Dataiku vs ThoughtSpot (2026)

Agents call managed tools, API endpoints, OpenAPI specs, local and remote MCP servers, Knowledge Bank search, LLM Mesh queries, web search, inline code and plugin tools, over connections secured per group.

Sourcedoc.dataiku.com/dss/latest/agents/index.htmlread 2026-09-27

AgentSpot agents act inside the tools teams already use, such as Salesforce, Slack, Asana and Jira, for example routing work through Slack and creating Asana tasks, across CRM, HCM and ERP systems.

The connector list runs past 60 systems, including Google Workspace, Microsoft 365, Notion, Snowflake, HubSpot, Zoho, Gong, Stripe, Rippling, Gusto, Zendesk, ServiceNow, GitHub, PagerDuty, Linear, Airtable and Zapier.

On the analytics side, every plan includes prebuilt data connectors, Essentials lists live connections to Snowflake, Databricks and Redshift, and Pro adds MCP connectors that bring business context to Spotter.

SourceThoughtSpot, thoughtspot.com/agentspot and /pricingread 2026-10-05

Structured visual agents define sequences with routing, delegation to other agents, parallel and for each branches, agentic loops and reflection blocks, alongside code agents and external agents from Snowflake Cortex, Databricks, AWS Bedrock and Google Vertex AI; Agent Hub can orchestrate a query across several agents.

Sourcedoc.dataiku.com/dss/latest/agents/structured-visual-agents/index.htmlread 2026-09-27

In AgentSpot a team describes the work and the platform assembles a team of agents with their tools, steps, logic and handoffs, and the team defines how those agents work together. Each agent is assembled from a plain language description, without code or templates, and carries out multistep actions across the systems the business runs on.

AgentSpot has a free plan with 25 credits a week and a Fleet plan at $1,650 a month with 250 credits a week. Inside the analytics platform, SpotterViz plans a story, generates the answers it needs and builds a complete Liveboard, from structure to layout and styling.

SourceThoughtSpot, thoughtspot.com/agentspot and /product/agents; thoughtspot.com/blog/introducing-agentspotread 2026-10-05

Agents run inside automation scenarios, which start on time based, dataset change, SQL query change, scenario completion or Python triggers without a person, and users reach agents in Slack (DM or mention), Microsoft Teams, Agent Hub, Agent Chat and through APIs.

Sourcedoc.dataiku.com/dss/latest/scenarios/index.htmlread 2026-09-27

AgentSpot runs workflows on a recurring schedule and on events, so agents act without a person starting each run; Spotter is also reachable embedded in Salesforce, ServiceNow, Slack and mobile. Examples include a weekly pipeline digest sent every Monday and an onboarding run that starts on each new hire's start date. Every analytics plan from Essentials up includes automated KPI monitoring and anomaly alerts, along with mobile apps for iOS and Android.

SourceThoughtSpot, thoughtspot.com/agentspot and /pricingread 2026-10-05

Knowledge Banks embed datasets and documents into vector stores that agents search through a Knowledge Bank Search tool with static, dynamic and agent inferred filters and document level security, with GraphRAG and automated RAG optimization also documented.

Sourcedoc.dataiku.com/dss/latest/agents/tools/knowledge-bank-search.htmlread 2026-09-27

Spotter's answers are grounded in verified business definitions in ThoughtSpot's semantic layer, which SpotterModel builds from raw data into governed semantic models. SpotterModel works from natural language rather than hand written SQL, and Spotter can work across structured and unstructured data, with Python and forecasting for deeper analysis. Pro plans list a semantic layer built for agents, and ThoughtSpot ties its answers to a patented search token architecture built for transparency.

SourceThoughtSpot, thoughtspot.com/product/agents and /pricingread 2026-10-05

Long term memory blocks store facts, such as preferences, and episodes from past conversations in memory banks, kept separately per user, shared by agents in a project through a default bank or split into named banks, and retrieved by LLM filtering and semantic search in later conversations. No retention period or delete path is stated.

Sourcedoc.dataiku.com/dss/latest/agents/structured-visual-agents/blocks/long-term-memory.htmlread 2026-09-27

AgentSpot describes memory that compounds, with each action drawing on past decisions, preferences and domain knowledge, but what is kept, for how long and how it is reviewed or deleted is not stated. The same page says agents learn and adapt from each interaction.

SourceThoughtSpot, thoughtspot.com/agentspotread 2026-10-05

Human approval set on a tool makes a visual agent pause before calling it and ask the user to confirm, optionally letting the person reviewing edit the tool inputs (not inside For Each, Parallel or Reflection sub sequences), and guardrails cover PII, prompt injection, toxicity, topic boundaries and bias.

Sourcedoc.dataiku.com/dss/latest/agents/tools/human-approval.htmlread 2026-09-27

The data team reviews and approves the semantic models SpotterModel generates before they are put to use, while the agent does the rest of the modeling work. SpotterModel maps relationships, dimensions and measures with a person validating the result. In AgentSpot, fine grained permissions set what each person can see and do, and no approval step before an agent acts is described.

SourceThoughtSpot, thoughtspot.com/product/agents and /agentspotread 2026-10-05

Dataiku offers SSO through SAML, OIDC, LDAP and Kerberos, MFA, user profiles, per project group and user permissions, connection security, user secrets and an audit trail. Its trust page lists ISO 27001:2022, ISO 27701, ISO 42001 and ISO 9001 certification, SOC 1 and SOC 2 Type II for Dataiku Cloud, and a HIPAA report.

Sourcedataiku.com/legal/trustread 2026-09-27

ThoughtSpot holds SOC 1, SOC 2, SOC 3, ISO 27001 and CSA STAR Level 1, and supports SAML and OIDC SSO, role based access and row and column level security. Data is encrypted with TLS in transit and AES 256 at rest, with keys held in a key management system, and multifactor authentication is supported. Login and activity logs are secured and monitored for anomalies.

Row level security and encryption come with every analytics plan from Essentials, while SSO over SAML, OAuth or OIDC, unlimited permission groups and advanced data encryption are Enterprise features. AgentSpot adds single sign on and role based access with strict data isolation.

SourceThoughtSpot, thoughtspot.com/trust/security, /pricing and /agentspotread 2026-10-05

Every LLM Mesh call returns a nested trace of the agent's LLM calls, guardrail steps, inputs, outputs, tokens and cost, viewed in the Trace Explorer (tree, timeline and explorer views), and the evaluation trajectory explorer replays tool calls in order; an audit trail records user actions.

Sourcedoc.dataiku.com/dss/latest/agents/tracing.htmlread 2026-09-27

AgentSpot logs every request, tool call and model interaction, and Spotter reasons through each step and shows it, so both the answer and the actions behind it can be traced. Across the platform, user login and activity logs are kept, secured and monitored for anomalies.

SourceThoughtSpot, thoughtspot.com/agentspot and /trust/securityread 2026-10-05

Dataiku runs as fully managed Dataiku Cloud or is installed on the customer's own infrastructure (Linux, macOS, experimental Windows) with hybrid options through sales, with installation, cloud and container deployment guides; locally running Hugging Face models keep inference in house.

Sourcedataiku.com/product/get-startedread 2026-09-27

Customers choose the data residency region for their ThoughtSpot environment based on compliance needs, with options across AWS, GCP and Azure. Embedded Enterprise customers can add VPN and VPC deployment options. Enterprise editions of both the analytics and embedded platforms support custom domains and multi tenant setups organized by customer organization.

SourceThoughtSpot, thoughtspot.com/trust/security and /pricingread 2026-10-05

Dataiku Solutions include named GenAI and agent solutions for separate jobs, Dynamic Selling Assistant, Supplier Management Assistant, Clinical Trial Intelligence Assistant, Medical Entity Extraction Assistant and Agentic Insights; Agent Hub distributes an organization's own governed agents and prompt library.

Sourceknowledge.dataiku.com/latest/solutions/index.htmlread 2026-09-27

ThoughtSpot ships four named, ready made agents: Spotter for analytical questions, SpotterModel for semantic modeling, SpotterViz for dashboards and SpotterCode for coding in IDEs. SpotterCode turns a short prompt into the code patterns, components and embed logic a developer needs.

On the analytics plans, Pro includes all four agents with 25 Spotter queries a month per user, and Enterprise makes them unlimited, while the free Developer plan for embedding includes the same core agents. AgentSpot publishes example agents such as New-Hire Onboarding Runner, Hiring Pipeline Digest and Interview Feedback Chaser.

SourceThoughtSpot, thoughtspot.com/product/agents, /pricing and /agentspotread 2026-10-05

Administrators define LLM Mesh connections to OpenAI, Azure OpenAI, Anthropic, AWS Bedrock and SageMaker, Microsoft Foundry, Google Vertex, Mistral, Cohere, NVIDIA NIM, Snowflake Cortex, Databricks foundation model APIs and locally running Hugging Face models, and agents pick from them, with cost control and rate limiting documented.

Sourcedoc.dataiku.com/dss/latest/generative-ai/llm-connections.htmlread 2026-09-27

Spotter works with GPT series models, Google Gemini, Snowflake Cortex and Claude, and the Spotter deployment docs include a Connect to your Large Language Model page for a customer's own LLM. Flexible LLM selection is listed as an Enterprise analytics feature. ThoughtSpot does not meter or charge for LLM tokens, so model use is covered by the subscription, and Pro includes unlimited tokens under platform governance.

SourceThoughtSpot, thoughtspot.com/product/agents and /pricingread 2026-10-05

Agents are exposed as A2A servers at a per agent public API endpoint with well known URI discovery and bearer API key auth, in JSON-RPC and SSE modes, beside a documented MCP server, the public REST API, the Python API and LangChain integration on developer.dataiku.com, and a plugin system.

Sourcedoc.dataiku.com/dss/latest/agents/a2a.htmlread 2026-09-27

The documented Spotter MCP Server at agent.thoughtspot.app, with OAuth or bearer token authentication and date based versions, lets Claude, ChatGPT, Gemini or custom clients run natural language queries, create Liveboards and visualizations and search content; it is an add on for Enterprise and Embedded plans, beside ThoughtSpot's REST API and embed SDK.

OAuth suits ready made clients and bearer tokens suit custom applications. The Spotter 3 version of the server adds advanced analytics, reasoning, forecasting and automatic selection of the data source. The free Developer plan gives up to 10 users a year of the REST embed API, the Visual Embed SDK and custom styles, themes and actions.

SourceThoughtSpot, developers.thoughtspot.com MCP integration docs and thoughtspot.com/pricingread 2026-10-05

The Evaluate Agent recipe scores answers and the path taken, with ordered and unordered tool call checks, RAGAS based LLM judges, BERTScore and custom metrics, stores results for side by side version comparison, and Agent Review lets builders and SMEs run test cases against an agent version with human verdicts overriding the judge.

Sourcedoc.dataiku.com/dss/latest/agents/evaluation.htmlread 2026-09-27

Spotter checks its own work and refines the result at run time; no test set, accuracy scoring or regression check for agents is described. Semantic models from SpotterModel are validated by people before they go into use.

SourceThoughtSpot, thoughtspot.com/product/agentsread 2026-10-05

The agent tool list covers APIs, MCP, knowledge search, code and an LLM side web search tool, with no browser or computer use tool documented.

Sourcedoc.dataiku.com/dss/latest/agents/index.htmlread 2026-09-27

No browser or desktop operation by Spotter or AgentSpot agents is described; they act through data connections and integrations. Reach into tools such as Figma, Miro, Canva and Zoom comes through the AgentSpot integration list.

SourceThoughtSpot, thoughtspot.com/agentspotread 2026-10-05