Resource hub

Managing Ambiguities in Context Graphs

Agents are the new apps. Agents are quickly becoming the new apps. Instead of navigating complex software interfaces, users are increasingly interacting with AI agents that understand intent, retrieve information, and take action on their behalf. And one of the most compelling things you can do with an agent is connect it directly to operational databases, as seen in the recent move by Google to connect all their operational databases to MCPs.

How far are NL and SQL in NL2SQL?

SQL has traditionally been the language for data experts, alienating business users from the data. However, with rapid progress in large language models (LLMs), translating natural language questions from business to SQL, i.e., NL2SQL, is getting increasingly popular. Turns out that business questions are often high-level and do not have a simple SQL translation. Answering such high‑level questions over complex data is hard since the system must map the business user intent to the right tables, joins, filters, and metrics without losing meaning.

Building Context Graphs for Operational Databases

Context graphs are the missing translation layer that makes operational data understandable to business users and AI.

Evaluating Reasoning Models

Large language models have become the powerhouses of reasoning. OpenAI's o1 was the first reasoning model to automate chain-of-thought reasoning for logical and mathematical tasks. Many other models have excelled in complex deductive, inductive, or multi-step reasoning tasks since then.

Test Driving GPT-5.2

OpenAI released GPT-5.2 in December 2025, promising improvements in reasoning, instruction following, and complex query handling over previous versions such as GPT-5.1 and GPT-4.1. We test drove GPT-5.2 for Tursio’s structured data search and summarize our findings in this blog. 

Structured Data Search with Microsoft Context

Microsoft is a trusted provider across various industries, and given our core members spent years building Microsoft products, it is natural for us to treat Microsoft as a first-class citizen in our structured data search.

The Tursio Journey

Data is to businesses like corals are to seas -- critical, fascinating, and full of potential. Just like corals, data systems and technologies have stayed relevant even as the world kept looping through successive technology cycles, including mainframe, desktop, web, mobile, cloud, and now AI. Shi and I saw this opportunity with data transitioning into AI when we started Tursio.

From data modeling to knowledge graphs

Data modeling is essentially the process of building rich business context on top of raw data. However, building this context manually requires significant effort. A knowledge graph can subsume data modeling by providing the relevant context dynamically.

Navigating LLMs: Is newer the better for data tasks?

OpenAI released GPT-5 earlier this year and the tech community immediately jumped to upgrade their AI systems. This was a natural reaction given that every new GPT model has gotten substantially better over the years.

SQL Server 2014: A Milestone That Still Powers the World’s Data

While the rest of the world is racing toward the latest AI-native databases and cloud data platforms, I find myself reflecting on a product that’s now over a decade old — SQL Server 2014.

Why Search Scales Differently from Data or BI

Search box powered by AI is quickly becoming the new expectation for accessing enterprise data. However, interestingly, this search box can reside in multiple places: it can be right within the database platform where the data is stored, or in the BI tool where the dashboards are built, or be standalone like Tursio. In this blog, we discuss the scalability aspect with these different architectural choices.

From 80% to 100%: The Accuracy Marathon in Enterprise AI

When organizations evaluate AI solutions, accuracy often becomes the headline metric. But what those numbers don’t reveal is the story behind them: the people, processes, and persistence required to transform an engine from “good enough” to exceptional. This is critical since most AI tools struggle with accuracy and are anywhere between 50-80% accurate out-of-the-box, which is typically insufficient for production deployments. In this blog, we describe our war story of overcoming this gap, i.e., going from 80% to 100% accuracy in a production environment. In our experience, this journey is less about the technology itself and more about the collaboration that fuels its growth.