check_connectivity
ChatGPTPing tool to test connectivity and authentication. You can use this if other tool calls are failing to verify if the connection is working.
Data & Analytics
Overview
From everyday data questions to high-level strategic analyses, Spotter by ThoughtSpot helps business and data teams get answers and insights they can trust, validate, and act on, enabling everyone to use data to drive the business forward.
Tools
create_analysis_session
ChatGPTStart an analytical session with the Analytics Agent. This is the first step in a three-step workflow: create a session, send a message, then poll for updates. Once created, you can use the returned
analytical_session_id to send analytical questions via send_session_message and retrieve answers via get_session_updates. Sessions are conversational, so you can ask follow-up questions in the same session without creating a new one. Using a single analytical session is preferable, because it reuses the same data source selection.create_dashboard
ChatGPTCreate a dashboard from a list of answers, allowing the user to revisit the results later. You can use this if the user asks for a dashboard or liveboard, or asks to save the results from the analysis. This can be a useful way to save the results to revisit later, or present them to other users.
get_dashboard_status
ChatGPTContinue waiting for a dashboard that is still being built or changed. Call this when
create_dashboard or modify_dashboard returned status: "in_progress", passing the task_id they gave you. Each call waits a short while before returning, so calling it repeatedly is the correct way to wait. Keep calling until status is completed, needs_input or failed. Do not start a new create_dashboard or modify_dashboard call for the same work, or you will create duplicate dashboards. Check status: completed (give the user dashboard_url), in_progress (call get_dashboard_status again), needs_input (show message to the user and wait for their reply, then pass the reply in instructions to whichever tool started the task, with the same task_id: create_dashboard, or modify_dashboard plus its dashboard_id), failed (message says why; tell the user and ask before trying again, so you do not build a duplicate).get_session_updates
ChatGPTGet the latest updates from the Analytics Agent. You can call this after
send_session_message to retrieve the Agent's response. If is_done is false, you can call this tool again to continue polling, as the Agent is still generating a response. Even if is_done is false, you can use the updates to show status updates or progress to the user, so that they are informed about the ongoing process. An empty session_updates list while is_done is false is normal; it means the Agent is still thinking. When is_done is true, the Agent has finished and the results in session_updates are complete, so you can present them to the user. You can also send a follow-up message in the same session after is_done is true.list_orgs
ChatGPTList the Orgs the authenticated user can access on the ThoughtSpot instance, including the ID, name, and description of each Org. The Org marked
is_active: true is the one currently active for your account, which all tool calls operate against. Use this to tell the user which Org they are in. Only available when authenticated via OAuth. If the list is large , summarize or show only the most relevant orgs (e.g. the active one and a few others) rather than listing all of them, unless the user explicitly asks to see all orgs.modify_dashboard
ChatGPTChange an existing dashboard. It can rearrange and restyle what is already there, add new charts, add short explanatory text, and organise charts into groups or tabs.
dashboard_id is always required. Add task_id as well to continue something you already started, which is how you answer a question the designer asked you or send a follow-up instruction about the same dashboard. Pass the change in instructions in the user's words. If it is too vague to act on, the designer comes back with a question. New charts use the data sources the dashboard already has unless you say otherwise. Changes are saved to the user's real dashboard, so only call this when the user has asked for the dashboard to change. Changing a dashboard can take a few minutes, so this may return before it is finished. Check status: completed (give the user dashboard_url), in_progress (call get_dashboard_status again), needs_input (show message to the user and wait for their reply, then pass the reply in instructions to whichever tool started the task, with the same task_id: create_dashboard, or modify_dashboard plus its dashboard_id), failed (message says why; tell the user and ask before trying again, so you do not build a duplicate).search_objects
ChatGPTSearch for objects (Answers, Liveboards, Worksheets) in ThoughtSpot matching a given search term. Supports optional filters (types, owner, tag, modified_since, verified_only) and pagination (limit, cursor). Returns
results (ranked), plus next_cursor. Each result carries: object_id, title, type (LIVEBOARD | ANSWER | LIVEBOARD_VIZ | WORKSHEET; LIVEBOARD_VIZ is a viz pinned on a Liveboard — render it as 'Liveboard viz'), author_name, description, tags, last_modified (ISO-8601), verified, external_link, query (Answer/viz sage tokens; null for Liveboards) and confidence. Returns identifiers and metadata only — never the object's data or contents, and it does not run queries. Explaining an object is best grounded in its actual DATA, not this metadata: the fields here (title, description, query tokens, tags) describe an object, not its contents. description and query tokens are authoring metadata — they can be stale and are often copied verbatim across sibling vizzes, so two objects can share a byte-identical description while their data differs, which makes them unreliable for telling objects apart or explaining them. How to present the results: • Render as a table with fixed columns in this order: Object (the name, linked to external_link) · Type · Owner · Verified (✓ or —) · Last Modified. • Put the description and, for an Answer/viz, the query tokens as sub-lines under the name (e.g. '↳ sales by region, last 3 months') — never as their own columns. • Render last_modified as a plain date (2026-05-15), never the raw timestamp. • Lead with the top match; if the top 2–3 are close, present them as ranked candidates. • Never surface next_cursor or the numeric confidence in your prose. Outcomes other than a hit list: • status: "no_results" — the search ran but nothing matched. Tell the user nothing matched, and suggest broadening the term or dropping a filter. Do not invent results. • status: "error" — the search failed. Tell the user briefly using error.message; if error.retryable is true, offer to try again. Never show error.code.send_session_message
ChatGPTSend a message to a session with the Analytics Agent. The Agent may take some time to think and generate a response, so the response will not be returned immediately. Instead, you can use the
get_session_updates tool to query for the latest updates on the session. After the Agent finishes responding (when get_session_updates returns is_done: true), you can send another message to the same session to ask follow-up questions without creating a new session. Do not send a new message until the Agent has finished responding to the previous message (when get_session_updates returns is_done: true). If the user wants to create a dashboard, do not send a message with that request; instead use the create_dashboard tool.switch_org
ChatGPTSwitch the active Org. After switching, all subsequent tool calls (analysis sessions, answers, data sources, dashboards) operate against the selected Org. Pass an
org_id returned by list_orgs. If you do not have access to the Org, the switch fails and the active Org is unchanged. The selection is durable and shared across all of your sessions — it persists across reconnects and applies to your other active conversations; it resets only on re-authentication or after prolonged inactivity. Only available when authenticated via OAuth.check_connectivity
Claudecreate_analysis_session
Claudecreate_dashboard
Claudeget_session_updates
Claudesend_session_message
ClaudeCapabilities
Writes
Example Prompts
Click any prompt to copy it.
Links
App Stats
15
Tools
3
Prompts
ChatGPT, Claude
Platforms
Category
Data ExplorationWorks with
ChatGPT
Claude
Data refreshed daily