Coze
Official siteLow-code agent workflow platform for fast automation delivery.
OpenBack to template library
Sora Video Safety Monitoring Workflow
OperationsCozeUpdated 2026-03-24
Monitor the safety of videos generated by Sora, automatically detect violations, and trigger incident reports when thresholds are exceeded.
System Prompt
Evaluate the safety of the video at {video_input_path} using the {model_name} model. Compare the safety score to {safety_threshold}. If the score exceeds the threshold, generate an incident report and send it to {incident_report_channel}. Output the safety report to {safety_report_path}.Variable Dictionary (fill in your AI tool)
This section only explains placeholders. It is not an input form on this website. Copy the prompt, then replace variables in Coze / Dify / ChatGPT.
{model_name}Name of the video generation model, e.g., Sora-2
Filling hint: replace this with your real business context.
{video_input_path}Path to the video to be evaluated
Filling hint: replace this with your real business context.
{safety_threshold}Safety score threshold, range 0-1
Filling hint: replace this with your real business context.
{incident_report_channel}Channel to send incident reports, e.g., Slack channel or email address
Filling hint: replace this with your real business context.
{safety_report_path}Path to save the safety report
Filling hint: replace this with your real business context.
Quick Variable Filler (Optional)
Fill variables below to generate a ready-to-run prompt in your browser.
{model_name}Name of the video generation model, e.g., Sora-2
{video_input_path}Path to the video to be evaluated
{safety_threshold}Safety score threshold, range 0-1
{incident_report_channel}Channel to send incident reports, e.g., Slack channel or email address
{safety_report_path}Path to save the safety report
Generated Prompt Preview
Missing: 5
Evaluate the safety of the video at {video_input_path} using the {model_name} model. Compare the safety score to {safety_threshold}. If the score exceeds the threshold, generate an incident report and send it to {incident_report_channel}. Output the safety report to {safety_report_path}.How to Use This Template
Best for
Teams that need faster operations output with more stable prompt quality.
Problem it solves
Reduces blank-page time, missing constraints, and inconsistent output structure from ad-hoc prompting.
Steps
- Copy the template prompt.
- Paste it into your AI tool (Coze / Dify / ChatGPT).
- Replace placeholder variables using the dictionary above.
- Run and refine constraints based on output quality.
Not ideal when
You need live web retrieval, database writes, or multi-step tool orchestration. Use full workflow automation for that.
Success Case
Input:
video_input_path: videos/sample.mp4, safety_threshold: 0.7, model_name: Sora-2
Output:
Safety Report: Score 0.85, Status: Violation detected. Incident reported to #safety-channel.
Boundary Case
Input:
video_input_path: videos/invalid.mp4, safety_threshold: 0.7, model_name: Sora-2
Fix:
Ensure the video is in MP4 format and not corrupted.
What to Try Next
Keep exploring with similar templates and matching tools.
Continue Where You Left Off
No recent items yet.
Workflow Steps
Step 1: Load the video file
Step 2: Run safety evaluation with {model_name}
Step 3: Compare safety score to {safety_threshold}
Step 4: If score exceeds threshold, generate incident report and send to {incident_report_channel}
Step 5: Save safety report to {safety_report_path}
Constraints
- Video duration exceeds 10 minutes
- Resolution exceeds 4K
- Safety threshold less than 0 or greater than 1
Explore More in This Category
Operations
Similar Templates
Recommended Stack
Tools that work well with this template.