different moment selection. Pick your favorite!

| Variation | Cut Type | Style   | Target | Status |
| --------- | -------- | ------- | ------ | ------ |
| 1         | <type>   | <style> | ~<Xs>  | ✅      |
| 2         | <type>   | <style> | ~<Xs>  | ✅      |
| 3         | <type>   | <style> | ~<Xs>  | ✅      |

Note: actual durations may vary — Quick Cut selects the best moments rather than cutting to an exact second. The prompt vibe (e.g. "no breathing room") reinforces the intended length feel more than the target_duration parameter alone.

"Which variation do you want to download, or would you like all 3? You can also rerun with a different style or cut type."

video_create_quick_cut

video_resize

media_enhance_speech

1. Tell the user: "Quick Cut outputs can't be passed directly to the resize tool — you'll need to download your preferred cut first, then re-upload it and I'll resize from there."
2. Let them download from the preview.
3. Open the picker:

   asset_add_file()

4. Once re-uploaded, run

   video_resize

   on the fresh

   assetId

   with their target dimensions.

• Content-aware cuts based on speech ("remove the parts where they repeat themselves")
• Trimming to specific timestamps ("cut from 0:30 to 1:15")
• Semantic understanding of dialogue

• video_create_quick_cut

  returns 403 (entitlement): Retrying does not help for a 403 entitlement — stop and surface the plan requirement. Respond with:

  "I was unable to create your quick cut.

  Why: Adobe Quick Cut isn't available on your current Adobe plan.

  *Options:

  • Manually trim the video in another editor.*

  Let me know how you'd like to proceed."

• Any tool call returns 401 (not authenticated): Ask the user to re-authenticate via Adobe OAuth and retry.

• StoryBuilderNoARoll

  : The most common error. Means Quick Cut detected no A-roll (talking head / primary camera footage) in the clip — only B-roll. The tool requires at least some dialogue or narration to anchor the story structure. Respond with:

  "This video appears to be B-roll only — scenery, action, or product shots without anyone speaking to camera. Quick Cut needs some talking-head footage to build a story around. Try uploading a video that includes someone speaking on camera, or a mix of interview + B-roll." Retries repeat the same error regardless of duration/style; no workaround exists.

• Job fails with any other error on first attempt: Retry once with the same parameters. If it fails again, report and suggest re-uploading the source video.
• Stuck at same % for 5+ poll rounds: Inform user, suggest re-uploading the source video.
• User uploads an image by mistake: Detect from

  mediaType

  — if not

  video/*

  , say so and re-open picker.
• One of the 3 variations fails (but not all): Preview and deliver the successful ones, note the failure clearly. If all 3 fail with

  StoryBuilderNoARoll

  , apply the B-roll error response above.