When creating an SOP from a video or file, you can specify how the AI should analyze it using "Analysis options." You can create an SOP by pressing "Run" with the default settings. This article explains what each setting changes and how to choose.
Analysis options are available on all plans. The number of times you can run AI analysis varies by plan.
Opening Analysis options
Any of the following actions will open the same screen.
- It displays automatically when uploading a video or file
- For materials that have not been analyzed, open it from "Run AI processing" in the material details modal (Running AI analysis on unanalyzed video materials)
- To redo analyzed materials, open it from "Check AI analysis results" and then "Re-run AI" (How to re-run failed AI processing)
The screen is divided into three sections: "Video description," "Analysis options," and "Advanced settings." You'll normally adjust the first two; "Advanced settings" can be left at the default.
Video description
This field tells the AI what work the video shows. Describing the target equipment, work purpose, tools used, and similar details improves analysis accuracy.
You only need to write information specific to that video. Common prerequisites like in-house terminology and equipment names can be registered once in the "Terminology Glossary" and will be reflected in AI analysis without entering them each time.
You can also insert saved templates from the icon in the top right of the field.
Analysis options
Split granularity
Specifies how finely to break the video into steps.
| Choice | Division unit |
|---|---|
| Phase | Divides into large units like setup, execution, and cleanup |
| Step | Divides into standard work step units. Recommended when issuing as an SOP |
| Action | Divides finely at the individual action level, such as button presses and tool use |
| Single | Does not divide; treats the entire video as one step |
The default is "Step." Choose "Single" when you want to use the video as one edited cut video without dividing into steps (How to create one edited cut video without step division).
Text style
Specifies the ending and phrasing of step text.
| Choice | Content |
|---|---|
| Command | Plain form and imperative. Standard for SOPs |
| Polite | Polite language. For new employee training or SOPs submitted to business partners or auditors |
| Invitation | Soft, suggestive tone. For education and training |
The default is "Command." If you have registered a "Procedure Authoring Policy," "Follow policy" becomes an option and is the default.
Subtitle style
Specifies the ending and phrasing of action subtitles displayed in the video. This is set separately from step text, and the choices are the same three types as text style plus "Match text." The default is "Command."
If you choose "Match text," it will align with the step text's style. However, when text style is set to "Follow policy," you cannot choose "Match text," so select a subtitle style individually.
Videos without narration (analyzed only by video)
When checked, audio is ignored and only video is analyzed. Step division and descriptions of actions are generated as before, but transcription of speech is not generated.
Use this for videos without narration, videos with only background music or machine sounds, or videos with unclear speech. It's also effective when re-running a video that failed AI analysis due to audio issues.
Advanced settings
Target step count
Specifies a target for the number of steps. The default is "Auto," where AI judges the fineness according to split granularity.
| Choice | Content |
|---|---|
| Auto | AI judges based on split granularity (default) |
| Specify step count | Specifies approximately how many steps to divide the entire video into |
| Specify seconds | Specifies approximately how many seconds per step |
Even if specified, how steps are divided (breaking at natural boundaries of the work) does not change. The target only affects the number of steps. Also, it is a target—it does not guarantee that exact number.
When split granularity is set to "Single," it does not display because it conflicts with treating the entire video as one step. When aligning with material divisions using "Reference SOP," the material's step count takes priority and this is not used.
Recognition Language
The language of the speaker in the video. Setting it correctly improves transcription accuracy. Languages not in the list can be entered directly in the input field to search.
Aggressively cut sections without speech
This setting broadly excludes sections with no narration from the created SOP. The default is OFF.
Even when OFF, obvious unnecessary parts like filler words and long silences are conservatively cut, but natural pauses during work are kept. When ON, work videos with long silent stretches may have the actual work cut out, so the default is OFF.
Turn this ON for videos where narration is continuous (lectures or explanations) or when you want to tighten up overly drawn-out sections. Cut sections can be restored in the video editor.
If "Videos without narration (analyzed only by video)" is checked, this setting is unavailable because there is no narration by definition.
Reference SOP (beta)
Specify one existing SOP file (PDF, Excel, Word, or image) and the video will be divided to match that material's structure, step count, and order. Use this to carry over the structure and terminology of an existing SOP to a video manual.
When specified, split granularity and target step count are not used. For details, see Specifying a reference SOP in video analysis (beta).
When to use split granularity vs. target step count
| What you want to do | Settings |
|---|---|
| Create an SOP and let AI decide | Split granularity = Step, Target step count = Auto |
| Want finer or coarser divisions | Change split granularity to Action or Phase |
| Want to match step count | Specify step count or seconds in target step count |
| Want to match an existing SOP structure | Specify a reference SOP |
| Don't want to divide into steps | Split granularity = Single |
Creating an SOP from a file
When creating an SOP from a file (PDF, Excel, Word, or PowerPoint), the settings differ from video. Split granularity, subtitle style, target step count, and reference SOP are not displayed.
| Setting | Content |
|---|---|
| Conversion method | Page settings for Office files. Choose from "1 sheet = 1 page," "Fit width to 1 page," or "Print settings." "Print settings" is recommended if the original file's print settings are properly configured |
| Step split method | How many steps to create from one page. "Per content" splits tables and bullet lists within a page into separate steps. "Per page" makes one page one step. In either case, one step stays within one page and does not span pages |
| Body writing style | "Format" reads the content and organizes it into work content, tips, cautions, and safety. "Transcribe" transcribes the original wording as-is. Use "Transcribe" for materials prioritizing the original text, like regulations and checklists |
For details, see Creating an SOP from a file (Excel, Word, PowerPoint supported).
Settings memory
Your specified settings are saved and become the defaults the next time you open this options screen. When you "Re-run AI" on analyzed materials, the conditions from the previous analysis of that material (such as reference SOP and target step count) are restored.
You can check which conditions were used to analyze a material from that material's "Check AI analysis results."
Frequently asked questions
Q. How long does analysis take?
A. Approximately as long as the video itself (a 10-minute video takes about 10 minutes). Analysis continues even if you close the app, and you'll receive an email notification when complete. You can analyze up to 1 hour of video per submission.
Q. Is there a setting to not generate subtitles?
A. No. Subtitles are always generated. If you don't want speech transcription, check "Videos without narration (analyzed only by video)."
Q. Can I change options and analyze again?
A. Yes. From "Check AI analysis results," you can select "Re-run AI," change options, and analyze again. The previous results will be overwritten.
Q. The step divisions don't match what I expected.
A. First, change split granularity and re-analyze. If you want to match a specific count, specify the target step count. To match an existing SOP structure, specify a reference SOP. If that still doesn't work, you can manually edit steps in the video editor.
Related information
- Step 1: Upload your video
- Running AI analysis on unanalyzed video materials (apply AI processing later)
- Specifying a reference SOP in video analysis (beta)
- Defining a Procedure Authoring Policy (reflect your organization's phrasing and standards in AI)
- Terminology Glossary (terms and multilingual translations)
- Unifying notation variations (Notation Unification Dictionary)
- How to re-run failed AI processing