# General Commercial Agent with Base row DB and Email Tool

### <mark style="background-color:yellow;">1. Overview</mark>

The General Commercial Agent (GCA) is designed to support commercial, sales, and business development operations. It acts as a digital assistant that can capture leads, manage prospects, follow up via email, maintain structured data in Base row DB, and automate routine commercial workflows.

We are creating an ASUS Commercial Agent which handles all the product specifications, deals, retails prices, no. of units left etc. and give the exact product details to the users. Agent also sends an email to the user with all product details.

### **2.&#x20;**<mark style="background-color:yellow;">**Business Value Proposition**</mark>

#### 1. Accelerated Sales Cycles&#x20;

* Instant lead capture and automated follow-ups reduce response time
* Faster movement from inquiry to quotation

**Business impact:** Shorter deal closure time

#### 2. Improved Partner & Reseller Experience&#x20;

* Timely responses to partner inquiries
* Reduced dependency on manual follow-ups

**Business impact:** Stronger partner trust and loyalty

#### 3. Higher Lead Conversion Rates&#x20;

* No lead loss due to missed follow-ups
* Clear visibility of deal status

**Business impact:** More qualified opportunities entering the pipeline

#### **4. Operational Efficiency & Cost Savings**&#x20;

* Automates repetitive sales admin tasks (CRM updates, emails)
* Reduces manual data entry
* Sales teams focus on high-value activities (closing, negotiations)

**Business impact:** Lower operational cost per deal

### <mark style="background-color:yellow;">**3. Step-by-step Process**</mark>

### **A. AI Agent Creation**

| Steps                 | Instructions                                                                                                                                                                                                                                         |
| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Step 1                | User opens Soika Mockingjay platform with Login ID and Password                                                                                                                                                                                      |
| Step 2                | <p>Ask Soika to Create an AI Agent based on the use case with Natural Language Prompt </p><p>Example : “Create an General Agent. The name of the agent is ASUS Commercial Agent which contains all the product details and send email to users.”</p> |
| <p> </p><p>Step 3</p> | <p> The Agent is created in the left panel : ASUS Commercial Agent</p><p>Choose your LLM Model from the Agent in <strong>Edit AI-> AI Model-> gpt-4o-mini</strong></p>                                                                               |

<figure><img src="/files/UZ0Ba15tKvG92fozRRSd" alt=""><figcaption><p>Creation of Agent</p></figcaption></figure>

<figure><img src="/files/y3PWAT0TCssWWKBd537q" alt=""><figcaption><p>Agent created with name and Agent ID</p></figcaption></figure>

<figure><img src="/files/4jke7mgscCbuCQaAWKyK" alt=""><figcaption></figcaption></figure>

### **B. Tool Integration (Email + Base row )**

| Steps  | Instructions                                                                                                           |
| ------ | ---------------------------------------------------------------------------------------------------------------------- |
| Step 4 | Connect the AI Agent with the Default Tools under the Edit AI -->Tools-->default Tools Section  -->  Email  Tools      |
| Step 5 | Connect the AI Agent with the Default Tools under the Edit AI -->Tools-->default Tools Section  -->  Base Row DB Tools |

<figure><img src="/files/PcaiAKfhkocMW0mUsEZE" alt=""><figcaption><p>General Functionalities of agent</p></figcaption></figure>

### **Connect Tools**

### **A. Email Tool**

&#x20;       Email: <https://developers.google.com/workspace/gmail/imap/imap-smtp>

&#x20;       Authorize using Gmail IMAP/SMTP (<https://myaccount.google.com/apppasswords>)

<figure><img src="/files/x4wvvOuKxvH39XYUPDuh" alt=""><figcaption><p>Click on Edit AI of the Commercial Agent to see the functionalities</p></figcaption></figure>

<figure><img src="/files/5hAn2ky1g0ib0wxGxHYf" alt=""><figcaption><p>Tools-> Default Tools->Email Tools</p></figcaption></figure>

<figure><img src="/files/l3GczUPOq86SDF2Fua7r" alt=""><figcaption><p>SMTP server and IMAP server /port details</p></figcaption></figure>

<figure><img src="/files/eADtT9EmXrxIN05QImfl" alt=""><figcaption><p>Email tool is authorized</p></figcaption></figure>

### **B. Base row DB**

* Create a Table  as mentioned below with the  API URL [Grid - Email\_Analyzer | Baserow](https://baserow.io/database/246855/table/585845/1090589)
* **Create a Table on the baserow\.io**:  <https://baserow.io/database/319560/table/746411/1436007>&#x20;
* **For Authorization in Soika Default Tools  Use API URL**: <https://api.baserow.io>

### **Example of Creation of ASUS Laptop details Table  in Base Row DB**

<figure><img src="/files/uQxDp1FlXNCWGpk4EOBn" alt=""><figcaption><p>Database created with Product Specifications. Table ID (746411) would be used in System Instructions</p></figcaption></figure>

<figure><img src="/files/5JlUkZu4vhUXxfXn0HnR" alt=""><figcaption><p>Edit AI-> Tools->Default Tools->Base row</p></figcaption></figure>

<figure><img src="/files/0dbSMUhPfMyALBq4FMHU" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/11vZA8gF9hGDaAD7eL8j" alt=""><figcaption><p>Base row DB is authorized</p></figcaption></figure>

#### **Enable & Manage Tools**

Go to `Tools → Default Tools` and enable:

* Email -   Enable the Function -Send Email
* Base row -Enable the Function-Get Rows
* Slack

| Steps                          | Instuctions                                                                                                                           |
| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------- |
| Step 6 :Enable and Mange Tools | <p></p><p>Once Authorized, Enabled the tools with the help of <strong>Tools-> Tools Manager - Default -Toggle the button</strong></p> |

<figure><img src="/files/nCBU423lXGuTZdcRVPbS" alt=""><figcaption><p>Enable the functions w.r.t Email and Base Row DB</p></figcaption></figure>

<figure><img src="/files/feY80ZuAljlGXfsuE4p4" alt=""><figcaption></figcaption></figure>

### Example of System Instructions

Based on the system instructions agent with perform the actions. Prompt generator will help you to provide the exact system instructions. You just have to mention the keywords in a step by step manner.

<figure><img src="/files/ME0sVkJaAEwhMgma2uC3" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/6EzYn0sV5glHlp1hRJvq" alt=""><figcaption></figcaption></figure>

Start with a Welcome message
\
Welcome to ASUS. How can I assist you today?

Step I : Once the agent receives the query, Ask the user for Name and Email ID.

Step II : Based on the query ,Agent will look into the base row DB database with Table Name ASUS Laptops and Table ID 746411.(**get the table ID from the database**)
\
Provide complete details to the user based on the user query.

Step III :Ask the user if user has any further queries ,if no further questions

Step IV :Ask user if they need all the details in the email. If yes, Send all the product details to user in user Email ID based on the user query.

#### Sending Emails to users

<figure><img src="/files/DjcCgYXrlYQrBLsGttna" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://soika-labs.gitbook.io/soika-mockingjay/use-cases/general-commercial-agent-with-base-row-db-and-email-tool.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.