The rise of Agentic AI is transforming the analytics landscape, but it comes with an often-overlooked challenge: database strain. Traditionally, operational databases are ringfenced to prevent unstructured, inefficient queries from affecting critical business functions. However, in a world where AI agents dynamically generate and execute SQL queries to retrieve real-time data, production databases are facing unprecedented pressure.
​
Additionally, Retrieval-Augmented Generation (RAG), a rapidly emerging AI technique that enhances responses with real-time data, is further intensifying this issue by demanding continuous access to up-to-date information. RAG works by supplementing AI-generated responses with live or external knowledge sources, requiring frequent, real-time queries to ensure accuracy. This puts even more strain on traditional database infrastructures. In a previous blog post, I looked at how Agentic AI will improve the experience for users of the Oracle Analytics ecosystem.

The Problem: AI Agents, RAG & Uncontrolled Query Load

A well-managed production database is typically shielded from unpredictable query loads. Database administrators ensure that only structured, optimised workloads access production systems to avoid performance degradation. But with Agentic AI and RAG, that fundamental principle is breaking down.
Instead of a few human analysts running queries, organisations may now have dozens or even hundreds of AI agents autonomously executing SQL queries in real time. These queries are often:

• Ad hoc and unpredictable, making performance tuning difficult
• Highly frequent, since AI agents are designed to work autonomously
• Complex and computationally expensive, often scanning large datasets

This creates significant challenges for traditional RDBMS architectures, which were not designed to handle the scale and unpredictability of AI-driven workloads. With Retrieval-Augmented Generation (RAG) in particular, AI models require frequent access to real-time data to enhance their outputs, placing additional stress on transactional databases. Since these databases were optimised for structured queries and controlled access, the introduction of AI-driven workloads risks causing slowdowns, performance degradation, and even system failures.

For users of Oracle Analytics, this shift presents serious performance implications. If production databases are overwhelmed by AI-driven queries, query response times increase, dashboards lag, and real-time insights become unreliable. Additionally, Oracle Analytics’ AI Assistant, Contextual Insights, and Auto Insights features, which rely on efficient access to data sources, could suffer from delays or inaccuracies due to excessive load on transactional systems.

To mitigate this, organisations must rethink their database strategies, ensuring that AI workloads are governed, optimised, and properly distributed across more scalable architectures.

The Traditional Approach: Cloning Production Data

One way that organisations have attempted to address this issue is by cloning production databases on a daily or weekly basis to offload AI-driven queries. However, this approach presents several major drawbacks:

• Clones are not real-time – Since they are refreshed periodically, they lack the latest data required for up-to-the-minute AI-driven insights.
• Cloud clones are expensive – Storage and compute costs for cloud-based clones can be prohibitively high, making large-scale adoption unsustainable.
• Complexity & Latency – Maintaining and synchronising clones across multiple environments increases operational overhead and slows down analytics workflows.
• Doesn’t scale with RAG demands – Since RAG requires real-time retrieval of data to generate accurate responses, stale clones fail to meet its needs.

For AI-driven analytics, relying on periodic database clones leads to significant inefficiencies. Since AI agents require access to up-to-date, contextual information, working with outdated data introduces data integrity risks and lowers the effectiveness of AI-generated insights. Additionally, managing and maintaining multiple clones across different environments adds a significant administrative burden, requiring additional governance, access control, and monitoring.

For Oracle Analytics users, these challenges could lead to outdated insights, reduced trust in AI-generated recommendations, and a poor user experience due to lagging or inconsistent data. Given these drawbacks, it’s clear that cloning is not a viable long-term solution for handling the database demands of Agentic AI.

A Shift in Data Architecture: Data Lakes & Lakehouses

Instead of relying on traditional RDBMS architectures, organisations are increasingly adopting data lakes and lakehouses to support AI-driven analytics. These architectures offer several key advantages:

• Decoupled storage and compute – Unlike traditional databases, lakehouses allow AI agents to access structured and unstructured data without directly querying transactional systems.
• Scalability – Cloud-based lakehouses scale seamlessly with AI workloads, reducing the risk of database bottlenecks.
• Cost-effectiveness – By storing data in low-cost cloud object storage, lakehouses significantly reduce the expenses associated with cloning full databases.

However, while lakehouses present an effective alternative, the migration from a traditional RDBMS to a lakehouse architecture is not without its challenges. The shift requires significant investment in re-architecting data pipelines, ensuring data governance, and retraining teams to work with new query engines and tools. Moreover, performance tuning for structured transactional data in a lakehouse can be complex compared to optimised RDBMS queries, which may lead to initial adoption friction.
​
For users of Oracle Analytics, this shift could mean that existing reports and dashboards need to be refactored to work efficiently with a lakehouse structure, adding additional effort and complexity.

Optimising Performance with Modern Storage Solutions

Beyond adopting new architectural patterns, organisations can leverage modern storage solutions like Silk to mitigate the strain on production databases. Silk provides a virtualised, high-performance data layer that optimises storage performance and scalability without requiring a complete architectural overhaul.
By using Silk or similar intelligent storage virtualisation and caching technologies, organisations can:

• Provide instant, efficient data replication – Unlike traditional cloud-based clones, modern solutions can create real-time, low-overhead replicas, ensuring fresh data access without excessive costs.
• Optimise query performance – Intelligent caching and virtualisation technologies help ensure AI workloads do not compromise the performance of mission-critical systems.
• Reduce the complexity of migrating from an RDBMS – By providing compatibility with existing RDBMS environments, these solutions offer a more gradual and manageable transition to modern data architectures.

For organisations using Oracle Analytics, integrating such solutions could help sustain real-time data access while alleviating the performance burden on production databases. However, despite these advantages, storage virtualisation and caching solutions are not a panacea. Organisations must still ensure that their AI workloads are properly governed to prevent excessive resource consumption, and they need to assess whether virtualised storage aligns with their broader data architecture and security policies.

Conclusion: Preparing for the Future of AI-Driven Analytics

Agentic AI and RAG are here to stay, and with them comes a fundamental shift in how data is accessed and managed. However, blindly allowing AI-driven queries to run against production databases is not a sustainable solution. To support the evolving demands of AI, organisations must modernise their data strategies by:

• Shifting AI workloads to scalable architectures like data lakehouses
• Implementing AI query governance to optimise performance
• Leveraging modern storage technologies like Silk to mitigate traditional RDBMS bottlenecks

For Oracle Analytics users, this shift will require rethinking how data is stored, accessed, and processed to ensure that the platform continues to deliver timely insights without compromising performance. The key takeaway? Traditional database architectures were not designed for AI-driven workloads. To fully embrace the potential of Agentic AI and RAG, organisations must rethink their data foundations - or risk being left behind.

How is your organisation adapting to the challenges of AI-driven analytics? Let’s continue the conversation in the comments!

How AI is Reducing SQL’s Visibility in Oracle Analytics

AI-powered features in Oracle Analytics allow users to explore data without manually writing SQL. Three key capabilities demonstrate this shift:

1. Contextual Insights: Auto-Generated SQL Behind the Scenes
• Example: A sales manager sees an unexpected spike in revenue on a dashboard. Instead of running queries, they click on the data point, and Contextual Insights automatically surfaces key drivers and trends.
• What happens in the background? Oracle Analytics generates SQL queries to identify correlations, anomalies, and patterns, but the user never sees or writes them.

2. AI Assistant: Querying Data Without SQL
• Example: A marketing analyst wants to compare Q1 and Q2 campaign performance. Instead of writing a SQL query, they ask the AI Assistant:
“Show me campaign revenue for Q1 vs Q2.”
• What happens in the background? The AI Assistant translates the request into SQL, retrieves the data, and presents a visual answer.
• Why it matters: Business users get answers instantly, without needing SQL expertise.

3. Auto Insights: Surfacing Trends Without Querying Data
• Example: A finance team wants to understand profit fluctuations. Instead of manually querying revenue data over time, they use Auto Insights, which highlights key trends and anomalies.
• What happens in the background? Oracle Analytics runs SQL queries to detect significant changes and patterns.
​
These features make SQL less visible but not obsolete. In fact, AI relies on SQL to function effectively, which leads to the question—where is SQL still essential?

Why SQL is Still Essential

While AI is making SQL more accessible, it hasn’t eliminated the need for SQL expertise. Several areas still require manual intervention:

1. Handling Complex Joins & Business Logic
• AI struggles with complex queries that involve multiple joins, subqueries, and conditional logic.
• Example: A financial analyst wants to calculate profitability by region, requiring a multi-table join across sales, inventory, and expenses. AI might generate an inefficient or incorrect query.

2. Performance Optimisation
• AI-generated SQL isn’t always the most efficient. SQL tuning (e.g., indexing, partitioning) still requires human expertise.
• Example: AI might generate a query that performs a full table scan instead of leveraging an index, slowing down performance.
​
3. Explainability & Trust
• AI-generated queries can sometimes produce unexpected results, making it difficult for users to validate the logic.
• Example: If AI Assistant returns an unusual data trend, an analyst may still need to inspect the underlying SQL to ensure accuracy.

SQL remains a crucial tool for data engineers, analysts, and DBAs who need control over data processing, query performance, and governance. However, as AI continues to evolve, could it overcome these challenges?

The Role of the Semantic Model in AI-Driven Analytics

One of the key features of Oracle Analytics is its semantic model, designed to abstract the complexity of source systems from end users. Instead of writing raw SQL queries against complex database structures, users interact with a logical layer that simplifies relationships, calculations, and security rules.

Why the Semantic Model Exists

The semantic model serves several purposes, including:

• Hierarchies & Drilldowns: Defining business hierarchies (e.g., Year → Quarter → Month) for intuitive analysis.
• Logical Joins & Business Logic: Providing a structured way to join tables without requiring users to understand foreign keys or database relationships.
• Row-Level Security: Enforcing access control so users only see the data they are authorised to view.

This abstraction enables self-service analytics while ensuring data governance, performance, and accuracy.
Will AI Make the Semantic Model Redundant?

AI-powered analytics features in Oracle Analytics Cloud (OAC)—such as Contextual Insights, AI Assistant, and Auto Insights—are reducing the need for manual query writing. But does this mean the semantic model is no longer needed? Not quite.

AI currently relies on the semantic model to:

• Ensure accurate and governed data access—AI cannot enforce security rules or business logic without a structured data layer.
• Interpret user queries correctly—When an AI Assistant generates SQL, it uses predefined joins and relationships from the semantic model.
• Maintain consistency—Without a semantic layer, different AI-generated queries might return inconsistent results due to varying assumptions about data relationships.

The Future: AI-Augmented Semantic Models?
​
Rather than replacing the semantic model, AI could enhance it by:

• Auto-generating relationships & joins based on data patterns.
• Improving performance optimisation, recommending indexing strategies or pre-aggregations.
• Enhancing explainability, showing why certain joins or hierarchies were applied.

AI and the Semantic Model Will Coexist

While AI reduces the need for manual SQL, the semantic model remains essential for structured, governed, and performant analytics. The future is likely AI-assisted semantic models rather than their elimination.
The Future of AI in SQL GenerationAI will likely become more sophisticated in handling SQL, but rather than eliminating it, AI will enhance SQL’s role. Here’s what the future might look like:

1. AI-Powered Query Optimisation
• AI could not only generate SQL but also analyse and optimise it for better performance.
• Example: Future AI Assistants might suggest indexing strategies, rewrite inefficient queries, or recommend materialised views.
2. Better Handling of Complex Joins & Business Logic
• AI could integrate knowledge graphs or semantic layers to better understand relationships between tables, improving the accuracy of generated SQL.
3. Explainable AI for SQL Generation
• AI might offer query rationale explanations, showing users why a specific query was generated and suggesting alternative approaches.
4. AI Agents & Autonomous Databases
• AI Agents could work alongside SQL experts, automating routine queries while letting humans handle complex cases.
• Oracle’s Autonomous Database could play a larger role in self-optimising SQL execution.
​While AI will continue to reduce the need for manual SQL writing, it is more likely to enhance SQL rather than replace it.