How Dagster Compass Powers Brooklyn Data’s Self-Service Analytics

2026-05-31 · Source: Dagster Blog · Field: Technology & Digital — Data Science & Analytics, Artificial Intelligence & Machine Learning · Depth: Intermediate, medium

Summary

Dagster Compass, a text-to-analytics (T2A) solution, enables self-service data access directly within Slack, addressing usability, governance, and trust challenges. Brooklyn Data (BDC) evaluated and deployed Compass on top of Snowflake, integrating it with their dbt project to transform professional services automation (PSA) and CRM data. Key features include its native Slack app interface, robust governance via private channels and Git-managed context, and strong performance with user-driven context corrections. BDC utilized Compass to expose modeled PSA data to their delivery excellence organization, reducing query times from 5-10 minutes to 1-2 minutes for operational questions, improving searchability, and enhancing decision-making for project management and resource allocation. The firm plans to expand its use to marketing data.

Key takeaway

For Directors of AI/ML or Data Engineers evaluating self-service analytics tools, consider Dagster Compass to integrate natural language querying directly into Slack. This approach can significantly boost operational efficiency by reducing data access barriers and query times, as demonstrated by Brooklyn Data's 5-10 minute to 1-2 minute improvement. Prioritize validating T2A responses against known outputs and establish robust governance through channel permissions and Git-managed context to ensure accuracy and trust.

Key insights

Text-to-analytics adoption hinges on seamless integration, strong governance, and user-driven context improvement.

Principles

• Validate T2A tools against known outputs.
• Centralize data for consistent metrics.
• Integrate analytics where users already work.

Method

Deploy T2A on a well-modeled data layer, configure specific table access, and manage context via Git pull requests.

In practice

• Connect T2A to PSA/CRM data for operational insights.
• Use private Slack channels for data access control.
• Enable users to correct model context directly.

Topics

• Text-to-Analytics (T2A)
• Dagster Compass
• Self-Service Analytics
• Data Governance
• Slack Integration
• Snowflake
• dbt

Code references

• dagster-io/dagster

Best for: Data Engineer, Analytics Engineer, Director of AI/ML

Related on AIssential

• The Dagster Almanack: From Complexity to Composability — Dagster simplifies complex data environments by shifting to data-asset-based, declarative orchestration with a unified control plane.
• Xero Slack Integration With AI: A Better Way to Bring Finance Answers Into Slack — AI-powered financial intelligence layers offer flexible, on-demand access to financial data within communication platforms like Slack.
• How conversational analytics removes the BI bottleneck — Actionable insights, not just trivia, drive business value from conversational analytics.
• Fine-Tune LLMs on Your Mac: DagsHub + Apple MLX-LM Integration — DagsHub and Apple MLX-LM enable full MLOps for local LLM fine-tuning on Apple Silicon.
• Making Dagster Easier to Contribute to in an AI-Driven World — AI tools ease PR generation, but effective open-source contribution requires streamlined review and clear guidelines.
• You can't trust one token number across your tools. Here's the guide to a dashboard that keeps Codex, Claude, and ChatGPT honest. — A token burn dashboard reveals AI usage habits, improving outcomes and expanding imaginative computing beyond mere cost tracking.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Dagster Blog.