Automated Runway Generation and Prompt Logging
Every night, WebRun opens Runway, walks the day's generations across your projects and folders, records the prompt, model settings, and asset link behind each one, posts the day's entries to Microsoft Teams, and pings Telegram with the count.
How do I keep a record of the prompts behind each AI generation?
WebRun opens Runway every night and walks the day's generations across your projects and folders. It records the prompt, the model settings, and the asset link behind each one, posts the entries grouped by project to Microsoft Teams, and pings the nightly count to Telegram.
- A look that worked months ago can be reproduced exactly
- Every asset carries the prompt and settings that made it
- Nothing is generated and no credits are spent by the run
Built for creative studios · video editors · AI artists · content teams
What does WebRun do on every run?
The exact actions WebRun takes, in order - in plain language, so you can adjust anything.
-
WebRun signs in and gets to work
Opens
app.runwayml.comin a real browser with your saved login - no setup, no API keys. -
1
Runway - read today's generations and prompts
runwayml.com
WebRun opens Runway to read today's generations and prompts. - Open Runway and list the generations created today across your projects and folders
- For each one, capture the prompt text, the model and settings used, and the asset link
- Note the project and folder so the entry can be found by the work it belonged to
- Skip generations already logged in an earlier run
Done when Every generation from today has its prompt, settings, and link captured.
-
2
Microsoft Teams - post the day's log entries
microsoft.com
WebRun opens Microsoft Teams to post the day's log entries. - Post the day's entries grouped by project, each with its prompt and settings
- Keep the prompt text in full so it can be copied and reused later
- Include the asset link beside each entry so the look and the recipe stay together
Done when The day's generation log is posted in Microsoft Teams.
-
3
Telegram - ping the nightly count
telegram.org
WebRun opens Telegram to ping the nightly count. - Send a one line ping with how many generations were logged and across which projects
- Call out any generation whose prompt could not be read so the gap is known
- Keep it internal to your team channel
Done when The team has tonight's count on Telegram.
How is each run configured?
Secure by default
Connect once, stays signed in
WebRun signs in once and keeps each session in a persistent environment, so every run picks up right where it left off.
Every action is checked against this policy before it runs.
Questions, answered
Will it start new generations or spend credits?
No. This run is read only inside Runway. It records generations that already exist with their prompts and settings, and never queues a render or spends a credit of its own.
Does it move or download the finished assets?
No. It logs the asset link alongside the prompt and settings, so the file stays where your team put it and the log stays a record of how each look was made.
Why keep the prompt and settings together?
Because a style that worked in March can then be reproduced in June without guessing. The log holds the prompt in full and the model settings beside the asset that came out of them.
Related templates
Put this on autopilot.
Turn it on in minutes - or have our team set it up for you.