Speaker A
[Music] Hi there, and thanks for tuning in. To trust data, consumers, both people and AI systems, need confidence that it's accurate, timely, and fit for purpose.
Discover how Alation uses Agentic AI to transform data quality monitoring with intelligent prioritization, instant checks, and proactive resolution.
Ask about this video. Answers come from its transcript only — with the timestamp, so you can check them.
Generated from the transcript and can be wrong — check the timestamp.
Key Takeaways
- Intelligent prioritization focuses efforts on the most critical data assets.
- Agentic AI automates the generation of data quality checks, reducing manual work.
- A unified platform enables proactive resolution through monitoring, collaboration, and alerts.
- Together, these innovations accelerate trusted data use and decision-making at scale.
What the video covers
- Traditional data quality checks are slow, manual, and rules-based, creating challenges for trusted data use.
- Alation introduces Agentic AI to make data quality monitoring smarter, scalable, and contextual.
- Intelligent prioritization uses the Behavioral Analysis Engine (BAE) to rank and focus on the most popular and frequently used data sets.
- Users can manually select data sets and fields for targeted data quality checks.
- Agentic AI automatically recommends and infers relevant data quality rules, eliminating the need for manual coding.
- Example given: credit score field with AI-suggested rules ensuring values fall between 300 and 850.
- Users can customize, modify, or delete data quality checks to fit specific use cases.
- A unified dashboard provides a comprehensive view of data quality rules and their status, highlighting failures such as stale data.
- Automated scheduling and alerts are supported via email, Microsoft Teams, and Slack for proactive monitoring.
- The platform integrates monitoring, collaboration, and resolution to turn data quality into a competitive advantage.
Chapters
- 00:00Introduction to Data Trust and Challenges
- 00:19Reimagining Data Quality with Agentic AI
- 00:42Intelligent Prioritization with Behavioral Analysis Engine
- 01:54Manual Selection and Popular Fields Highlight
- 02:22Instant Data Quality Checks Powered by Agentic AI
- 03:43Example: Credit Score Field and Customization
- 05:18Proactive and Unified Data Quality Dashboard
Full Transcript — Download SRT & Markdown
Speaker A
The challenge is traditional data quality checks are slow, manual, and rules-based. At Elation, we are reimagining data quality monitoring,
Speaker A
making it smarter, scalable, and contextual with Agentic AI. And over the next few minutes, we are excited to show you our three game-changing innovations.
Speaker A
Now, the first step in this process is intelligent prioritization. As we all know, not all data sets are created equal. And so instead of manually deciding where to start, Elation's behavioral analysis engine, or BAE, intelligently ranks and prioritizes
Speaker A
your most popular and frequently used data sets. This helps you focus your data quality efforts where they'll make the most impact on the data the people actually use.
Speaker A
Now, of course, you're also able to manually select which data sets to run DQ checks on based on your target use case. For example, let's take a closer look into this fact loan applications table living in Snowflake.
Speaker A
Upon selecting this data set, Elation once again instantly highlights the top five most frequently used and popular fields in that table.
Speaker A
So there's virtually no guesswork required since you're really focusing on what matters to the business. Next, the second key differentiator of Elation is instant data quality, where we're letting Agentic AI do the heavy lifting in building these data
Speaker A
quality rules. As we can see here, instead of hand-coding these checks manually, all we had to do was hit recommend checks, and Elation will intelligently recommend and infer which data quality rules make sense for each of these fields in the table.
Speaker A
Now, let's take a closer look into the credit score field. As we can see, Elation has automatically suggested two relevant data quality rules. And what I love about this example is that the Agentic AI of Elation was able to intelligently know
Speaker A
that credit scores need to fall within this relevant range of 300 to 850. We can also customize the scope of your data quality checks by modifying or deleting a check that's not relevant for your use case. In this simple example,
Speaker A
I'm only interested in monitoring credit scores and the freshness of my data using this ETL ingest date attribute.
Speaker A
So, all I have to do is remove and delete the other columns that are not in scope for my check.
Speaker A
Now that we've developed our data quality monitor, let's highlight Elation's final differentiator, which is our proactive and unified approach to data quality.
Speaker A
This dashboard provides a bird's eye view of the four data quality rules applied to this data set.
Speaker A
As we can see, one out of the four rules failed, indicating that this data set may be stale or outdated.
Speaker A
Elation DQ also supports automated scheduling of these data quality monitoring jobs with built-in alerts and notifications via email, Microsoft Teams, and Slack.
Speaker A
And so, in summary, here are three key takeaways. First, you get intelligent data quality by prioritizing your most critical data assets.
Speaker A
Second, Agentic AI takes on the heavy lifting by instantly generating the checks for you. And finally, Elation enables proactive resolution through a unified experience where monitoring, collaboration, and resolution all happen in one platform. And together, these three pillars turn data quality from a
Speaker A
chore into a competitive advantage. And ultimately, this helps teams move faster to deliver trusted decisions and AI at scale.
Topics:AlationData QualityAgentic AIBehavioral Analysis EngineData MonitoringData GovernanceSnowflakeData Quality RulesAutomated AlertsData Trust
