Tursio Product Updates: Towards 100x knowledge workers

Product

Use cases

About

Spotlight Stories

Tursio Product Updates: Towards 100x knowledge workers

Published: May 13, 2025

Shraddhaa Khanna

Share this post

Tursio Product Updates: Towards 100x knowledge workers

Knowledge workers are the backbone of modern enterprises. Yet, conversations with our customers reveal that knowledge workers struggle with productivity when it comes to enterprise data. Tursio empowers them with quick analyses using generative AI, and our latest product release is targeted to reducing friction and making Tursio AI work end-to-end for the knowledge workers.

Auto Mode – Ask Better, Ask Faster

Querying data sources can be overwhelming. We got the feedback that knowledge workers are often unaware of the underlying data schemas and structures, making it difficult for them to ask for the right piece of information. Therefore, we are introducing “Auto” mode to guide the users through the semantic model and help construct questions for getting the desired data. Tursio takes care of interpreting them correctly behind the scenes and generates backend queries.

“Auto” mode makes it simple. Instead of manually figuring out what to ask, just start typing your question. Tursio will walk you through it—step by step—using your semantic model. You get the right answers every single time without needing to know how to write perfect queries.

For example, a loan analyst asking "Show down payment trends for Accent, Accord and Taurus between 2010-2013" gets the trend data along with a detailed analysis without any syntax errors or second guessing.

Analyze Mode – Explore Deeper

Knowledge workers have more questions once they see an answer, a curiosity to dig deeper with open-ended analyses. Therefore, we are introducing “Analyze” mode to combine accurate data search with creative reasoning for holistic perspectives and fast decisions.

The “Analyze” mode

operates on the data retrieved already and helps users refine the answer, draw more insights, or simply combine the data with external knowledge available to the language models. Essentially, it helps leverage the creativity of language models while still grounding the response strictly to the facts.

For e

xample, a loan strategist can ask for forward looking perspective, e.g.,

“What should the expansion strategy be based on down payments and car model popularity?”. The response is still grounded in facts from their portfolio.

Persistent Sharing – Never Lose an Insight

Insights are valuable and knowledge workers want to share all the time. We got feedback that people want to share results with others for both verification and consumption purposes. Therefore, we now persist cached results into permalinks that can be shared and accessed anytime. Tursio still ensures access control to the underlying data.

Thus, important insights never vanish. Send it, save it, come back to it anytime. Whether it’s leadership, teams, or clients—you can now keep everyone on the same page.

Smarter PDF Export – Clean. Clear. Contextual.

We have revamped PDF report generation with support for large tables and wide layouts. The report truncates data results smoothly and backs it up with summarized highlights.

Thus, users can present very persuasive and insightful reports to their stakeholders, while also creating the artifacts for future reference.

User Recommended – Power of the Crowd

Knowledge workers do not work alone, and they want to recommend things they found to each other. We have now made it easier to surface upvoted insights as “User Recommended” questions, making asking questions a collaborative effort.

Users can discover questions their peers are asking and explore them for their own additional context.

Research Mode – Feeling Lucky

Finally, we introduce a “Research” mode for people who may not know what to ask or who would like to be surprised by what comes out. This is both experimental and open-ended, giving users the chance to try new things.

For example, a CLO may ask “How is my loan portfolio doing?”, an open-ended inquiry meant to be followed up with more specific questions.

Summary

This new product release is designed to make enterprise data accessible and actionable for knowledge workers—at every stage of their workflow.

With Auto, Analyze, and Research modes, plus better sharing and smarter exports, Tursio helps you go from questions to decisions faster.

Reach out to us if you want to try Tursio on your data. We would love to learn what you think. This is just the beginning — stay tuned for more updates!

Related blog posts

Context Graphs

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.

Alekh Jindal

nl2sql

query-complexity

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.

Shivani Tripathi