Sequence Planning

Nine tools for arranging scenes into timed sequences, generating and comparing variants, working with sequence archetypes, and using style packs and brief templates.


plan_sequence

Arrange analyzed scenes into a sequence manifest guided by a style pack. Produces an ordered timeline with transitions, timing, and choreography notes.

  • Name
    scenes
    Type
    object[]
    Description

    Array of analyzed scene objects to sequence.

  • Name
    style
    Type
    string
    Description

    Style pack to guide transition choices and timing: prestige, energy, dramatic, minimal, intimate, corporate, kinetic, fade, analog, or documentary.

  • Name
    total_duration
    Type
    number
    Description

    Optional target total duration in milliseconds.

Returns: Ordered sequence manifest with inter-scene transitions, cumulative timing, and choreography notes.

Try asking your AI:

"Plan a sequence from these 5 scenes with prestige style, targeting 30 seconds total"


plan_variants

Generate multiple sequence variants from the same scenes for A/B comparison.

  • Name
    scenes
    Type
    object[]
    Description

    The scenes to create variants from.

  • Name
    style
    Type
    string
    Description

    Style pack to constrain variants.

  • Name
    count
    Type
    number
    Description

    Number of variants to generate (default: 3).

Returns: Multiple sequence plans with different ordering, timing, and transition strategies.


compare_variants

Rank two or more sequence variants on pacing, variety, flow, and style adherence.

  • Name
    variants
    Type
    object[]
    Description

    Array of sequence variants to compare.

Returns: Ranked comparison with scores for pacing, variety, flow, and overall quality.

Try asking your AI:

"Generate 3 variants for this product sizzle and compare them"


evaluate_sequence

Score a sequence on four dimensions: pacing, variety, flow, and adherence to the target style.

  • Name
    sequence
    Type
    object
    Description

    The planned sequence to evaluate.

  • Name
    style
    Type
    string
    Description

    Style pack to check adherence against.

Returns: Per-dimension scores (0-100), improvement suggestions, and an overall quality rating.

Try asking your AI:

"Evaluate this sequence for quality and prestige style adherence"


validate_manifest

Validate a manifest against personality guardrails. Checks structural correctness, required fields, and personality compliance.

  • Name
    manifest
    Type
    object
    Description

    The manifest object to validate.

  • Name
    personality
    Type
    string
    Description

    The personality to validate against.

Returns: Validation result with structural errors, missing fields, schema violations, and personality guardrail warnings.

Try asking your AI:

"Validate this manifest before I commit it"


recommend_sequence_archetype

Recommend a sequence archetype for a set of scenes. Six archetypes are available, each with a distinct narrative structure and pacing pattern.

  • Name
    scenes
    Type
    object[]
    Description

    Analyzed scenes to recommend an archetype for.

  • Name
    intent
    Type
    string
    Description

    Optional intent description (e.g., "product launch", "brand story", "feature tour").

Returns: Recommended archetype with rationale, beat structure, and expected pacing.

Try asking your AI:

"What sequence archetype works best for a 6-scene product launch?"


instantiate_sequence_archetype

Instantiate a sequence archetype with specific scenes. Maps your scenes to the archetype's beat structure and generates a ready-to-use manifest.

  • Name
    archetype
    Type
    string
    Description

    Archetype name from recommend_sequence_archetype.

  • Name
    scenes
    Type
    object[]
    Description

    Scenes to map into the archetype structure.

Returns: A sequence manifest built from the archetype template with your scenes slotted in.

Try asking your AI:

"Instantiate the crescendo archetype with my 8 product scenes"


get_style_pack

Retrieve a style pack definition. Ten packs are available: prestige, energy, dramatic, minimal, intimate, corporate, kinetic, fade, analog, and documentary.

  • Name
    name
    Type
    string
    Description

    The style pack name to retrieve.

Returns: Style pack definition with cut cadence, camera preferences, transition weights, and timing biases.

Try asking your AI:

"Show me the prestige style pack definition"


list_brief_templates / get_brief_template

Browse and retrieve brief templates. Five templates are available for common video intents.

list_brief_templates takes no parameters and returns all template names with descriptions.

  • Name
    name
    Type
    string
    Description

    Template name to retrieve (for get_brief_template).

Returns: Template structure, available parameters, and an example of generated output.

Try asking your AI:

"What brief templates are available?"

"Show me the product-launch brief template"

Was this page helpful?