ThoughtSpot unveils AI agents to automate analytics

ThoughtSpot has launched a suite of four artificial intelligence agents that it says can automate most stages of the business intelligence workflow, from data modelling through to dashboard creation and embedded analytics.

The California-based analytics company has introduced SpotterModel, SpotterViz, SpotterCode and Spotter 3 as part of what it calls its Agentic Analytics Platform. The products sit alongside its existing core agent, Spotter.

ThoughtSpot positions the agents as a single set of tools that sit across data engineering, analysis, software development and business decision-making. The launch targets organisations that still rely on static dashboards and manual reporting.

The four agents are designed as a connected team. Each one focuses on a specific part of the analytics process but shares a common underlying platform.

“The era of the Agentic Enterprise is here, and it will be defined by platforms that move beyond merely answering questions to actually acting on them,” said Francois Lopitaux, SVP of Product Management, ThoughtSpot. “With our team of agents, we are delivering the industry's first unified platform that augments every role-analysts, data engineers, developers, and business users-with an intelligent agent that handles the manual work. It is the foundational element towards the autonomous enterprise, turning intelligence into an engine that continuously drives business forward and delivers ROI on your AI investments.”

SpotterModel targets data engineers and other technical users who manage data foundations. The agent uses natural language prompts for the creation and maintenance of semantic data models.

The tool generates governed, reusable models from user prompts. It selects tables, defines schema and creates joins that match pre-defined business logic.

ThoughtSpot has integrated SpotterModel with Snowflake, Databricks and dbt. The company says this can cut the time needed to generate or modify models from days to minutes.

The design shifts engineering effort towards architecture and planning. Routine upkeep and schema changes move into the agent.

SpotterViz focuses on dashboard and visualisation work for analysts. ThoughtSpot describes it as a “Liveboard agent”.

The agent automates layout, organisation, styling and publishing of dashboards. Users describe the dashboard in natural language and the system assembles the content.

This approach moves analysts away from manual dashboard building. It creates more time for interpreting trends and discussing results with business stakeholders.

SpotterCode targets software developers who embed analytics into applications. The agent sits inside popular integrated development environments such as Cursor, Claude Code, GitHub Copilot and Microsoft VS Code.

It acts as an AI pair programmer that focuses on ThoughtSpot Embedded. The agent reads the project context and generates code for connecting and embedding ThoughtSpot features.

SpotterCode follows the company’s recommended implementation patterns. It generates code that uses the ThoughtSpot software development kit and supports fully branded interfaces.

ThoughtSpot says this reduces friction for product teams that want application-level analytics. It also aims to standardise how developers embed the company’s tools across different apps.

Spotter 3 sits at the centre of the new line-up. ThoughtSpot describes it as a core intelligence engine that can work with both structured and unstructured data.

The agent connects with traditional data sources along with applications such as Slack and Salesforce. This gives users a wider view of business activity inside one interface.

Spotter 3 has self-checking features. It can answer a question, assess the quality of its own response and run follow-up analysis until it reaches what it judges as the most accurate output.

The agent also supports validation, Python coding and forecasting. ThoughtSpot says this reduces reliance on specialist data teams when business users need complex analysis.

Tekion, a cloud technology company in the automotive sector, is an existing ThoughtSpot customer. The firm uses ThoughtSpot for embedded self-service analytics in its platform.

“We initially chose ThoughtSpot because it delivered immediate, best-in-class, self-service analytics that we could integrate into our platform. We knew ThoughtSpot would be a great partner to work with as they are the organisation innovating for the true future of analytics,” said Shiva Somasundaram, Senior Director of Product, Tekion. “The new suite of agents looks promising - we are looking forward to putting them to use. We anticipate this will drastically reduce the time our analysts spend on manual tasks, allowing them to shift their focus entirely to high-value strategic interpretation. By automating complex workflows and accelerating our data preparation process, we are effectively optimising our teams to tackle critical, upstream projects.”

Industry analysts are also watching the launch. Ferraro Consulting follows developments in analytics and AI tools.

“The end goal of analytics is to get more people using insights to make decisions. ThoughtSpot's two pronged approach simultaneously empowers non-technical business users with accessible insight and dramatically boosts the productivity of data engineers and analysts with dedicated, role-based BI agents. This strategy accelerates data workflows and decision-making across the entire organisation,” said John Santaferraro, CEO of Ferraro Consulting.

ThoughtSpot has framed its product strategy around what it calls “agentic analytics”. The concept brings multiple role-specific agents into a single environment that spans data engineering, analysis and decision-making.

The company says this launch is the next phase of its autonomous roadmap. It plans future features that will let teams design and deploy custom agents.

Spotter 3 is available to selected customers now. ThoughtSpot will roll out the other agents across the analytics workflow over the coming months as part of its Agentic Analytics experience.