Getting Your Organization’s Data Ready for AI

Since the turn of 2025, AI has been thrown around a lot in conversations – both individual and also at an organizational level. Major technology providers have started their own suite of tools to build AI agents. 

While these tools are good enough for simpler AI use cases like fetching data from systems and presenting to us, but complex use cases like predicting patterns, collating data from multiple systems and driving insights from connected systems – that’s where AI implementations need to be looked at like projects which needs architecting and implementing with organization’s vision of AI. 

Let’s look at how we can make sure that AI implementations give us over 95% accuracy and not just answers every time which we assume might be correct. 

Is AI enough by itself? 

Common perception that AI Agents are deployed on top of applications which can be used to interact with the underlying systems to do what users are supposed to get done from AI. 

This perception stems from our use of AI tools like ChatGPT/Claude/Gemini as they interact with the Internet to get your queries answered. Since this is a tool available independently, there’s not technical setup and it is ready to go. 

Speaking of being Copilot being enough on itself, it depends on where the data is sourced from – and what the intent of the Agent is. If your Custom Copilot / AI Agent is meant to only look at some SharePoint files, some websites and within 1 system in your M365 gated access, you should be able to patch to knowledge sources and be good enough to let AI Agent give you the information in the format you need. 

Challenge occurs where you expecting the AI Agents to make sense of the data which is stored differently in different systems with different naming conventions – that’s when AI agents will fall through because it cannot understand when you are pointing to an “Account” in CRM, but the same is stored as a “Customer” in Business Central. 

And this is where something like a Unity Catalog comes into picture. The term itself describes that the data comes together in a catalog for common access and AI agents to source from. 

Let’s look at how we can imagine this unity catalog to be in the next section. 

Unity Catalog 

Unity Catalog can be thought of as an implementation strategy and collection of connected systems over which AI Agents can be based upon. 

Here’s how I summarize this process –  

1. Given you have set of different platforms in your organization across departments, some might or might not be connected with each other. 

2. Data from these platforms must be brought to a common catalog which you can call as a “Data Catalog” or a “Unity Catalog”. Feel free to establish the vocabulary of choice within your org! 

3. Source your data from Data Bricks for better processing. 

4. Cleanse your data before sending it to the data repository like Azure Data Lake from where the AI Agents will be based on. You can call this as the medallion approach where data is unified, de-duped, unified with common metadata ready to be ingested in Data Lake for AI consumption. 

5. Build AI Agents on top of Azure Data data for better speed, accuracy of your AI agents and refrain from AI Agents to directly connect to the source systems to avoid inaccuracy and performance degradation. 

6. Now this being the overarching approach, your organization’s needs might feed off this catalog thought process and can have different variations of this approach. 

7. And with this, you have a data/unity catalog which acts as the source for AI Agents with high-reliability, accurate data at AI Agents’ disposal 

Above diagram is a summary for how AI implementations will scale within organizations and have different variations of the same. 

To encapsulate, while independent AI agents can be implemented for personal use within the organization, given the appropriate privileges, for AI to make sense of and enable trusted decision making, AI implementations need to have data readiness in place with clarity. 

Hopefully, this topic summarizes the direction in which organizations can think of AI implementation, more than just building agents. 

We hope you found this blog useful, and if you would like to discuss anything, you can reach out to us at transform@cloudfonts.com.