back_office_ops · workflow
GenV: agentic workflow for extracting structured insights from Google Meet recordings using Vertex AI Gemini
Crucial details from video meetings get lost after calls end; manually scrubbing through recordings to find decisions, action items, and context is tedious and inefficient, and generic note-taking apps are insufficient.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Locate recent recordings
The agent mounts Google Drive and identifies video files modified within a configurable recent period.
Tools used
GenVGoogle ColabGoogle Cloud StorageVertex AI APIVertex AI's Gemini models
Outcome
GenV automates structured knowledge extraction from meeting recordings, providing rapid summarization, action item capture, decision tracking, and knowledge retrieval while saving significant time compared to manual review.
Results
Time savedsignificant time
Grounding & classification
Source type: technical build writeup
18 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowdata extractionsummarizationmeeting recordingbuilder submittedtools describedworkflow describedemployee productivitytime savedtechnical build writeupback office opsmeeting to artifacts