, I’ve the chance to attempt new AI-powered analytical instruments, together with Microsoft Material’s information agent. That’s why I wish to share what I’ve realized, clarify what an information agent is, and spotlight the distinction between it and a “customary” AI agent.
So, with out additional ado, right here is my definition of an information agent:
A knowledge agent is a report you’ll be able to speak to.
For these of us in analytics, this implies two long-held needs would possibly lastly develop into a actuality:
#1: Analysts spend approach much less time constructing visualisations.
#2: Self-service insights come nearer to enterprise customers.
Let me elaborate on every of those factors a bit extra.
Fewer visualisations, not fewer insights
I actually get pleasure from a great report that may inform me “what’s up” with the metrics I’m at the moment thinking about. However being skilled in analytics, I understand how stories can typically forged metrics within the fallacious gentle, main enterprise customers to ceaselessly ask analysts for KPIs interpretation, normally 10 minutes earlier than essential conferences.
And that’s one of many causes we frequently find yourself in a vicious cycle of getting dashboards nobody is utilizing, and stakeholders always wanting “the quantity” served advert hoc or through spreadsheets.
On the intense aspect, visualisations and spreadsheets usually are not going wherever, however serving the insights has a brand new approach with a Material information agent.
As an alternative of wrapping queries in graphs, you’ll be able to wrap them in prompts and directions paired with the consumption-ready ruled information property in Material, i.e., in a lakehouse, warehouse, Energy BI semantic fashions, KQL database, and even an ontology. This suggests the underlying information nonetheless must be ready and modelled to reply enterprise questions corresponding to “What was the income this week in comparison with final week?”
Nonetheless, from a design perspective, somewhat than making a scoped visible report back to reply this enterprise query, you now create a scoped information agent to supply this, and different subsets of solutions derived from the underlying information mannequin(s).
Extra exactly, the input-output movement goes as follows:
(1) a stakeholder asks a query, (2) the agent, powered by Azure OpenAI Assistant API, interprets the query and “decides” which of information sources is most probably to have the reply primarily based on supply schemas and agent directions, (3) generates the suitable question (SQL, DAX, or KQL relying on the supply kind), (4) validates it, (5) executes it underneath the stakeholder’s credentials, and (6) returns the end result as a textual content or a desk, not (but) as a visible.
In sum, a stakeholder interplay with insights through the information agent is a Q&A session on high of the curated dataset, and drill-down visuals could be changed with follow-up questions, corresponding to “Are you able to additionally break the income out by section?”
With that, it’s clear how analysts’ work not must be re-expressed solely through dashboards, aka the long-known tangible proof that the work of capturing the enterprise logic inside information fashions was delivered.
Now, let’s discuss…
Self-service insights, nearer to the place enterprise customers “stay”
I discussed earlier than that stories can typically misrepresent metrics, however that’s not the one purpose why “For those who construct it, they’ll come” hardly ever works for them or analytics normally. The reality is, the information barrier is usually too excessive to know the underlying semantic fashions and learn how to use BI instruments to create visuals on high.
Though this factors to information literacy, which is a change-management downside, it’s a proven fact that the focused enterprise viewers, who needs to be report shoppers, typically has an excessive amount of on their plate to trouble studying BI instruments for self-service analytics.
That’s why it’s essential to deliver insights nearer to the place finish customers “stay”, which these days factors in the direction of AI-powered instruments like M365 Copilot.
With the chance to show insights through information brokers outdoors of Material, analysts can now concentrate on the analytical logic behind self-service information brokers, and finish customers can entry insights in the identical AI-powered instruments that assist their different day by day duties, with out the complexity of switching to a different platform.
I’ve to notice this isn’t the one option to combine Material information brokers within the workflows, and no matter whether or not you’re a developer or a client, it’s good to know…
The distinction between information and an AI agent
We’ve realized to this point that the Material information agent is an analytical agent centered on read-only, ruled information entry, able to translating pure language prompts into complicated database queries that unlock insights, even outdoors the Material tenant.
On the opposite aspect, an AI agent is outlined as a system that enables Giant Language Fashions (LLMs) to do issues, not simply reply to prompts, on behalf of customers or different methods by accessing instruments and information.
That means, the entire magic is within the AI agent setup, the place you should use a Material information agent as a specialised instrument or information supply.
I’ll illustrate this with one easy instance.
Think about an authorised consumer requests the AI agent to “Draft an electronic mail to the staff summarising final week’s income by section.” To get this work accomplished, the AI agent would, amongst different issues, want to organize income insights from the enterprise database. So, in an purpose to cut back errors in income calculation, the developer would design an agentic workflow to route the enter immediate to the Material information agent instrument, which might deal with the heavy lifting of figuring out the schema, writing the question, executing it, and returning the exact figures. Lastly, the AI agent would then use these figures to complete its broader workflow and write the e-mail.
What’s the distinction between these two, then? It’s that an AI agent acts, whereas the information agent grounds.
Thanks for studying.
For those who discovered this submit worthwhile, be at liberty to share it along with your community. 👏
Wish to study extra about information brokers?
If that’s the case, take a look at the next sources:
Material information agent creation – Microsoft Material
Learn to create a Material information agent that may reply questions on information.study.microsoft.com
Implement Microsoft Material Information Brokers – Coaching
Implement Microsoft Material Information Brokers (chat along with your information)study.microsoft.com
