Back office

Google Workspace workflows for AI agents

An AI agent collects an enquiry and prepares details for your spreadsheet or email notification through a configured, approved connection.

Instagram

An Instagram enquiry joins the school spreadsheet

The AI agent collects the student's level, schedule and contact. A configured automation adds their expression of interest to Google Sheets, giving the school an organised list for follow-up.

Lingua school Instagram
  1. Customer

    I am interested in an evening German course for beginners.

  2. Telp

    The A1 group meets on Tuesdays and Thursdays at 7 pm. If that suits you, share your name and email for enrolment information.

  3. Customer

    That works. Ana Example, [email protected]. Please register my interest in that group.

  4. Telp

    Ana, enquiry K-803 is on the interest list for the A1 group at 7 pm. The school has your email for start dates and enrolment details.

Phone

Reception gets an email while the guest is still on the call

A guest calls about a late arrival and the AI agent collects the details. With a configured Gmail automation, it emails reception with the booking and arrival time.

Park Hotel Phone

Call transcript

  1. Customer

    We are running late and will arrive around midnight tonight. Please notify reception.

  2. Telp

    Please give the booking number, name, guest count and contact phone for arrival arrangements.

  3. Customer

    H-310, Peter Example, two people, +381 60 0000000. Please let them know we arrive around midnight.

  4. Telp

    Peter, reception has been emailed about H-310: two guests arriving around midnight tonight. Your phone number is included for check-in arrangements.

The customer context

An AI agent collects an enquiry and prepares details for your spreadsheet or email notification through a configured, approved connection.

Use Google Sheets, Gmail or controlled email delivery as a practical operational output for smaller teams.

What this workflow can cover

  • Map validated conversation fields to a defined payload
  • Send an approved notification or append a structured row
  • Keep the original conversation as the source of truth
  • Move to a stricter direct integration when complexity grows

Back office

How it works

  1. 1

    Define the exact columns or message template.

  2. 2

    Expose the destination through an approved tool or automation.

  3. 3

    Test validation, duplicate handling and unavailable-destination behavior.

What your team gets

Fast internal visibility

Less manual transcription

A traceable source conversation for each request

Telp

How your team keeps control

Credentials remain server-side

Secrets are not placed in prompts or customer-visible conversation text.

Every tool has a contract

Names, descriptions, fields and permission policy define what the agent may request.

Writes can require confirmation

The platform can prepare a structured draft and execute only after explicit approval.

FAQ

Frequently asked questions

Can an AI agent record a customer enquiry in Google Sheets?

Yes, through a configured spreadsheet connection. Define columns such as name, contact, service and deadline, then check that the entry reaches the correct row and spreadsheet.

Can sales receive an email with the conversation details?

Yes, through a connected internal notification action. You choose the recipient and required information; sending a notification is not the same as managing an entire customer email thread.

Does the agent get access to all our documents and messages?

No. This workflow is limited to the selected spreadsheet or notification action. Broader access is not implied just because the company uses Google Workspace.

What happens if a spreadsheet row is not created?

The agent must not claim that the entry is complete. The conversation remains available to your team in Telp, and the failed connected action can be reviewed before proceeding.

Want to validate this workflow with your own examples?

Tell us the channel, current process and first result you want to improve. We will suggest a focused rollout path and the cases your team should test.

View pricing