Modern enterprises want everyone, not just data engineers, to be able to ask questions of their data. But turning natural language into reliable, secure, and business-aware queries is far from simple. In this session, we introduce a new end-to-end architecture that combines intent screening, retrieval augmented context, hybrid fuzzy semantic matching, and large language model reasoning to generate executable queries that are both accurate and safe to run in production environments.
We will walk through how the system screens user intent, retrieves relevant past examples, aligns user language with schema entities, and constructs structured queries using a modular prompting strategy. We will also show how deterministic, LLM independent aggregation ensures numerical accuracy and eliminates hallucinated metrics. The talk will include a deep dive into the technical modules, vector search workflows, validation layers, and execution pipeline, along with performance and reliability considerations for real world deployments.
Attendees will leave with a clear understanding of how to design natural language to SQL systems that are secure, scalable, and enterprise ready, and how to combine LLMs with deterministic computation to deliver trustworthy insights at scale.
Main Takeaways
Natural language to SQL requires more than an LLM.Reliable systems must combine intent screening, contextual retrieval, and hybrid fuzzy semantic matching to correctly interpret user intent.
Deterministic computation is essential for trust.All aggregations and metric calculations must happen outside the LLM to eliminate hallucinations and ensure numerical accuracy.
Enterprise readiness depends on safety, validation, and governance. A production grade pipeline must enforce security checks, schema aware validation, and role based access controls before any query is executed.
Interview:
What is the focus of your work these days?
I am focused on building enterprise ready AI systems that combine large language models with deterministic, schema aware components. This includes designing architectures that safely translate natural language into executable queries, improving evaluation frameworks for AI assisted analytics, and ensuring that these systems meet the reliability, security, and governance standards required in large scale commercial environments.
What is the motivation behind your talk?
The motivation was to address a growing gap between what LLMs can generate and what enterprises can safely deploy. Many teams want natural language interfaces for data, but they struggle with accuracy, hallucinations, and security risks. This talk highlights a practical architecture that solves these challenges by blending LLM reasoning with retrieval, hybrid search, strict validation, and deterministic computation. The goal is to show a path to building systems that are both powerful and trustworthy.
Who is your session for?
This session is designed for data scientists, machine learning engineers, AI architects, and technical product leaders who are building or evaluating natural language interfaces for analytics. It is also relevant for engineers working on enterprise AI platforms, vector search, retrieval augmented generation, and evaluation frameworks for LLM based systems.
Speaker
Francesca Lazzeri
Principal Group Director of Data and Applied AI Science @Microsoft, Advisor and Lecturer for MIT’s "Break Through Tech AI" Program,
Francesca Lazzeri, Ph.D., is Principal Group Director of Data and Applied AI Science at Microsoft, where she leads a multidisciplinary organization of AI researchers, data applied scientists, and machine learning engineers. Her core strengths include building interpretability and explainability tools for safe and trustworthy AI, fine-tuning foundation models with rigorous evaluation and experimentation, advanced prompt engineering, MLOps and AIOps integration, production-grade AI governance with full-stack observability.
Francesca is also Advisor and Lecturer for MIT’s "Break Through Tech AI" program, where she designs and delivers hands-on modules on LLM evaluation methodologies, covering prompt-engineering assessments, fairness and bias measurement, and the development of ethical guidelines for generative AI systems.
Prior to joining Microsoft, Francesca was a Research Fellow at Harvard University (Technology and Operations Management Unit) and taught Python for AI as an Adjunct Professor at Columbia University.
She has authored several books, including:
- Machine Learning Governance for Managers (Springer Nature, 2023)
- Impact of Artificial Intelligence in Business and Society (Routledge, 2023)
- Machine Learning for Time Series Forecasting with Python (Wiley, 2020)
She also contributes regularly to journals like O’Reilly, InfoQ, and DZone, and serves as Chief Editor of Data Science at Microsoft, a publication dedicated to practical insights for developers and data scientists.
Francesca is proud to serve on advisory boards for initiatives like Break Through Tech AI (MIT), AI-CUBE project (European Union) and Women in Data Science (Stanford University).
