Log meals from Telegram and track nutrition

An n8n Telegram agent records meals from text, voice, or photos, estimates nutrition, and sends daily progress updates.

Done with n8nGemini· Intermediate

What they did
They built the workflow in n8n with Telegram as the entry point and Gemini for meal understanding. When a message came in, the agent checked whether the person was already set up; if not, it collected calorie and protein targets without saving weight or height. It then handled typed meals, voice messages after transcription, and food photos, adding estimated calories and macros to a Meals sheet while storing goals in a Profile sheet.
How it went
The setup is described as a template with those features, but there were no reported test results or accuracy numbers. The nutrition totals were guesses based on meal descriptions or images.
Tips
This needs Telegram bot access, Google Sheets, and Gemini or a compatible model, plus two sheets that match the template’s column structure. Ask the agent to stop before any irreversible action and wait for approval if you want it to do anything beyond logging and reporting.

Try it yourself with n8n

Set up an n8n workflow that connects a Telegram bot to Google Sheets and [Gemini or compatible model]. When I send a meal by text, voice note, or photo, estimate the calories and macros, then add the entry to a Meals sheet at [sheet link]. Keep my daily targets in a Profile sheet with [calorie target] and [protein target], and use them to calculate progress in a daily summary sent at [time]. Before you make any irreversible change, such as submitting, deleting, sending, or overwriting data, pause and ask me to approve it. Finish when [success condition, such as a test meal appears in the sheet and I receive the report in Telegram].

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on n8n.io ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.