AI Agents - Usecase on Extraction of Invoices Data from Gmail => Google Sheets

-

We all know about AI Agents and the benefits of them from the previous article in this blog: Click here. From this article, I am covering the sample AI Agent using a free site -> Relay This site is free for 30 days to create workflows for AI Agents. Their process is very easy to build the agent using GPT, Gemini, etc. models. The good part of this site is that they don't ask our API keys or configuration for any AI model selected. To work on this usecase, we only need our gmail id access credentials as prerequisite. Relay can take care of Google API calls internally to connect to Google sheets & Gmail Inbox.

Snapshot of the agent built in Relay:






























Here are the simple steps to create the agent using Relay:

1) Login/Signup into Relay.

2) Login into Google Sheets: Click here and create a simple sheet like below. This sheet is used to capture/store all the invoices data from Gmail later.







3) Create a instant trigger in Relay site by setting up the necessary configuration mentioned below. This step is basically looking for a Gmail with Sub: Invoice (or) Invoices and the body of the email with Invoice image pasted or Invoice file attached to the email.





















3) Extract the invoice data using GPT-4o-mini model and the data is same as in Step1.


 



















4) After finishing the extraction using GPT model, we need to add them to the sheet in row-by-row fashion. Here is the step to be defined from Relay.





















5) We need to make this agent execute (on) by clicking the radio button given in the Step3. 

6) Send an email to the Gmail with an invoice and allow the agent to pick the invoice to process all the above steps. Below is the snapshot with the attached invoice file.




















Here is the list of runs on the agent successfully:










Here is the final output after running the agent:















This is a very simple usecase to understand the AI agent functionality. I will cover another usecase in my next post and is not this simple :) :)

References:

1) https://google.com

2) https://relay.app

Popular posts from this blog

Connecting Claude to Pega Infinity 25.1.3 via MCP — Step-by-Step

-
Image
Enable AI-powered access to your Pega Investigative Case Management data directly from Claude prompts using the Model Context Protocol (MCP) and OAuth 2.0. What is MCP and why connect Pega to Claude? The Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude securely call tools and read data from external systems — all from a natural-language prompt. Think of it as a universal adapter between your enterprise systems and AI. Pega Infinity V25.1.3 ships with a first-class MCP service built on its existing REST framework. Once enabled, Claude can: Query and summarize investigative cases without switching apps Retrieve assignment details and case status on demand Trigger Pega workflows from conversational prompts Version requirement: This guide is based on Pega Infinity V25.1.3 (Community Edition) with the Rule-Service-MCP rule type. Earlier versions may not include native MCP support. Architecture overview The connection uses three layers: Claude as the AI c...
Read more

Build Pega Applications with GitHub Copilot CLI, Pega Infinity AI Plugin & MCP — Branch-Based Agentic Authoring

-
Image
To work on this experiment, we need the Github Copilot CLI, Pega Infinity Instance, and Pega Infinity AI Plugins ( https://github.com/pegasystems/infinity-ai-plugins ) . In my case, I have used the Pega Infinity V26.1 Community Edition and here is the Github repository to upload it in the Github Copilot plugin marketplace. For this entire exercise to work well, we need Java 17 or above.  Windows Command Prompt (Agent-Driven Terminal): Represents the Github Copilot CLI. It shows the active terminal execution where commands like pega-setup, list-skills, list-available-applications etc. MCP (Model Context Protocol) Orchestrator: Acts as the bridge and mediator between the AI terminal environment (GitHub Copilot) and the Pega platform. It translates natural language directives and agent commands into structured operations and API calls to manage application configurations. Here the name of the MCP server is pega--infinity-authoring Workflow Directives: Represents...
Read more

itextpdf API to generate PDF doc from an image file using Pega PE

-
Image
Probably some of the techies might have an idea on an opensource called " itextpdf " (earlier name is lowagie ) to convert an image file(png,jpeg,jpg,tiff,gif etc.) to a PDF file. It is very simple to use this API in Pega function to build the logic using java code. Moreover, this API comes in one single jar file and we need to import it in Pega before we start using it.  I see the conversion comes good in PDF file but not sure if any limitations of this API in terms of conversion is like formatting, font, images etc. So far so good and may be we can keep this API as one of our solutions while working on the requirements accordingly.  Heard that same API can be used to convert the text file to PDF but I didn't explore on it. Those who are interested to work on text -> PDF can take a look at the documentation. Don't hesitate to contact me offline for any further discussion in this context :) :) Prerequisites for doing this exercise: 1) itextpdf 5.4.0 jar file 2) Peg...
Read more