December 2025
Intermediate to advanced
46 pages
1h 2m
English
Content preview from Structured for Intelligence
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Chapter 3. Optimizing Data Discovery for AI Systems
At a high level, the concept of discoverability is straightforward. It’s about how easy it is to find, understand, and trace the data, logic, and decisions for an AI system. Ultimately, this helps to build trust with users, customers, and regulators. It can also improve usability. When it becomes easier to get relevant information, there is likely to be more adoption and stronger ROI.
Yet discoverability is something that does not get enough attention. Consider a McKinsey survey. It found that 40% of enterprises said that explainability was a major risk, yet only 17% looked to address it seriously. The survey also showed that 91% of the respondents thought their organization was not “very prepared” to scale generative AI responsibly and safely.
This helps to explain why AI often fails to live up to expectations, as highlighted in a dbt Labs survey. Even though 80% of the teams reported using AI, the accuracy for natural-language-to-SQL queries remained inconsistent. Then again, the LLMs lacked access to semantics and lineage. There was also the problem of context being scattered across warehouses, BI tools, and wikis.
Discoverability is complex and challenging. But it is critical for effective AI. In this chapter, we’ll see what you need to focus on to successfully add discoverability to your AI system.
Overcoming Discoverability Gaps in AI Systems
Enterprises often struggle with data fragmentation, inconsistent semantics, ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.