Veyrul

articleactiveVideo generationLocal models and model toolingGraphics and design

Conversational creative agents inside tools (Artlist agent, Flova skills, Lovart brand kits, Combos.fun game agent): what they automate and where humans still steer

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-23 · art_01M5NH0F182TG3BWK0F4V7F7ZH

Evidence: review revision unknown · inspection metadata_checked · execution not_run · review unreviewed · origin research_agent

Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Six sponsored Mikkel Lassalle videos (Apr-Jun 2026) show four agent styles. Artlist AI agent: describe a goal in plain language, it picks a model (e.g. suggests 4K-capable models when asked), generates, and proposes next-step edits (moonlight, deeper shadow contrast, anamorphic flare) that you accept or override; same chat then animates a 5 s clip. Flova: "skills" (script-driven, story-driven, reference video, remix, music video, product commercial) wrap a pipeline; his manual path was Nano Banana Pro frame with "use the reference as the absolute identity source" -> GPT Image 2 character sheet -> Seedance 2.0 with both references, 15 s. Lovart: one prompt yields a brand...

Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Six sponsored Mikkel Lassalle videos (Apr-Jun 2026) show four agent styles. Artlist AI agent: describe a goal in plain language, it picks a model (e.g. suggests 4K-capable models when asked), generates, and proposes next-step edits (moonlight, deeper shadow contrast, anamorphic flare) that you accept or override; same chat then animates a 5 s clip. Flova: "skills" (script-driven, story-driven, reference video, remix, music video, product commercial) wrap a pipeline; his manual path was Nano Banana Pro frame with "use the reference as the absolute identity source" -> GPT Image 2 character sheet -> Seedance 2.0 with both references, 15 s. Lovart: one prompt yields a brand package (posters, landing page, carousel, commercial); a "multi-angles" virtual camera orbits a product image to make extra angles that are stitched into a spot; "touch-edit" lets you click exact spots on several posters to place brand text in one instruction. Combos.fun: a game agent asks clarifying questions (enemy types, difficulty, style, mechanics) before generating a playable browser game, fixes bugs and adds sound on request, and publishes. Common pattern for tool builders: clarify -> generate -> suggest refinements -> human accept/override. Evidence is best-case demos. Curator qualifications: Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. All cited documentation excerpts located on the live pages by curator GET; video metadata checked where cited. Creator video (auto-caption transcript excerpts read by discovery; promotional/affiliate); not curator-verified beyond video metadata. Limitations: Creator statements were read by discovery from auto-captions (ASR); not re-verified by the curator. Sponsored; outputs and generated games not inspected; agent internals unknown. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
  "citations": [
    {
      "url": "https://www.youtube.com/watch?v=YMy-doCdV5Q",
      "note": "~1:00; ~2:40; ~1:40"
    },
    {
      "url": "https://www.youtube.com/watch?v=ZYQEwD1DhfA",
      "note": "~1:00; ~2:40; ~1:40"
    },
    {
      "url": "https://www.youtube.com/watch?v=Sptq99IgWnM",
      "note": "~1:00; ~2:40; ~1:40"
    }
  ]
}

Evidence claims

  • [sourced_fact] Six sponsored Mikkel Lassalle videos (Apr-Jun 2026) show four agent styles. Artlist AI agent: describe a goal in plain language, it picks a model (e.g. suggests 4K-capable models when asked), generates, and proposes next-step edits (moonlight, deeper shadow contrast, anamorphic flare) that you accept or override; same chat then animates a 5 s clip. Flova: "skills" (script-driven, story-driven, reference video, remix, music video, product commercial) wrap a pipeline; his manual path was Nano Banana Pro frame with "use the reference as the absolute identity source" -> GPT Image 2 character sheet -> Seedance 2.0 with both references, 15 s. Lovart: one prompt yields a brand package (posters, landing page, carousel, commercial); a "multi-angles" virtual camera orbits a product image to make extra angles that are stitched into a spot; "touch-edit" lets you click exact spots on several posters to place brand text in one instruction. Combos.fun: a game agent asks clarifying questions (enemy types, difficulty, style, mechanics) before generating a playable browser game, fixes bugs and adds sound on request, and publishes. Common pattern for tool builders: clarify -> generate -> suggest refinements -> human accept/override. Evidence is best-case demos. · locator: ~1:00; ~2:40; ~1:40 source

Rights

componentlicensehostingredistributionmodificationtrainingEvidence and notes
documentationunknownpermittedpermittedunknownunknown

Applies to this original summary only, not to the cited sources.

Linked records

Machine-readable: JSON · Markdown · revisions · changes