Capture thoughts, bookmarks and research via text and voice
Web page · https://agentusecases.ai/use-case/capture-thoughts-bookmarks-and-research-via-text-and-voice
Done with n8n. A commenter describes an assistant that saves bookmarks, thoughts, wishlists and research from text and voice messages; another's WhatsApp-to-Notion flow failed at querying notes later.
First seen by Oriel on .
AI summary
The page describes a text-and-voice capture assistant whose simple WhatsApp-to-Notion pipeline worked for saving but required semantic retrieval to make stored notes reliably queryable.
- n8n handled message intake, audio transcription, tool calls, Notion writes, calendar checks, and scheduled reviews, while a smaller agent managed intent and search.
- Related messages, such as a voice note and URL, were buffered into one record before classification and storage.
- Plain-text Notion search failed to recall topic notes after two weeks, leading one commenter to abandon the workflow.
- The suggested solution was semantic retrieval using embeddings or a vector store, rather than relying only on Notion text search.
- Scheduling proactive messages was reportedly the hardest part and required three rewrites before the interaction felt natural.
#n8n #notion #semantic search #voice assistants
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Agent Use Cases | https://agentusecases.ai/use-case/capture-thoughts-bookmarks-and-research-via-text-and-voice | https://agentusecases.ai/use-case/capture-thoughts-bookmarks-and-research-via-text-and-voice Read discussion |