ThoughtSpot Deploys AI Agents to Deliver Modern Analytics

For data and analytics leaders, agentic AI is driving an unprecedented pace of change. But understanding the need to act and knowing exactly what to do are two different challenges. Fortunately, companies like ThoughtSpot are ready to help—dedicated, in their own words, to "reimagining analytics and BI from the ground up."

“Agentic systems are truly moving us into new territory,” says Jane Smith, Field Chief Data and AI Officer at ThoughtSpot. “We're shifting from passive reporting to active decision-making.”

“Traditional BI waits for you to uncover insights,” Jane continues. “Agentic systems, on the other hand, monitor multiple data sources around the clock. They diagnose why changes occur and automatically trigger the next steps.”

“The emphasis is increasingly on action.”

In addition to the move from passive to active, Jane highlights two other shifts in BI: the true democratization of data, and renewed focus on the semantic layer. “You can’t have an agent taking action as I described unless it fully understands business context,” she notes. “A robust semantic layer is essential for bringing order to the complexity of AI.”

ThoughtSpot offers a range of agents designed to drive meaningful outcomes for customers. In December, the company introduced four new BI agents, built to work together as a team to deliver modern analytics.

Spotter 3, the latest version of an agent first released in late 2024, stands out. It integrates with platforms like Slack and Salesforce, not only answering questions but also evaluating the quality of its responses and refining them until it gets it right.

“Using the Model Context Protocol, Spotter 3 lets you query your organization’s structured data—everything in your rows, columns, and tables—while also incorporating unstructured data,” Jane explains. “That means you get highly contextual answers through our agent, or through your own LLM if you prefer.”

With this capability comes responsibility. As highlighted in ThoughtSpot’s recent eBook on data and AI trends for 2026, executives must design systems where every decision—human or AI—can be explained, improved, and trusted.

ThoughtSpot refers to this emerging framework as “decision intelligence” (DI). “We'll see more of what I call decision supply chains,” Jane says. “Rather than one-off insights, we'll see decisions flow through repeatable stages: data analysis, simulation, action, and feedback. These human-machine interactions will be logged in what we consider a decision system of record.”

What does this look like in practice? Jane gives an example from pharmaceutical clinical trials. “The system would log and version every step: how a patient is selected, how health records identify a candidate, how the decision aligns with the trial protocol, the matching process, and how a doctor ultimately recommends the patient,” she explains.

“These processes can be audited and improved for future trials. By meticulously recording each element of the decision flow—like a supply chain—we create a clear, traceable framework.”

ThoughtSpot will be at the AI & Big Data Expo Global in London, February 4–5. Watch the full interview with Jane Smith below:

Photo by Steve Johnson on Unsplash