> ## Documentation Index
> Fetch the complete documentation index at: https://docs.videngineer.com/llms.txt
> Use this file to discover all available pages before exploring further.
# What it's selling
> The classification and comprehension layers: format, logline, premise, thesis — what kind of video this is and what it's actually doing.
This layer answers: **what kind of video is this, and what is it actually doing to the viewer?** It comes in two passes. *Classification* decides the format — before anything else interprets the video, because a 15-second ad and a 33-minute documentary must not get the same read. *Comprehension* then watches a storyboard sampled across the whole runtime and reads the video as a piece of communication: the idea it argues, the feeling it sells, the brand move it makes.
*Live example: [Coinbase — 'Break The Cycle' teardown](https://videngineer.com/teardowns/cinematic/coinbase-break-the-cycle-manifesto-teardown/) — the logline under the title.*
## Classification — the format call
| Field | What it holds |
| --------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `format` | One of: `b2b_ad`, `ugc_ad`, `long_form_doc`, `short_form_hook`, `explainer`, `kids`, `vlog`, `tutorial`, `cinematic`, `product_demo`, `news_commentary`, `other` |
| `format_confidence` / `format_evidence` | How sure the call is, and the one-sentence why |
| `matched_template` | Whether the structure matches a productized template: `pile_up_reveal` (chaos → hard cut → calm reveal → proof → CTA), `numbers_story`, `before_after`, `pov_native` — or `null` |
| `duration_band` | `micro` (under 15s) \| `short` (under 60s) \| `mid` (under 5min) \| `long` (under 20min) \| `extended` |
| `platform_native` | Best-guess home platforms — linkedin, tiktok, reels, shorts, youtube, ctv… |
| `intent` | `sell` \| `teach` \| `entertain` \| `inform` \| `inspire` |
| `primary_audience` / `language` / `is_ai_generated` | Who it's for, what language, and whether it reads as AI-generated |
The format decides which rubric the [Scorecard](/layers/scorecard) applies — that's why classification runs first.
## Comprehension — the meaning read
Metrics measure a video; comprehension *understands* it. A vision model watches 12 frames sampled evenly across the runtime — in order, as a storyboard — and can even overrule the metrics-only format guess (`format_correction`) when the frames tell a different story. It exists because metrics alone once filed a global brand manifesto as a travel documentary and saw its climactic logo reveal as "a frame".
| Field | What it holds |
| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `logline` | One vivid sentence: what this video *is* |
| `premise` | The situation or world it sets up |
| `thesis` | The single idea it argues, or the feeling it delivers |
| `selling` | What it actually sells — usually a feeling or idea, not a feature |
| `emotional_target` | The intended arc, e.g. "awe → belonging → pride" |
| `is_branded` / `brand` | Whether there's a brand, and the brand object: `name`, `appears_at_sec`, `screen_time_pct`, `reveal_technique` — how restrained the reveal is |
| `genre` / `sub_genre` | The real genre — brand\_film, manifesto, ad, doc, music\_video, explainer, ugc, narrative\_short… |
| `subjects` / `comparable_to` | Core themes, and 2–4 well-known reference campaigns it sits beside |
| `signature_technique` | The one move a director would carry into their own work |
| `director_notes` | Two or three sentences on how to rebuild the *feeling*, plus a list of 3–5 concrete, replicable techniques to reference — patterns, never content |
| `rebuild_caveats` | The gotchas — cost reality, skill required, what the metrics get wrong |
| `format_correction` | A better format call than classification's, when the frames disagree — otherwise `null` |
## What to do with it
* **Steer with the `thesis`, not the topic.** Two videos about the same product can argue opposite ideas; matching the thesis is what makes a reference actually comparable to your brief.
* **Study the `brand` object before your own brand placement.** `appears_at_sec` and `screen_time_pct` quantify restraint — high-performing brand films routinely hold the logo back for most of the runtime.
* **Use `comparable_to` to brief stakeholders.** "It's structured like \[known campaign]" lands faster in a review than any metric.
* **Trust `rebuild_caveats` on scope.** When the notes say the feeling costs real production, a cheap imitation of the surface won't inherit the performance.
## Related layers
The format-specific rubric this classification selects.
The skeleton delivering this thesis.
How the argument earns its first three seconds.
The people and world carrying the message.