> For the complete documentation index, see [llms.txt](https://pmse.gitbook.io/pmse-dhdk/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://pmse.gitbook.io/pmse-dhdk/2.-software-requirement-specification/2.4-system-architecture/2.4.3-use-case.md).
# 2.4.3 Use Case
### General User request:
> We require a question-answering AI application to guide users through the user manual of the GIS software template for the Geoportale Nazionale per l'Archeologia (GNA) project. This manual is a vital resource for systematically and digitally cataloging and mapping Italian archaeological sites.
>
> The manual provides comprehensive details on the structure, features, and step-by-step instructions for completing individual fields in the GNA database. The AI system should address frequently asked questions, offering relevant and meaningful answers while referencing specific sections of the manual for deeper insights.
>
> This software solution would significantly improve the manual’s accessibility, clarity, and ease of use, empowering users to navigate the platform effectively and ensuring more accurate and consistent cataloging practices.
### **Use Case Name:** GNA AI-powered Chatbot Application for User Assistance
### Primary Actor
Users of the GNA platform, including government officials, researchers, archaeologists, and other stakeholders in the cultural heritage domain and Istituto Centrale per la Catalogazione (ICCD).
### Stakeholders and Interests
* **GNA Administrators**: Require the chatbot to reduce the workload on support teams and streamline user assistance.
* **Government Officials**: Need quick access to data and policies related to cultural heritage projects.
* **Researchers and Academics**: Seek detailed information on cultural heritage datasets, grants, and ongoing projects.
* **Developers and Technical Teams**: Require seamless integration of the chatbot into the existing GNA platform without disrupting current functionalities.
* **End-Users (General Public)**: Interested in basic inquiries about cultural heritage initiatives and funding opportunities.
***
### **Preconditions**
1. The GNA platform must be operational and accessible.
2. Users must have valid login credentials to access personalized features.
3. The chatbot must be fully integrated with the GNA platform and its databases.
4. Data sources and APIs must be functional to ensure accurate responses.
### **Postconditions**
1. The user receives accurate, context-specific information or assistance.
2. The chatbot logs the interaction for analysis and continuous improvement.
3. Any escalated issues are appropriately redirected to human support teams.
***
**Trigger****:** A user accesses the chatbot through the GNA platform to seek assistance.
### **Main Success Scenario**
1. A user logs into the GNA platform and initiates a chatbot interaction.
2. The chatbot greets the user and offers assistance with a menu of options (e.g., grant applications, cultural data queries, technical support).
3. The user selects a category, such as "Grant Applications."
4. The chatbot fetches relevant information using APIs and provides detailed responses (e.g., grant deadlines, eligibility criteria).
5. If the user's query is complex, the chatbot offers additional clarification options or escalates the issue to a human representative.
6. The chatbot ends the session after ensuring the user’s satisfaction.
#### **Extensions**
1. **Data Retrieval Failure**:
* If the chatbot fails to retrieve information, it informs the user of the issue and escalates the query to the technical team.
2. **User Provides Insufficient Information**:
* The chatbot prompts the user for additional details and provides examples of acceptable input formats.
3. **High User Traffic**:
* If the system is under heavy load, the chatbot informs users about expected response delays and offers a callback or follow-up option.
***
#### **Basic Flow**
This outlines the ideal sequence of interactions where everything functions as intended without errors or interruptions. It details the steps involved in the standard exchange between the user and the chatbot system. For instance, a user poses a question, and the chatbot responds promptly and accurately.
1. The user clicks the chatbot icon on the GNA platform.
2. The chatbot opens a conversational interface and greets the user.
3. The user types or selects a query related to the GNA user manual.
4. The chatbot processes the input using natural language processing (NLP) techniques.
5. The chatbot fetches relevant information and performs an action based on the user’s query.
6. The user receives the requested information or assistance.
#### **Alternative Flow**
This outlines deviations from the standard process, such as scenarios where users might interact with the chatbot differently (e.g., using voice input or asking questions in multiple languages) or when exceptions occur (e.g., system delays or ambiguous queries).
1. **Voice Interaction**:
* The user activates a voice interface to interact with the chatbot, which processes spoken queries and provides verbal or text responses.
2. **Multilingual Queries**:
* Users input queries in different languages, and the chatbot utilizes translation services to provide responses in the preferred language.
***
### Performance Metrics
* **Response Time**: The chatbot should respond to user queries within 2 seconds on average.
* **Accuracy**: The chatbot must achieve at least 90% accuracy in understanding and responding to user queries.
* **User Satisfaction**: Post-interaction surveys should indicate an 85% or higher satisfaction rate.
### **Potential Risks and Mitigation**
1. **Risk**: Users may provide ambiguous or vague queries.
* **Mitigation**: Implement fallback mechanisms and prompts to guide users.
2. **Risk**: Downtime in third-party services like Mistral AI.
* **Mitigation**: Develop backup solutions and maintain a local fallback model.
3. **Risk**: User resistance to adopting the chatbot.
* **Mitigation**: Offer training sessions and emphasize the benefits of the chatbot during onboarding.
---
# 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://pmse.gitbook.io/pmse-dhdk/2.-software-requirement-specification/2.4-system-architecture/2.4.3-use-case.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.