Skip to main content

Highlight And Teaser Moments From Active Sequence

This workflow analyzes the currently active Premiere Pro sequence and marks short, self-contained moments that could work as teasers, highlights, podcast cold-open lines, social cutdowns, or review points.

Instead of searching the raw recordings manually, you ask the agent to understand the content actually used in the edit, find moments that can stand on their own, and add duration markers over the exact timeline ranges that make those moments useful.

New to Automation Agent?

This recipe uses Automation Agent for Adobe Premiere. The ready-made Library script runs without a live MCP-agent session but still uses your configured Workflow AI provider for editorial judgment. The adaptable prompt uses the agent workflow via MCP. See Set Up Your AI for both setup paths.

Fastest Path: Run The Library Script​

Open Library > Examples > Publishing & Social and run Find Highlights And Teasers In Active Sequence.

The script analyzes the transcripts of the sequence that is active when you continue from its setup dialog and creates scored duration markers for promising teasers, highlights, pull quotes, overview moments, reveals, reactions, and social cutdowns. The setup dialog lets you add optional editorial context, choose fewer or more candidates, emphasize teasers, highlights, or social cutdowns, and optionally retain a detailed report or troubleshooting files. You can switch sequences while the dialog is open; the sequence active when you click OK becomes the target.

This is the quickest repeatable path for spoken-word edits. The saved workflow already knows how to collect only the transcript ranges used in the edit, map them into sequence order, call Workflow AI with stable text IDs, validate the response, create the markers, and read them back. It therefore usually takes less time and fewer agent tokens than asking a live agent to discover and build the complete workflow during every run. Provider speed and sequence length still affect the runtime.

You need the Python Runtime Pack and a configured Workflow AI provider. Codex CLI and Claude Code are the currently tested recommendations for this complete-context editorial task. Local models running through LM Studio have not yet been validated for it. The script sends the usable transcript text and your optional guidance to that provider.

This Library script is transcript-only

It does not inspect frames, title cards, B-roll, screen content, silent reveals, or reactions that are not expressed in the transcript. Use the live-agent prompt below when visual or silent content matters: a live agent can inspect a small number of targeted frames and adapt its analysis to what it finds.

The result is a set of proposals, not an automatic editorial verdict. Review every score, title, boundary, duration, overlap, and coverage warning. If no candidate is strong enough, an empty result is valid and the script leaves the existing marker set unchanged.

After a successful run, the default keeps only the Premiere markers. Working files and the empty working folder are removed. Enable Keep detailed report to retain ::HOME::/automation-agent-sequence-highlights/Latest Highlights And Teasers Report.md, or enable Keep troubleshooting files to retain the run artifacts in the same folder. Failed runs and retirement warnings may keep diagnostic files so the problem can be investigated.

This walkthrough shows the repeatable Library path: configure Workflow AI, describe the moments you need, analyze the active-sequence transcript, and review the scored duration markers in Premiere.

Run the transcript-based Library workflow, inspect scored teaser candidates, and keep the final selection and cut under editorial control.

Earlier Live-Agent Walkthrough (Optional)​

The earlier walkthrough below shows the flexible live-agent version. It remains useful when visual or silent evidence matters and an agent should adapt the analysis beyond the transcript-only Library workflow.

Short walkthrough of finding the Best Moments in Your Premiere Timeline with Automation Agent in Adobe Premiere.

When This Is Useful​

Use this workflow when:

  • you want to find strong teaser or highlight moments in an edited sequence
  • you need podcast cold-open candidates made from sentences spoken later in the episode
  • you want a review layer of candidate moments directly on the timeline
  • you want each candidate to have a score and explanation, not just a timestamp
  • you want the agent to inspect only the sequence content that viewers actually hear and see

Typical examples:

  • podcast interviews where the opener should include two or three strong lines from later in the episode
  • long interviews where the best standalone quotes should be surfaced for social clips
  • tutorials or explainers where the most useful payoff moments should be marked
  • presentations, demos, or product videos where a few moments should become promotional cutdowns
  • documentary or event edits where a reviewer needs a first pass of emotionally or informationally strong moments

What You Need For The Live Agent Prompt​

Before you run the prompt:

  1. Open the target sequence and make sure it is the active sequence in Premiere.
  2. Make sure Automation Agent is connected through your MCP workflow.
  3. Make sure the source clips used in the sequence have transcripts where possible.
  4. Decide whether you want the default number of candidates or a specific target count.
  5. If the sequence is visually driven, expect the agent to inspect a small number of targeted still frames where transcript context is not enough.

Both paths only need to write sequence markers in Premiere. To protect the rest of your edit, open the Execution Permissions tab before running either one, enable Restrict write access in the Project section, then use + Add and choose Active Sequence Markers.

This adds write access for ::SEQ\ACTIVE::MARKER. The workflow can create highlight and teaser markers on the sequence captured for this run, but it cannot move clips, change track items, rename project items, or otherwise modify the project unless you add more write permissions.

The Library script also needs the installed Python Runtime Pack and filesystem access to its working folder under ::HOME::/automation-agent-sequence-highlights. Its Workflow AI call sends the usable transcript and optional guidance to your configured provider and may use network access, model tokens, and paid provider capacity according to that provider's configuration.

If the live agent exports transcripts or targeted still frames for analysis, also allow the narrow temporary folder it proposes. You do not need to grant broad filesystem access; review that path before the live run continues.

The Library script owns only markers whose final non-empty comment line is its exact versioned automation-agent:highlights-teasers tag. Scores, intended use, quotes, and explanations therefore appear before the technical ID. On a rerun it creates and verifies the new marker set before retiring the previous owned set. It does not delete unrelated markers. If old owned markers cannot all be retired, the new verified markers remain and the report warns that both runs are visible.

Copy And Paste Prompt​

Paste this prompt into your MCP client exactly as-is:

Using Automation Agent in Premiere Pro, analyze the currently active Premiere Pro sequence and create duration markers for strong highlight, teaser, and standalone pull-quote moments.

The goal is not to create chapters. The goal is to find short timeline ranges that could work as:
- teaser moments,
- highlight moments,
- podcast cold-open lines,
- social cutdown candidates,
- or concise overview moments that make a viewer curious.

Follow these steps carefully:

1. Capture Premiere's transcript of the active Sequence.

   * Capture the currently active Sequence once, then check `HAS_TRANSCRIPT` on that Sequence ref.
   * Export that same Sequence ref once with `prExportTranscriptJson` and verify that the JSON contains usable timed words.
   * Treat this as the transcript shown in Premiere's Text panel. Its word times are already Sequence times.
   * Do not rebuild it from individual source clips or filter it by track mute, clip disabled state, or a chosen audio track.

2. Preserve Premiere's Sequence semantics.

   * Use Premiere's composed result for nested Sequences, Multicam selections, repeated placements, cuts, and trims.
   * Keep transcript text and Sequence timecode unchanged, so duration markers cover the intended moment.
   * If a different transcript scope is required, stop and ask the editor to activate or construct the Sequence whose Text-panel transcript represents that scope.

3. Understand the content and editorial purpose.

   * Read the timeline-aware transcript as the actual spoken content of the edited video.
   * Look for sentences, exchanges, explanations, reveals, claims, emotional beats, jokes, conflicts, insights, or summaries that can stand alone without too much missing context.
   * Prefer moments that create curiosity, communicate a strong idea, or make the viewer want to keep watching.
   * For podcast-style material, especially look for one- to three-sentence moments that could be placed at the beginning as a cold open.
   * Avoid selecting moments that only make sense after a long setup unless the selected range includes the needed setup.

4. Use visual analysis only when helpful.

   * Start with transcript-based analysis.
   * If the transcript is sufficient, do not export unnecessary still images.
   * If a candidate moment depends on visuals, or the transcript is incomplete or ambiguous, export selected still images from the sequence for visual inspection.
   * Visual analysis is especially useful for:

     * screen recordings,
     * product demos,
     * visual reveals,
     * before/after examples,
     * slides or presentations,
     * montage sections,
     * long transcript gaps,
     * or visually important reactions.

   * Do not export frames continuously or at fixed short intervals by default.
   * Export still images only at strategically useful positions, such as inside a likely candidate range or around an unclear visual reveal.
   * Use the visual information to refine the candidate range and explanation, not to create noise.

5. Select candidate moments.

   * Choose only moments that are genuinely useful as highlights or teasers.
   * A candidate may be a single sentence, a short exchange, a visual reveal, or a compact passage.
   * Each candidate must have a clear start and end time in the active sequence.
   * The marker range must cover the full usable moment, not just its start.
   * Prefer tight ranges, but include enough context for the moment to make sense.
   * Avoid overlapping candidates unless both versions are meaningfully different.
   * Do not create candidates merely because there is a cut, pause, or topic change.
   * If no target count was given by the user, choose a sensible number based on sequence length and quality:

     * under 15 minutes: usually 3 to 6 candidates,
     * 15 to 45 minutes: usually 5 to 10 candidates,
     * 45 to 120 minutes: usually 8 to 16 candidates,
     * over 120 minutes: usually 12 to 20 candidates.

   * Quality beats quantity. If only a few moments are strong, create only those.
   * If there are many strong moments, prefer the strongest candidates and mention that more could be extracted in a second pass.

6. Score and label each candidate.

   * Give every final candidate a score from 1 to 100.
   * Use the score to represent how strong the moment is as a teaser or highlight, not how important it is to the full video.
   * Score higher when the moment:

     * works without much setup,
     * creates curiosity,
     * contains a strong quote or reveal,
     * has emotional or informational punch,
     * is easy to reuse in an opener or cutdown,
     * and has a clean start and end.

   * Assign one primary type: Teaser, Highlight, Pull Quote, Overview, Reveal, Reaction, or Social Cutdown.
   * Write a short title that describes the moment in plain language.

7. Add duration markers to the Premiere Pro sequence.

   * For every final candidate, create a sequence marker on the active sequence.
   * The marker must be a sequence marker, not a clip marker.
   * The marker must have both a start time and a duration that covers the complete candidate range.
   * Use marker type COMMENT unless there is a specific reason to use another marker type.
   * Use this marker name format:
     `92 Teaser - Short moment title`
   * Replace `92` with the actual score, replace `Teaser` with the primary type, and keep the title concise.
   * Do not include timestamps in the marker name.
   * Put the detailed reasoning in the marker comment using this format:

     Score: 92/100
     Type: Teaser
     Use: Podcast cold open, social teaser
     Quote or beat: "Short representative quote or visual beat"
     Why: One or two sentences explaining why this moment was selected.
     Notes: Any uncertainty, transcript limitation, visual dependency, or suggested handle adjustment.

   * If the exact frame is uncertain, choose the tightest reliable range and mention the uncertainty in the comment.

8. Output the result in the chat.

   * After creating the markers, provide a ranked list of the selected moments.
   * For each moment, include start time, end time, score, type, marker name, and a short reason.
   * Also briefly mention that the same moments were added as duration markers in Premiere Pro.
   * If visual still images were used, briefly mention that selected frames were inspected.
   * If some clips had missing or incomplete transcripts, mention this limitation briefly.

Important quality guidelines:

* Base the analysis primarily on Premiere's active-Sequence transcript as shown in the Text panel.
* Do not use unused parts of source clip transcripts.
* Create duration markers, not instant-only markers.
* Do not mark every interesting sentence. Mark the moments that would actually help an editor choose teasers or highlights.
* Keep marker ranges tight but usable.
* Use score and comments to make the review pass easy to scan.
* If the sequence contains very little spoken or visually interpretable content, create only the candidates that are justified by the available information.
* Before creating the final markers, reason through the candidate list carefully and remove weak or redundant moments.

Implementation Prompt For Repeatable Or Local Runs​

If you want to run this workflow repeatedly, or with a local / limited-context MCP client such as LM Studio, use an implementation prompt instead of the high-level prompt above.

This version gives the agent concrete Automation Agent MCP and Runtime DSL patterns up front. That reduces the amount of discovery the agent has to redo on every run.

Show the implementation prompt
Implement this as a bounded Automation Agent workflow:

1. Show setup options before binding Premiere state.
2. After the editor confirms, capture the active Sequence ref once and keep it as the marker owner.
3. Check HAS_TRANSCRIPT on that Sequence ref, export it exactly once with prExportTranscriptJson, and write the JSON to a run-scoped file.
4. Validate that the export contains usable timed words before semantic analysis. HAS_TRANSCRIPT alone is not sufficient.
5. Treat the exported word times as Sequence times. Do not enumerate source clips, remap source in/out ranges, or filter by track mute, Track Item disabled state, solo, or a selected audio track.
6. Use Premiere's composed transcript semantics for nested Sequences, Multicam choices, repeated placements, cuts, and trims.
7. Build stable local text IDs, send only the bounded semantic request to Workflow AI, and keep timing ownership outside the model.
8. Validate every returned ID and range before creating COMMENT duration markers on the captured Sequence.
9. Read markers back before retiring markers from the previous owned run. Never delete unrelated markers.
10. Clean run-scoped transcript and request files after success unless troubleshooting retention was explicitly selected.

If the editor wants a different transcript scope, ask them to activate or construct the Sequence whose Text-panel transcript represents that scope and rerun. Do not suggest muting tracks as a transcript filter.

What The Agent Will Do​

In practical terms, a good run of this workflow should:

  1. capture the active Sequence and export its Premiere transcript once
  2. verify that the exported JSON contains usable timed words
  3. use Premiere's existing Sequence-time transcript directly, including nested and Multicam edits
  4. identify short moments that can work as teasers, highlights, or standalone pull quotes
  5. use targeted still-frame inspection only where transcript context is not enough
  6. choose a practical candidate count based on sequence length and moment quality
  7. create duration markers that cover the full candidate ranges
  8. label each marker with score, type, and a concise title
  9. put the detailed rationale and any uncertainty into marker comments
  10. return a ranked list of the marked moments in the chat

Expected Result In Premiere​

The result should be:

  • a set of duration markers on the active sequence
  • one marker per selected teaser or highlight candidate
  • marker names that are easy to scan in the Markers panel, such as 91 Teaser - The impossible tradeoff
  • marker comments that explain the score, use case, quote or beat, and reason for selection
  • ranges that cover the complete usable moment rather than only a single timestamp

This workflow is meant to produce an editorial review layer. The agent should surface strong candidates, but the editor still decides which moments become the final opener, trailer, short, or cutdown.

Marker Naming And Comments​

Use the marker name for fast scanning and the marker comment for editorial detail.

Recommended marker name:

92 Teaser - Short moment title

Recommended marker comment:

Score: 92/100
Type: Teaser
Use: Podcast cold open, social teaser
Quote or beat: "Short representative quote or visual beat"
Why: The moment works without much setup and creates a clear open question for the viewer.
Notes: Start could be extended by 0.5 seconds if the cut feels too abrupt.

This keeps the marker list readable while still preserving the reasoning behind each choice. Putting the score at the start of the name makes the strongest candidates visible immediately, while the comment remains the place for nuance.

Prompt Variants​

You can adapt this workflow depending on the kind of highlights you want.

1. Podcast cold-open candidates only​

If you are preparing a podcast intro, add this instruction:

Only select moments that could work as podcast cold-open lines before the episode starts. Prefer one- to three-sentence spoken moments that are understandable without setup, create curiosity, and do not spoil the entire discussion.

That is useful when:

  • you want two or three strong lines for the beginning of an episode
  • the final use is audio-first or dialogue-first
  • you do not want broader visual highlights

2. Social cutdown candidates​

If the goal is short-form clips, add this instruction:

Prefer moments that can become standalone 15- to 60-second social cutdowns. Include enough setup inside each marker range for the clip to work when separated from the full video.

That is useful when:

  • the marked ranges may become reels, shorts, or trailers
  • a single quote is too short without surrounding context
  • you want fewer but more complete ranges

3. Tight pull quotes only​

If you want the shortest reusable quotes, add this instruction:

Prefer tight pull-quote markers over longer highlight ranges. Each marker should usually cover one complete sentence or one compact exchange.

That is useful when:

  • you are collecting text quotes, captions, or opener lines
  • you want less context and faster review
  • the sequence has many strong spoken moments

4. Give the agent a target count​

If you already know how many candidates you want, add a target count:

Create exactly 8 final candidate markers unless there are not 8 moments that meet the quality bar. If fewer than 8 are justified, create fewer and explain why.

That is useful when:

  • the sequence is long and you want a controlled first pass
  • multiple editors will compare candidate lists
  • you want a predictable amount of marker noise on the timeline

5. Rank for a specific audience or campaign​

If the strongest moment depends on the intended viewer, give the agent that context:

Rank moments for an audience of first-time viewers who do not know the speaker. Prefer moments that communicate stakes, surprise, or a clear practical takeaway.

That is useful when:

  • the best highlight depends on marketing strategy
  • internal context would otherwise make weak moments look stronger than they are
  • you want the score to reflect a particular use case

6. Require visual verification for visual reveals​

If the sequence contains important visual moments, add this instruction:

For any candidate that depends on a visual reveal, product state, screen recording, slide, or reaction shot, inspect at least one still frame inside the proposed marker range before creating the marker.

That is useful when:

  • the transcript alone cannot prove the moment works
  • a visual punchline or reveal is more important than the spoken words
  • marker comments should explain both the spoken and visual value

This recipe is closely related to YouTube Chapter Markers From Active Sequence. Both workflows reconstruct the edited sequence from transcript portions and targeted visual inspection. The difference is the editorial goal:

  • YouTube chapters mark section starts with instant markers.
  • Highlight and teaser moments mark reusable ranges with duration markers, scores, and review comments.