[Read on Dashport](https://dashport.ai/documentation/writing-effective-prompts)

Asking ChatWriting effective prompts

Copy page

[

Dashport Docsv2.0](/documentation)

Getting Started

IntroductionCreating your account5-minute quick start

Connecting Data

Supported integrationsConnect a databaseColumn comments & AI contextSuperSheets as a sourceCredential securityRefresh intervals

Using SuperSheets

What is SuperSheets?Creating a sheetData entry & column typesFormulas & calculationsFormatting & selectionSort, filter & columnsRow operationsValidation & frozen panesImport & exportSharing & activity logKeyboard shortcutsUse as a data source

Asking Chat

How Chat worksWriting effective promptsExample conversationsBuilding charts via ChatLimits & best practices

Building Dashboards

Three ways to buildDrag-and-drop builderAsk Chat to buildSharing & permissions

Asking ChatWriting effective prompts

Copy page

## Writing Effective Prompts[](#ch-prompts)

Chat is designed for natural language, but a few habits will get you better results faster:

### Be specific about data sources[](#ch-prompts-be-specific)

VAGUE"Show me revenue."

CLEAR"Show me monthly revenue from my PostgreSQL sales database for the last 6 months."

VAGUE"What's trending?"

CLEAR"Which product categories had the highest sales growth in Q4 compared to Q3 in my Shopify connection?"

VAGUE"Make a chart."

CLEAR"Create a line chart of daily active users from my analytics database and add it to the Growth dashboard."

### Use conversation context[](#ch-prompts-context)

Chat remembers previous messages in a session. You can build on earlier results without repeating yourself:

Copy

```
User:  "Show me revenue by region for Q4."
Chat:  [Returns table with 5 regions]

User:  "Now filter that to just Europe and add it as a bar chart on my Q4 dashboard."
Chat:  [Applies filter, creates chart, adds to dashboard]
```

Previous

How Chat works

Next

Example conversations
