> For the complete documentation index, see [llms.txt](https://connectyai.gitbook.io/documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://connectyai.gitbook.io/documentation/usage-guides-enterprise-plan/chat-features/ask-a-question.md).

# Ask a Question

The Ask a question feature is the primary entry point for interacting with structured data in natural language via Connecty AI. This functionality allows users to pose questions related to their databases and receive context-aware answers, generated through multi-layer reasoning.

### Prerequisites

Before asking a question, ensure the following prerequisites are met:

### **Select a Workspace**

A data source must be connected and authorized. This determines the scope of available tables, columns, and metrics

{% hint style="info" %}
Clck on "**+**" icon to start a new chat thread.
{% endhint %}

<figure><img src="https://4247993803-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FMVGgoc4urxfCJy9iAJG7%2Fuploads%2FdPMNwhZo0ystSK70EfxT%2Fimage.png?alt=media&amp;token=537e6604-cee1-43bd-a1c5-5a7f06c4372f" alt=""><figcaption></figcaption></figure>

### Select agent with '/' (Optional)

Chat offers Analyze, Discover, and Transform agents. Type a backslash (‘/’) and select the relevant agent. If no agent is specified, the Analyze agent is selected by default.

{% hint style="info" %}
Analyze agent is included in Team and Enterprise plan tiers. Discover and Transform agents are available in the Custom plan tier.
{% endhint %}

<figure><img src="https://4247993803-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FMVGgoc4urxfCJy9iAJG7%2Fuploads%2Fm0DNpMkGz2AbpVfAn1mm%2Fimage.png?alt=media&amp;token=a6ab86b7-c1ee-473f-af2f-881804c0f854" alt=""><figcaption></figcaption></figure>

### Tag users in a shared conversation with '@' (Optional)

<figure><img src="https://4247993803-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FMVGgoc4urxfCJy9iAJG7%2Fuploads%2Fblf95TDxFfe0ogBcmAnt%2Fimage.png?alt=media&amp;token=1d8351ae-41bb-457d-8459-f84e0ea3342e" alt=""><figcaption></figcaption></figure>

### Select 'Verified' knowledge (Optional)

If a user wants to restrict the chat knowledge source to the [Verified Knowledge](/documentation/usage-guides-enterprise-plan/chat-features/verified-knowledge.md) by Workspace moderator, they should select the **Verified** button..

<figure><img src="https://4247993803-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FMVGgoc4urxfCJy9iAJG7%2Fuploads%2FZI1gCEqw8767HneGByyg%2Fimage.png?alt=media&amp;token=9ae315b8-0e1b-42bd-a4fb-d7a6e9e6c3fd" alt=""><figcaption></figcaption></figure>

### How to Formulate Questions Correctly

Formulating clear and meaningful questions increases the accuracy and value of the AI-generated output.

### Best Practices<br>

* **Be specific**: Use concrete business terms (e.g., revenue, orders, regions, last month)
* **One objective per question** — e.g., “Show average cart size by day”
* **Use natural language**: Don’t write SQL — say what you need in plain English
* **Specify filters**: Add timeframes, segments, or regions to narrow scope
* **Use known metrics/dimensions**: Ensure the term exists in your connected catalog

### **Question Types for 'Analyze' agent (Do's and Don'ts)**

| Supported Question Types                                                                                                                     | Unsupported Question Types                                                                                                                |
| -------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| <p>✅ <strong>Metric Lookups</strong></p><p>“What is the total revenue in Q1 2024?”</p>                                                       | <p>❌ <strong>External KPIs</strong> (not in your database)</p><p>“How much is the GDP of the USA?”</p>                                    |
| <p>✅ <strong>Time-Based Aggregations</strong></p><p>“Show sales by month this year”</p>                                                      | <p>❌ <strong>Real-Time World Data</strong></p><p>“What’s the weather like today?”</p>                                                     |
| <p>✅ <strong>Top/Bottom Filters</strong></p><p>“Show top 10 products by revenue”</p>                                                         | <p>❌ <strong>Industry Benchmarks</strong></p><p>“How does my sales compare to the industry average?” (unless stored in your own data)</p> |
| <p>✅ <strong>Comparisons</strong></p><p>“Compare revenue this year vs last year”</p>                                                         | <p>❌ <strong>Access Limitations / System Questions</strong></p><p>“Why aren’t you giving me access to external data?”</p>                 |
| <p>✅ <strong>Anomaly or Trend Detection</strong></p><p>“Identify top 3 churn spikes in 2023”</p>                                             | <p>❌ <strong>Social Prompts</strong></p><p>“How are you today, Connecty AI?”</p>                                                          |
| <p>✅ <strong>Customer Segmentation</strong></p><p>“List high-value customers by region”</p>                                                  | <p>❌ <strong>Live Market Data</strong></p><p>“Tell me the price of Tesla stock”</p>                                                       |
| <p>✅ <strong>Funnel/Drop-off Analysis</strong></p><p>“What is the drop off rate in the onboarding funnel from trial to conversion page?”</p> | <p>❌ <strong>UI Troubleshooting</strong></p><p>“Why is this question not working?”</p>                                                    |
| <p>✅ <strong>Drilldowns</strong></p><p>“Break down revenue by campaign grouped by region”</p>                                                | <p>❌ <strong>General Business Advice</strong></p><p>“Can you help me write a business plan?”</p>                                          |
| <p>✅ <strong>Metric Definitions</strong></p><p>“What is Customer Lifetime Value?”</p>                                                        | <p>❌ <strong>Cross-Workspace Data Access</strong></p><p>“Give me data from another data workspace”</p>                                    |
| <p>✅ <strong>Filters</strong></p><p>“Only show customers from Germany”</p>                                                                   | <p>❌ <strong>Sentiment/Opinion Analysis</strong> (outside DB)</p><p>“What do people think of our pricing model?”</p>                      |

**More examples from** [**TPCH**](https://docs.snowflake.com/en/user-guide/sample-data-tpch) **dataset**

<table data-header-hidden><thead><tr><th width="168.66656494140625"></th><th></th></tr></thead><tbody><tr><td><strong>Topic</strong></td><td><strong>Metric Question</strong></td></tr><tr><td>Supplier analytics</td><td>Average fulfillment time by supplier and customer nation for parts from Asia region suppliers grouped by part type</td></tr><tr><td>Supplier analytics</td><td>Gross margin per part category from suppliers who shipped parts with discount over 5%</td></tr><tr><td>Supplier analytics</td><td>Late shipment rate by supplier region and part size category grouped by nation and year</td></tr><tr><td>Supplier analytics</td><td>Total number of parts supplied by high-value-order suppliers segmented by part brand</td></tr><tr><td>Supplier analytics</td><td>Profit margin from parts supplied by top 10 European suppliers segmented by customer segment</td></tr><tr><td>Customer analytics</td><td>Average order value per part category for 'Automotive' segment customers ordering from European suppliers</td></tr><tr><td>Customer analytics</td><td>Total profit per supplier from orders by customers who only ordered in the last 3 years</td></tr><tr><td>Customer analytics</td><td>Average order value by part type for delayed shipments to Asian customers ordering German parts</td></tr><tr><td>Customer analytics</td><td>Number of unique suppliers per customer segment in orders containing discounted parts</td></tr><tr><td>Customer analytics</td><td>Customer lifetime discount amount grouped by region</td></tr><tr><td>Order analytics</td><td>Average line item count per part category in orders from 1995 with Japanese suppliers and European customers</td></tr><tr><td>Order analytics</td><td>Total discount amount by supplier nation for orders over $20,000 with average line item count analysis</td></tr><tr><td>Order analytics</td><td>Average part cost grouped by region in multi-supplier orders with at least 3 suppliers and higher cancellation rates</td></tr><tr><td>Order analytics</td><td>Supplier count per order for fast-shipped orders (under 10 days) containing at least 5 distinct parts with average part cost analysis</td></tr><tr><td>Order analytics</td><td>Gross margin segmented by part brand for orders with line items sourced from multiple regions</td></tr><tr><td>First/last order analytics</td><td>Total number of suppliers engaged by customers active for over 5 years and their first-to-last order time gap</td></tr><tr><td>First/last order analytics</td><td>Average line item discount in first orders per customer segment by supplier region</td></tr><tr><td>First/last order analytics</td><td>Total part cost grouped by part category in last orders for customers with decreasing order frequency and high discount rates</td></tr><tr><td>First/last order analytics</td><td>Difference in gross margin and order value between first and last orders per supplier segmented by customer segment</td></tr><tr><td>First/last order analytics</td><td>Average part discount grouped by part type in first orders from new suppliers in each region</td></tr></tbody></table>

{% hint style="info" %}
Avoid vague requests like “Tell me about my business performance”
{% endhint %}
