This release features two major capabilities: "Create SOP from file" and "Specify reference SOP in video analysis (Beta)". Many customers currently manage SOP assets in Excel. We've streamlined the process to leverage your existing spreadsheets directly within Dive's video SOP platform. We've also added QR codes to output files, improved mobile and tablet layouts, enhanced viewing records and usage reports, and more.
Create SOP from file (Excel / Word / PowerPoint support)
"Create SOP from file" previously supported PDF only. Now we support Excel (.xlsx / .xlsm / .xls) / Word (.docx / .doc) / PowerPoint (.pptx / .ppt) as well. You can upload existing Excel manuals, work standards, checklists, and more, and have AI automatically convert them into SOPs.
- Most customers currently manage SOPs in Excel. The goal is to leverage your existing assets directly in Dive without having to re-film videos or rewrite manuals.
- When you upload, the system converts to PDF, and AI automatically generates the title, summary, and steps (including survey questions and pass/fail checks).
- AI processing Options let you fine-tune the import method (body mode: formatted summary or verbatim transcript), step split method (per content or per page), tone (directive, polite, persuasive, or follow policy), and conversion mode (follow print settings, fit width to 1 page, or 1 sheet = 1 page).
- After import, you can edit, share, and export seamlessly using the same editor as video SOPs.
For details, see Create SOP from file (Excel / Word / PowerPoint support).
Specify reference SOP in video analysis (Beta)
Building on the above, you can now specify reference materials (existing SOPs or files in PDF / Excel / Word / image format) during video analysis. This addresses needs like creating a video manual based on an existing Excel SOP or reusing terminology and structure you've already established.
- "Split video by reference sections (strict matching)" checkbox ON: Steps are divided to match the step count and order in the reference file. Title and body text are taken directly from the reference material, with information extracted from the video appended to the body (existing work procedure SOP as the base, video manual as the refinement).
- "Checkbox OFF (default)": The reference file serves only as supplementary material for terminology and context. Steps are divided automatically from the video.
- Beta in progress: We're still refining split accuracy and how content is captured. Please send feedback on what works and what doesn't to customer-success@episotech.com.
For details, see Specify reference SOP in video analysis (Beta).
Photo capture in survey responses
You can now take photos as evidence when answering survey questions. Use this during inspections, patrols, and checklist operations when you need to capture proof on the spot. Photos are linked to viewing records and can be reviewed and exported later.
QR codes in PDF and PowerPoint exports
PDF and PowerPoint exports of SOPs now embed QR codes for each step. After distributing your SOP on paper or slides, team members can scan the QR code to jump directly to Dive's playback screen with video. Use this to bridge print and digital workflows.
Other improvements and bug fixes
- Mobile and tablet layout overhaul: We've redesigned button placement and scroll behavior on narrow-width devices across key screens (SOP playback, editor, AI Options, etc.). We've also unified the approach for portrait tablets — treating them as large phones — making behavior more predictable.
- SOP playback: player font size is now adjustable: Viewers can adjust playback screen text size individually, making it easier to read SOPs on mobile, tablets, and small devices with a comfortable font size.
- Text retained after video cuts: When you cut a video, the text associated with that section (step text, title, captions, etc.) is no longer lost. Instead, it carries over to other steps. You no longer have to rewrite text after cutting.
- Viewing records and usage reports refinement: We've improved the display of viewing record details and list tables (filter, sort, photo answer preview, card view for mobile). We've also improved how individual usage reports are presented.
- User management: simplified remaining seat display: The user management screen summary for permission buckets (owner through viewer permission slots / guest permission slots) is now simpler, showing remaining seat counts at a glance. For details on permission buckets, see User roles and account count.
- AI processing count bug fix: We've fixed a bug where AI processing counts were sometimes overcounted.
- Terminology Glossary page performance improved: We've improved page display and editing performance for teams with large glossaries.
- Fixed: video description input disappears: We've fixed a bug where text entered in the "Video description" field under AI processing Options was sometimes unexpectedly truncated.
- Captions and read-aloud settings modal reorganized: In both file-based and video-based creation workflows, we've reorganized the layout of caption, read-aloud, and survey mode settings.