Skip to main content

Overview

Data analysts use Glean’s MCP server to query structured data sources, combine quantitative and qualitative insights, and generate reports without switching between multiple analytics tools.

Prerequisites

Recommended connectors:
  • Databricks (for data warehouse queries)
  • Salesforce (for CRM data)
  • Google Drive (for spreadsheets and reports)
  • Confluence or Notion (for analysis documentation)
  • Slack (for data discussions)
  • Jira (for project tracking)
Supported MCP hosts:
  • Claude Desktop
  • ChatGPT
  • Cursor (for data notebooks)
  • Any MCP-compatible interface

Use Cases

1. Natural Language Database Queries

Query structured data sources using natural language instead of SQL.
Use Glean to query Databricks for:
1. Total revenue by customer segment for Q3 2024
2. Month-over-month growth rates
3. Top 10 customers by revenue
4. Any significant anomalies or outliers Display results as a table and
highlight key insights.
Query Databricks via Glean to show user sign-ups by week for the last
quarter. Calculate week-over-week growth and flag any unusual drops.
Use Glean to analyze our sales data: What's the average deal size by
industry? Which industries have the highest close rates?
What it does:
  • Translates natural language to SQL queries
  • Executes queries against connected data warehouses
  • Formats results for easy interpretation
  • Identifies notable patterns or anomalies
Note: Requires Databricks Genie or similar connectors that support structured data queries.

2. Trend Analysis and Pattern Recognition

Identify trends in business metrics and customer behavior.
Use Glean to analyze customer purchase behavior trends:
1. Query our transaction data for the last 12 months
2. Identify seasonal patterns
3. Segment by customer type (new vs returning)
4. Look for correlations with marketing campaigns
5. Summarize the key trends and their business implications.
Search Glean for usage metrics discussions in Slack and product
analytics. What features are growing? What's declining? Why?
Use Glean to analyze support ticket volume over time. Are there spikes related
to releases or specific features?
What it does:
  • Queries time-series data
  • Identifies patterns and correlations
  • Combines quantitative data with qualitative context
  • Provides business interpretation

3. Automated Report Generation

Generate recurring reports by pulling data from multiple sources.
Generate a detailed analytical report on monthly sales data using Glean:
1. Query Salesforce for closed-won deals this month
2. Calculate key metrics: total ARR, average deal size, win rate
3. Compare to previous month and same month last year
4. Pull in any relevant context from sales team Slack discussions
5. Identify top performers and any concerning trends
6. Format as an executive summary with supporting data tables.
Use Glean to create a weekly performance report: pull key metrics from
our analytics dashboard, add context from team discussions, highlight wins
and areas needing attention.
Generate a quarterly business review using Glean to aggregate data from
Salesforce, support metrics, product usage, and financial reports.
What it does:
  • Aggregates data from multiple sources
  • Calculates key metrics automatically
  • Adds qualitative context from discussions
  • Formats for stakeholder consumption

4. Anomaly Detection in Financial Data

Identify unusual patterns or errors in financial datasets.
Analyze accounting data from Salesforce or your financial system using Glean to find anomalies:
1. Look for transactions with unusual amounts (outliers)
2. Identify accounts with unexpected activity patterns
3. Flag duplicate entries or reconciliation issues
4. Check for missing data or incomplete records
Prioritize findings by potential financial impact and create an audit checklist for items needing investigation.
Use Glean to analyze our expense data from the last quarter. Find
anomalies, duplicate charges, or policy violations.
Query financial data via Glean to identify high-risk transactions or accounts
that need closer review during our audit.
What it does:
  • Analyzes financial data for outliers
  • Identifies reconciliation issues
  • Flags potential errors or fraud
  • Prioritizes audit focus areas

5. Customer Cohort Analysis

Analyze customer behavior by cohort to understand retention and growth patterns.
Use Glean to perform a cohort analysis on customers:
1. Group customers by their signup month
2. Calculate retention rates by cohort
3. Analyze revenue trends for each cohort
4. Identify which acquisition channels have best long-term value
5. Visualize the cohort data and highlight insights for the growth team.
Query customer data via Glean to compare cohorts from Q1 vs Q2. Which
cohort has better engagement and retention?
Use Glean to analyze user behavior by signup source. Do customers from
different channels behave differently?
What it does:
  • Groups customers by cohort
  • Calculates retention and lifetime value metrics
  • Compares cohort performance
  • Identifies successful acquisition strategies

6. Root Cause Analysis

Investigate data anomalies by combining quantitative and qualitative sources.
Our conversion rate dropped 15% last week.
Use Glean to investigate:
1. Query analytics data to confirm the drop and identify when it started
2. Check for code deployments or feature releases during that time
3. Search Slack for mentions of site issues or customer complaints
4. Look for related support tickets or bug reports
5. Determine the most likely root cause and suggest data to validate it.
Revenue is down this month. Use Glean to analyze: Are we closing fewer
deals? Lower deal sizes? Different customer segments? What changed?
Use Glean to investigate this spike in API errors. Check logs, recent
deployments, and engineering discussions for clues.
What it does:
  • Combines quantitative metrics with qualitative context
  • Correlates changes with events (deployments, campaigns)
  • Searches for related discussions and issues
  • Proposes hypotheses for investigation

7. Competitive Benchmarking

Analyze competitive data and market positioning.
Use Glean to compile competitive benchmarking data:
1. Search for market research reports in Confluence
2. Find competitive pricing data from sales conversations
3. Look for analyst reports or industry surveys
4. Query our win/loss data by competitor
5. Create a comparison table showing our position vs top 3 competitors.
Search Glean for all mentions of [competitor] in sales calls and
analysis docs. How do we compare on features, pricing, and positioning?
Use Glean to analyze our competitive win rate by segment. Where are we
strongest? Where are we losing?
What it does:
  • Aggregates competitive intelligence
  • Compiles market research and analysis
  • Quantifies competitive performance
  • Identifies positioning opportunities

8. Data Quality Assessment

Audit data quality and identify gaps or inconsistencies.
Audit data quality in our CRM using Glean: 1. Find records with missing
required fields 2. Identify duplicate accounts or contacts 3. Check for
inconsistent data formats 4. Flag accounts without recent activity
Prioritize cleanup by potential impact on reporting and operations.
Use Glean to analyze our analytics data for gaps. Are there time periods
with missing data? Features with no tracking?
Query our data warehouse via Glean to identify tables or fields with high
null rates that might affect analysis accuracy.
What it does:
  • Identifies incomplete or inconsistent data
  • Finds duplicates and errors
  • Quantifies data quality issues
  • Prioritizes remediation efforts

9. Predictive Analysis Support

Gather data and context for predictive modeling.
I'm building a churn prediction model. Use Glean to gather: 1.
Historical customer data: tenure, usage, support tickets 2. Known churn
cases with reasons (from CRM and support) 3. Research on churn indicators
from past analyses 4. Feature ideas discussed by data science team in Slack
Compile a dataset and suggest additional predictive features to consider.
Use Glean to find factors that predict deal win rate. Query CRM data and
search for sales team insights about what makes deals succeed.
Search Glean for past analyses about [business outcome]. What variables were
found to be predictive? What data sources should I use?
What it does:
  • Aggregates historical data for modeling
  • Surfaces domain knowledge from past analyses
  • Suggests relevant features and variables
  • Connects quantitative data with qualitative insights

10. Ad Hoc Business Questions

Answer urgent business questions quickly with data.
Leadership is asking: "How many customers from [industry] churned last quarter and why?"

Use Glean to:

1. Query CRM for churned customers in that industry
2. Find their support ticket history and escalations
3. Search for exit interview notes or feedback
4. Look for patterns in account health scores

Provide a concise answer with supporting evidence.
How many deals did we close with new vs existing customers last month?
Use Glean to query Salesforce and break down by segment.
What's the average time to close by deal size? Use Glean to analyze our
pipeline data and identify where deals slow down.
What it does:
  • Quickly queries relevant data sources
  • Provides evidence-based answers
  • Combines data with contextual information
  • Formats insights for executive consumption

Best Practices

Start with Clear Questions

✅ "What's the month-over-month growth in user sign-ups?"
✅ "Which customer segment has the highest churn rate?"
❌ "Tell me about our customers" (too broad)

Specify Time Ranges

Always include time boundaries: "last quarter", "YTD", "since January 2024"

Combine Quantitative and Qualitative

Don't just query numbers. Also search for context in Slack discussions,
meeting notes, and analysis docs to understand the "why" behind the data.

Validate Results

When Glean returns data, cross-check key figures against known sources or
dashboards before using in reports.

Document Assumptions

Ask Glean to note any assumptions, filters, or data limitations in the
analysis so stakeholders understand the context.

Troubleshooting

Can’t query structured data?
  • Verify Databricks Genie or similar connector is properly configured
  • Check that your user has query permissions on the data warehouse
  • Ensure the data source is actively indexed
Inaccurate calculations?
  • Be explicit about formulas: “Calculate as (new - old) / old * 100 for growth rate”
  • Specify how to handle nulls, duplicates, or edge cases
  • Ask Glean to show the query it’s using so you can verify
Missing business context?
  • Connect Slack channels where data discussions happen
  • Index analysis documentation from Confluence or Notion
  • Include links to past analyses and reports
Results don’t match dashboards?
  • Check if time zones or date boundaries are defined consistently
  • Verify filters and segments match your dashboard definitions
  • Confirm you’re querying the same underlying data sources
I