Data & AI Summit Takeaways: Breakout Sessions

2026-06-20 · Source: Data Engineering on Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, quick

Summary

The Data & AI Summit featured several breakout sessions highlighting practical data and AI applications. Scribd demonstrated a Databricks App for data quality and observability, which includes rule management, AI-driven rule suggestions, and historical trend analysis, building on the DQX framework. Mercedes Benz Korea showcased their approach to conversational data interaction, leveraging metric views and Genie to create a semantic layer for business decisions, underscoring the importance of consistent data modeling. Boeing presented a robust data contract implementation, moving beyond Wiki pages to an open-spec standard, AI-assisted authoring, automated data checks, and a subscription-based contract marketplace for enhanced trust at scale.

Key takeaway

For Data Engineers or MLOps Engineers building robust data platforms, consider integrating AI-driven solutions for data quality and governance. You should explore developing custom Databricks Apps for managing data quality rules and adopt open-spec data contracts with AI-assisted authoring to ensure trust at scale. This approach streamlines data reliability, automates checks, and fosters better coordination between data producers and consumers, reducing manual overhead and improving data integrity.

Key insights

Modern data platforms and AI enable scalable solutions for data quality, conversational analytics, and trust through robust data contracts.

Principles

• Data consistency is foundational for conversational AI.
• Open-spec standards enhance data contract coordination.
• AI can accelerate data quality rule creation and contract authoring.

Method

Implement data contracts using an open-spec standard, accelerate authoring with AI, compile specs into running checks, and establish a marketplace for stakeholder subscriptions.

In practice

• Develop custom data quality rules within Databricks Apps.
• Utilize metric views and Genie for conversational data experiences.
• Adopt AI-assisted data contract authoring for improved coordination.

Topics

• Data Quality
• Databricks Apps
• Data Contracts
• Conversational AI
• Semantic Layer
• AI-Assisted Authoring

Best for: CTO, VP of Engineering/Data, Director of AI/ML, Data Engineer, Data Scientist, MLOps Engineer

Related on AIssential

• Welcoming Stately Cloud to Databricks: Investing in the Foundation for Scalable AI Applications — Acquiring Stately Cloud enhances Databricks' platform reliability for mission-critical AI workloads.
• The Contract-driven Data Platform — Data contracts enable a "contract-driven data platform" for consistent, interoperable, and governed data products.
• How I Replaced 1,000 Brittle Rules with 3 AI Calls: A Hybrid Data Quality Framework — Combine deterministic SQL rules with inline AI for scalable, context-aware data quality, reducing false positives and cost.
• Transforming industries with conversational AI: Partner solutions built on Databricks Genie — Databricks Genie enables conversational AI solutions, eliminating data access friction across diverse industries via partner-built accelerators.
• How Data Professionals Use AI — and What Really Matters — Widespread AI adoption among data professionals amplifies existing data quality challenges, making trust and verification paramount.
• Building Agent Ready Data Pipelines From Scratch — AI agents require data pipelines to provide rich metadata for accurate interpretation, beyond traditional data quality.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Data Engineering on Medium.