# Un-answered Questions

The **Un-answered Questions** section helps you identify customer queries that your AI agent was **unable to answer correctly**. These questions are logged automatically and allow you to continuously improve your agent’s knowledge and accuracy.

This feature ensures your AI agent becomes smarter over time by learning from real user interactions.

***

### What are Un-answered Questions?

Un-answered Questions are customer messages where:

* The AI could not find a relevant answer
* The knowledge base lacked required information
* The agent returned an error or fallback response

These questions are stored so you can review, analyze, and add correct answers to your agent’s knowledge base.

***

### Why are Un-answered Questions Important?

They help you:

* Identify gaps in your knowledge base
* Improve AI response accuracy
* Understand real customer intent
* Reduce fallback or error responses
* Train your agent using real conversations

***

### Accessing Un-answered Questions

To view un-answered questions:

1. Log in to your **BotPenguin Dashboard**
2. Go to **Agents**
3. Select the desired **Agent**
4. Open **Agent Knowledge Base**
5. Click on the **Un-answered Questions** tab

You will see a list of questions that the AI agent could not answer.

***

### Un-answered Questions Screen Overview

#### 1. Search Bar

Use the search field to quickly find specific customer questions.

***

#### 2. Date Filter

Filter un-answered questions by selecting a **date range**.\
This helps analyze recent issues or review past performance.

***

#### 3. Download Option

You can **export un-answered questions** to analyze them offline or share with your team for review.

***

#### 4. Empty State Message

If no data is shown, it means:

* No unanswered questions have occurred during the selected period
* The agent is responding successfully to all queries

***

### How to Use Un-answered Questions Effectively

1. Review customer questions regularly
2. Identify repeated or common queries
3. Add missing information to:
   * FAQs
   * Website data
   * File uploads
   * Google Sheets
4. Test the agent after updates
5. Monitor reduction in unanswered queries over time

<figure><img src="/files/9AJbB4dFkD6WmFT6am7i" alt=""><figcaption></figcaption></figure>

### FAQs

<details>

<summary>When does a question appear here?</summary>

A question appears when the AI cannot confidently answer using the available knowledge base.

</details>

<details>

<summary>Does this affect live chat?</summary>

No. These logs are for analysis only and do not block live chat handoff.

</details>

<details>

<summary>Will adding answers remove past un-answered questions?</summary>

No. Past entries remain for reference, but future similar questions will be answered correctly.

</details>

<details>

<summary>Can I delete un-answered questions?</summary>

Currently, they are maintained for tracking and learning purposes.

</details>

<details>

<summary>Does this help improve AI accuracy?</summary>

Yes. Regularly addressing un-answered questions significantly improves agent performance.

</details>

### Need Help?

If your agent doesn’t show up after installation or you encounter code-related issues, contact us at [**support@botpenguin.com**](mailto:support@botpenguin.com) or reach out directly via the WhatsApp Support option. We typically respond within 48 business hours.


---

# 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://help.botpenguin.com/ai-agents/creating-ai-agents-in-botpenguin/training-your-ai-agent/un-answered-questions.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.