ThoughtSpot AI API
The AI API from ThoughtSpot — 26 operation(s) for ai.
ThoughtSpot AI API is one of 29 APIs that ThoughtSpot publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Artificial Intelligence. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, a getting-started guide, and authentication docs.
This API exposes 26 operations across 26 paths, and defines 64 schemas. It is described by OpenAPI 3.2.0, at version 2.0.
Requests are made against a single base URL, {base-url}.
26 operations
26 paths
64 schemas
1 DELETE6 GET18 POST1 PUT
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 1
ThoughtSpot AI API declares
1 security scheme
for authenticating requests.
It accepts HTTP bearer tokens (bearerAuth).
By default, every request must be authenticated.
Paths & Operations 26
Across 26 paths, the API surfaces 26 operations — 1 DELETE, 6 GET, 18 POST, 1 PUT. Each is listed below with its method, path, parameters, and response codes.
AI 26
POST
/api/rest/2.0/ai/agent/conversation/create
Version: 26.2.0.cl or later Version: 26.2.0.cl or later Creates a new Spotter agent conversation based on the provided context and settings. The endpoint was in Beta from 26.2.0.cl through 26.4.0.cl.…
POST
/api/rest/2.0/ai/conversation/create
Beta Version: 10.4.0.cl or later Version: 10.4.0.cl or later Creates a new conversation session tied to a specific data model for AI-driven natural language querying. Requires CANUSESPOTTER privilege…
DELETE
/api/rest/2.0/ai/agent/conversations/{conversation_identifier}/delete
Deletes an existing agent conversation. Version: 26.7.0.cl or later Permanently deletes an existing saved agent conversation and all its associated messages. This operation is irreversible — deleted…
POST
/api/rest/2.0/ai/memory/export
Exports memory entries (rules, recipes, and always-apply rules) for the specified data-models as a single YAML payload. The payload can be edited locally and re-submitted through importMemory. Requir…
GET
/api/rest/2.0/ai/agent/instructions/get
Beta Version: 26.6.0.cl or later Retrieves the admin instructions currently configured for the AI agent (Spotter). Admin instructions are tenant- and org-scoped text that guide agent behavior across…
GET
/api/rest/2.0/ai/agent/conversations/{conversation_identifier}/messages
Retrieves the full public-safe content of a saved agent conversation: ordered turns (user messages and agent response items) and sanitized code-execution file metadata. Internal graph or branch state…
GET
/api/rest/2.0/ai/agent/conversations
Retrieves the list of saved agent conversations for the currently authenticated user. Only conversations created with enablesavechat: true are returned. Version: 26.7.0.cl or later Retrieves a pagina…
POST
/api/rest/2.0/ai/data-source-suggestions
Beta Version: 10.15.0.cl or later Suggests the most relevant data sources for a given natural language query, ranked by confidence with LLM-generated reasoning. Requires CANUSESPOTTER privilege and a…
POST
/api/rest/2.0/ai/instructions/get
Beta Version: 10.15.0.cl or later Retrieves existing natural language (NL) instructions configured for a specific data model. These instructions guide the AI system in understanding data context and…
POST
/api/rest/2.0/ai/relevant-questions/
Beta Version: 10.13.0.cl or later Breaks down a natural language query into a series of smaller analytical sub-questions, each mapped to a relevant data source. Requires CANUSESPOTTER privilege and a…
GET
/api/rest/2.0/ai/agent/conversations/{conversation_identifier}/get-shared-content
Returns the full read-only view of a shared conversation, including ordered messages and data source metadata. Accessible by the conversation owner and any principal (user or group) that has been gra…
GET
/api/rest/2.0/ai/agent/conversations/{conversation_identifier}/get-share-info
Returns the current share state for a conversation the caller owns: whether the shared view is outdated relative to the latest conversation content, and the list of principals that currently have acc…
POST
/api/rest/2.0/ai/memory/import
Imports memory entries (rules, recipes, and always-apply rules) from a YAML payload, typically a payload produced by exportMemory and edited locally. The imported entries replace the existing memory…
GET
/api/rest/2.0/ai/agent/conversations/{conversation_identifier}/answers/{answer_identifier}/details
Loads the full answer payload for a specific answer item in an agent conversation. Returns structured answer data including the TML query, token breakdown, visualization metadata, and agent context s…
POST
/api/rest/2.0/ai/analytical-questionsdeprecated
Beta Version: 10.7.0.cl or later Version: 10.7.0.cl or later Deprecated — Use getRelevantQuestions instead (available from 10.13.0.cl). Breaks down a topical or goal-oriented natural language questio…
POST
/api/rest/2.0/ai/agent/conversation/{conversation_identifier}/send
Version: 26.5.0.cl or later Version: 26.5.0.cl or later Sends natural language messages to an existing Spotter agent conversation and returns the complete response synchronously. Requires CANUSESPOTT…
POST
/api/rest/2.0/ai/agent/conversation/{conversation_identifier}/send/stream
Version: 26.5.0.cl or later Version: 26.5.0.cl or later Sends one or more natural language messages to an existing Spotter agent conversation and returns the response as a real-time Server-Sent Event…
POST
/api/rest/2.0/ai/agent/{conversation_identifier}/conversedeprecated
Beta Version: 26.2.0.cl or later Deprecated — Use sendAgentConversationMessage instead. Send natural language messages to an existing Spotter agent conversation and returns the complete response sync…
POST
/api/rest/2.0/ai/agent/converse/ssedeprecated
Beta Version: 26.2.0.cl or later Deprecated — Use sendAgentConversationMessageStreaming instead. Sends one or more natural language messages to an existing Spotter agent conversation and returns the…
POST
/api/rest/2.0/ai/conversation/{conversation_identifier}/converse
Beta Version: 10.4.0.cl or later Sends a follow-up message to an existing conversation within the context of a data model. Requires CANUSESPOTTER privilege and at least view access to the metadata ob…
PUT
/api/rest/2.0/ai/agent/instructions/set
Beta Version: 26.6.0.cl or later Creates or updates the admin instructions for the AI agent (Spotter). Admin instructions are tenant- and org-scoped text that guide agent behavior across all conversa…
POST
/api/rest/2.0/ai/instructions/set
Beta Version: 10.15.0.cl or later This API allows users to set natural language (NL) instructions for a specific data-model to improve AI-generated answers and query processing. These instructions he…
POST
/api/rest/2.0/ai/agent/conversations/{conversation_identifier}/share
Grants or revokes access to a shared conversation for one or more principals (users or groups). When principals are added, a read-only shared view of the conversation is created from its current stat…
POST
/api/rest/2.0/ai/answer/create
Beta Version: 10.4.0.cl or later Processes a natural language query against a specified data model and returns a single AI-generated answer without requiring a conversation session. Requires CANUSESP…
POST
/api/rest/2.0/ai/agent/conversation/{conversation_identifier}/stop-response
Stops an in-progress agent conversation response. Version: 26.6.0.cl or later Version: 26.6.0.cl or later Stops an in-progress agent response for the specified conversation. Use this endpoint to canc…
POST
/api/rest/2.0/ai/agent/conversations/{conversation_identifier}/update
Updates attributes of an existing agent conversation. Currently only the display title can be updated; additional conversation attributes may be supported in future versions. At least one updatable a…
Schemas 64
The contract defines 64 schemas that model the data the API accepts and returns. The most detailed are AnswerDetails (10 properties), QueryGetDecomposedQueryRequest (7 properties), ImportSummary (6 properties), AgentConversationList (6 properties). Each schema is shown below with its type and property counts.
eureka_DataSourceSuggestionResponse
object
1 property
SendMessageRequest
object
2 properties
2 required
ConversationMessageResponse
object
Response body of getConversation. messages is ordered oldest to newest. codeexecutionfiles is a list of sanitized code-execution file metadata entries, keyed i…
2 properties
eureka_RelevantQuestion
object
3 properties
ContextPayloadV2Input
object
2 properties
AnswerDetails
object
10 properties
ImportFailure
object
One per-item import failure surfaced by importMemory. linenumber is the best-effort line number in the uploaded YAML; fieldname is a dotted path within the ite…
4 properties
AgentConversationList
object
A saved agent conversation item returned in list responses.
6 properties
1 required
ImportMemoryRequest
object
2 properties
2 required
ExportMemoryResponse
object
Response from exportMemory. Contains the serialized payload ready for local editing and re-submission to importMemory.
1 property
EntityHeader
object
3 properties
QueryGetDecomposedQueryRequest
object
7 properties
SingleAnswerRequest
object
2 properties
2 required
SendAgentMessageResponse
object
2 properties
1 required
MemorySources
object
A single typed scope group identifying objects whose memory entries should be exported. One group binds a single type to a set of identifiers; pass one or more…
2 properties
2 required
ImportDiagnostic
object
A group of importMemory diagnostic messages that share a severity / disposition. This is the single, uniform channel for fatal errors, rollbacks, and non-fatal…
2 properties
ExportMemoryRequest
object
1 property
1 required
DataSource
object
3 properties
eureka_LLMDecomposeQueryResponse
object
1 property
ConversationMessage
object
One conversational exchange: an optional user prompt (message and attachments), followed by the agent's response items for that turn.
4 properties
2 required
AIContext
object
2 properties
ConversationSettingsInput
object
4 properties
CodeExecutionFileMetadata
object
Sanitized public metadata for a code-execution-generated file. Internal storage identifiers (e.g. Azure blob ids) are deliberately not exposed.
5 properties
2 required
SendAgentConversationMessageRequest
object
1 property
1 required
ImportTargetSource
object
Identifies the target object a group of import counts applies to. type is the source kind (DATAMODEL) and identifier is the object's GUID.
2 properties
eureka_LLMSuggestedQuery
object
3 properties
SendAgentMessageRequest
object
1 property
1 required
ShareConversationRequest
object
4 properties
2 required
SendAgentConversationMessageStreamingRequest
object
1 property
1 required
Input_eureka_NLSRequest
object
4 properties
SetNLInstructionsRequest
object
2 properties
2 required
AgentInstructions
object
Admin instructions configured for the AI agent.
5 properties
1 required
UpdateConversationRequest
object
1 property
UserPrompt
object
User-authored prompt for a conversation turn: the user's text message and any files or connector resources attached to it.
2 properties
CreateConversationRequest
object
2 properties
1 required
AgentConversation
object
2 properties
2 required
GetNLInstructionsRequest
object
1 property
1 required
SharedConversationResponse
object
Response returned by getSharedContent. Contains the full read-only view of the shared conversation including messages and data source metadata.
6 properties
5 required
eureka_DecomposeQueryResponse
object
1 property
ConversationShareStatusResponse
object
Response returned by getShareInfo.
3 properties
2 required
AgentConversationHistoryResponse
object
Response returned by getConversationList.
2 properties
SetAgentInstructionsRequest
object
1 property
1 required
NLInstructionsInfo
object
2 properties
2 required
eureka_SetNLInstructionsResponse
object
1 property
1 required
ErrorResponse
object
1 property
ImportMemoryResponse
object
Response from importMemory. On SUCCESS, summary is fully populated. diagnostics carries any fatal errors, rollbacks, and non-fatal warnings produced during the…
5 properties
1 required
eureka_GetRelevantQuestionsResponse
object
1 property
DataSourceContextInput
object
3 properties
MetadataContext
object
4 properties
ResponseMessage
object
6 properties
1 required
LoadAnswerResponse
object
1 property
NLInstructionsInfoInput
object
2 properties
2 required
eureka_GetNLInstructionsResponse
object
1 property
1 required
UserMessage
object
User-authored text message that begins a conversation turn. Null when the turn is a synthetic liveboard-started first turn.
2 properties
2 required
SendAgentMessageStreamingRequest
object
2 properties
2 required
DataSourceEntry
object
A data source associated with a conversation, returned as a typed entry.
2 properties
2 required
GetRelevantQuestionsRequest
object
5 properties
2 required
CreateAgentConversationRequest
object
2 properties
2 required
Conversation
object
1 property
1 required
ACState
object
2 properties
GetDataSourceSuggestionsRequest
object
1 property
1 required
ImportSummary
object
Per (memory type, target source) summary of what importMemory did — or would do, in DRYRUN. deletedrecordcount and insertedrecordcount are previews in DRYRUN a…
6 properties
PrincipalRefInput
object
Input reference to a principal (user or group) used when granting or revoking access to a shared resource.
2 properties
2 required
ConversationPrincipalInfo
object
A principal that has been granted access to a shared conversation.
5 properties
5 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from ThoughtSpot 12
Other APIs ThoughtSpot publishes across the network.
ThoughtSpot Authentication API
ThoughtSpot Collections API
ThoughtSpot Connection Configurations API
ThoughtSpot Connections API
ThoughtSpot Custom Action API
ThoughtSpot Custom Calendars API
ThoughtSpot Data API
ThoughtSpot DBT API
ThoughtSpot Email Customization API
ThoughtSpot Groups API
ThoughtSpot Input Tables API
ThoughtSpot Jobs API
#Artificial Intelligence
Where this information came from
This is an independent, third-party profile of ThoughtSpot AI API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.