Automate restaurant support with text and voice replies
They used Make.com to route customer messages for a restaurant chatbot that responds in both text and voice note form.
- What they did
- They put together a Make.com scenario to act as the message-handling layer for the restaurant’s support bot. Lovable was used to build the chatbot, while the Make workflow received customer input, turned voice notes into text, and sent back replies.
- How it went
- The system now supports two-way responses through Make.com, covering both typed messages and voice notes. No issues were reported beyond that setup.
- Tips
- Keep human oversight for anything involving money, disputes, or special cases. It also helps to test the voice-note path separately from the text path so you can catch transcription problems early.
Try it yourself with Make
Build a Make.com automation for [restaurant name] that connects to a chat assistant on [channel]. Take incoming written messages and audio notes, transcribe the audio, and use [source document] to reply about [menu, hours, location, reservations]. If someone asks about orders, refunds, complaints, or another issue outside those topics, stop and send it to me instead of answering. Pause before any reply goes out so I can approve the draft. It’s ready when trial messages in both formats get the correct response.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Schedule social posts from a sheet and mark them done
A Make scenario pulled images from Drive and posted them to Instagram and Pinterest on schedule from rows in Google Sheets.
Use agents to brief calls and plan YouTube ideas
She used Lindy to research discovery meetings and brainstorm YouTube content, while a more complex content process stayed in Make.
Screen leads and draft emails with human sign-off
They used n8n to clean incoming leads, score them, prepare outreach, and hold each message until a person okayed it.
Automate ticket triage and reply drafts
A Claude Code skill tied together support, billing, and database tools to sort tickets and prepare reply drafts for review.
Set up Lindy agents for support, calls, and content
A solo founder used Lindy to build support, calling, repurposing, and negotiation agents for small teams and niche businesses.
Let a voice agent handle service calls and owner updates
A call-answering agent for home-service companies logs key details and sends the owner a text recap.