> For the complete documentation index, see [llms.txt](https://mind-expression-docs.gitbook.io/home/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://mind-expression-docs.gitbook.io/home/concepts/subjects.md).
# Subjects
As real conversations always entail subjects to cover, Mind Expression enables human-like communication with Subjects. A Subject is what it matters to the customer consisting of Components and its associated actions as well as a response message. 3 types of Subjects help you achieve different session goals: Q\&A, Info Search, Query Freestyle.\
\
For each Subject, the conversation is built in full natural language text, such as "I have an internet problem." or "I want to check my payment history." Except for the Q\&A type Subjects, Components are required to define the conversational structures of the Subject.
### Subject types
**Q\&A Type**
The Q\&A Subject assists in providing a pre-defined answer to a question. It is suitable for simple Q\&As that consist of a pair of a question and an answer. It helps you answer questions a customer has or find specific information from your database. You can give pre-written answers or have a webhook to find an individual's personal data.
An example flow of the "Mind AI Q\&A" Subject would look like this.
* `The session starts with a query statement: "What is Mind AI?"`
* `Show response: "Mind AI is an AI startup headquartered in Seoul, South Korea."`
**Subject Building Process**
1. Define what is being searched for.
2. Lookup a pre-written answer or query system.
3. Show response.
### Info Search Type
The Info Search Subject assists in efficient information retrieval. It is suitable for advanced information search that requires further checking processes with the customer, system, or both. It helps you answer questions a customer has, or to find specific information from your database. You can give pre-written answers or have a webhook to find an individual's personal data.
An example flow of the "Data Usage" Subject would look like this.
* `The session starts with a query statement: "How much data have I used on my account?"`
* `Check with the customer: "For what month?"`
* `Show response: "For May: Voice 40 mins from total 300 mins, Data 3.2 GB from total 10 GB."`
**Subject Building Process**
1. Define what is being searched for.
2. Add Components.
3. Look up a pre-written answer or query system.
4. Show response.
### Query Freestyle Type
The Query Freestyle Subject helps you take care of customer queries that are more complex to process than simple information retrieval or Q\&A handling. It takes care of particular customer requests, it answers questions that a customer might have or finds specific information from your database. You can give pre-written answers or have a webhook to find an individual's personal data. An example flow of the "Change Plan Pack" Subject would look like this.
* `The session starts with a query statement: "I want to change my mobile plan package."`
* `Check with the customer: "Which package would you like to change to? 1. 5G Unlimited Data, 2. 5G Data 6GB, 3. 5G Data 4GB."`
* `Confirm with the customer: "This is the detail of the 5G Unlimited Data package. Features: 5G Nationwide, 4G LTE data, Perks: Disney+, Hulu, Apple Music for 3 months. Is it correct?"`
* `Show response: "Your package has been confirmed. Thank you."`
**Subject Building Process**
1. Define what is being searched for.
2. Add Components.
3. Look up a pre-written answer or query system.
4. Show response or confirm.
### Add Subjects
The inputs required to add a Subject are determined by the Subject types as they are supposed to accomplish different conversation goals.
### Q\&A, Info Search, Query Freestyle
* **Subject Name**
* **Query Statement**
An expected query from your customer
* **Additional Statement to Recognize (Optional)**
Statements which may be related to the original query statement or have the same response and can be used to trigger the subject.
### Manage Subjects
**Edit Subjects**
You can edit the Subject details. The details you can edit are determined by the Subject types as they are supposed to accomplish different conversation goals.
#### Delete Subjects
To delete a Subject, open the more actions menu and click **Delete**. Be aware that by deleting a Subject, all associated data will be permanently deleted and the action cannot be undone.
#### **Point Ontologies**
Additional Statements to Recognize
Point Ontologies are used as additional statements that can trigger the subject. The added points may or may not have the same meaning as the original query statement and are used to trigger the subject using statements that are still related to the subject's response.
### Closing
You can manage how the session will terminate.
### Restart
You can turn the restart closing message on and off at the Subject level. When the Restart toggle is on, the restart message will be displayed before terminating a session.
### Ending
You can turn the ending closing message on and off at the Subject level. When the Ending toggle is on, the ending message will be displayed in case of successful session termination.\
\
To learn more about how to customize closing messages, see [How-to Guides: Customize messages](/home/how-to-guides/customize-messages.md).
### Publish
Publish your Subject to deploy all Subject settings.
#### Publish Subjects
Click the Publish button located on the right side of the header to publish your Subject. If there is an error or a warning, the cases will be displayed with the reasons and the solutions.
#### Error and Warning Cases
When publishing the Subject, if there are any error or warning cases, the cases will stack up in Errors / Warnings.
* **Error Cases**
The Subject will not be published and it requires an immediate follow-up action.
* **Warning Cases**
The Subject will be published but a certain state will not be reached.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## 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, and the optional `goal` query parameter:
```
GET https://mind-expression-docs.gitbook.io/home/concepts/subjects.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.