A practical guide to getting the best results from your DataGalaxy-powered chatbot

What/Who is Blink?

Blink is a conversational assistant connected to your DataGalaxy catalog through MCP tools. It helps users:

• Find datasets, reports, glossaries, dashboards, tables, KPIs, and processes

• Understand business definitions and relationships

• Explore lineage and hierarchy

• Discover experts, owners, stewards, and governance roles

• Retrieve metadata and collaboration information

• Navigate the catalog using natural language

Blink has some limitations and cannot: 

- operate with all the custom attributes

- navigate via UI

- deal with administation of the platform

Blink works best when prompts are clear, contextual, and goal-oriented.

Core Principle

Treat Blink like a knowledgeable data colleague

Good prompts explain:

1. What you are looking for

2. Why you need it

3. Any business context

4. Expected output format

The more business context you provide, the better Blink can choose between:

• keyword search

• semantic search

• metadata exploration

• lineage retrieval

• governance discovery

Step 1. Start With Business Context

Weak Prompt

customer table

Better Prompt

Find datasets related to customer churn analysis for telecom subscribers.

Why?

• It includes a business topic

• It gives semantic meaning

• It helps Blink use semantic search effectively

Step 2. Use Natural Language, Not Technical Syntax

Blink is optimized for conversational requests.

Avoid

table:customer AND owner:finance

Prefer

Show me finance-owned customer reporting datasets.

Step 3. Be Explicit About the Object Type

If you know what you need, say it.

Examples:

• dataset

• dashboard

• KPI

• glossary term

• process

• report

• data source

Example

Find dashboards related to sales forecasting.

This reduces ambiguity and improves precision.

Step 4. Include Business Vocabulary

Blink understands business semantics better when prompts contain:

• department names

• project names

• business domains

• use cases

• metrics

• regulatory language

Good Examples

• “GDPR-sensitive customer information”

• “Supply chain forecasting KPIs”

• “Finance reconciliation process”

• “Marketing attribution dashboards”

Step 5. Ask for Relationships and Context

Blink can retrieve linked objects and hierarchy information.

Examples

Find dependencies

What objects are linked to the Customer Master dataset?

Explore hierarchy

Show the parent business domain of the Revenue KPI.

Understand lineage

What reports depend on the Sales Fact table?

Step 6. Ask Follow-Up Questions

Blink performs best in conversational workflows.

Example Conversation

Message 1

Find datasets related to customer retention.

Message 2

Which of these are owned by the marketing team?

Message 3

Show linked dashboards for the top 3 datasets.

Step 7. Specify the Desired Output

You can guide Blink toward concise or detailed responses.

Examples

Concise

Give me a short summary of the Payment Processing dataset.

Detailed

Provide complete metadata and linked objects for the Customer 360 dashboard.

Governance-focused

Who are the stewards and owners of critical finance datasets?

Step 8. Use Semantic Search for Concepts

Semantic search works best for:

• topics

• concepts

• business meaning

• intent-based discovery

Strong Semantic Queries

• “datasets about customer lifetime value”

• “objects related to fraud detection”

• “GDPR compliance reporting”

• “employee onboarding process”

Weak Semantic Queries

• “cust_tbl_v2”

• “rpt_001”

Note: For exact technical names, keyword search is often better.

Step 9. Use Precise Names When Known

If you already know the object name, include it directly.

Example

Show full details for dataset “Customer Revenue Snapshot”.

This helps Blink retrieve exact object metadata faster.

Step 10. Ask for Tags and Technologies

Blink can retrieve governance and technical classifications.

Examples

Tags

What tags are associated with the Supplier dataset?

Technologies

Which Snowflake objects are related to customer analytics?

Data Sources

Show datasets sourced from SAP.

Step 11. Break Complex Requests Into Steps

Large requests are easier to solve incrementally.

Instead of

Find all finance datasets with lineage, owners, technologies, comments, and linked dashboards.

Prefer

1. “Find finance datasets.”

2. “Show owners and stewards.”

3. “Retrieve linked dashboards.”

4. “Display technologies used.”

This improves accuracy and readability.

Step 12. Ask Blink to Compare or Prioritize

Examples

• “What are the main differences between these two KPIs?”

• “Which datasets appear most relevant for churn analysis?”

Step 13. Use Collaboration Features

Blink can retrieve comments and tasks.

Examples

• “Show comments on the Revenue dashboard.”

• “Are there open tasks related to Customer Master?”

• “Create a comment requesting data quality validation.”

Step 14. Avoid Overly Vague Requests

Too Vague

Show me data.

Better

Show me datasets related to quarterly revenue reporting in finance.

Recommended Prompt Templates

Best Practices Summary

Example of an Excellent Prompt

I’m preparing a finance governance review. Find critical finance datasets related to revenue recognition, show their owners and stewards, identify linked dashboards, and summarize any governance comments or tasks.

Why this works:

• Clear business objective

• Strong domain context

• Multiple related retrieval goals

• Explicit expected outcome

Final Recommendations

To get the best results from Blink:

• Think in terms of business intent

• Be specific when possible

• Use conversational follow-ups

• Combine business and technical language

• Ask for relationships, ownership, and governance context

Blink is most powerful when used as a data discovery and governance copilot, not just a keyword search engine.