The nine questions
The same nine questions, answered twice
Numbers in brackets point to the numbered sources at the foot of the page. The line under each question says what a complete answer contains.
1 · Where must the data live for questions and agents to work?
A complete answer names the systems the data has to be copied into, and the systems that are read where they stand.
ThoughtSpotThoughtSpot runs live queries straight on a customer's warehouse or database, reaching more than 30 platforms including Snowflake, BigQuery, Databricks, Redshift, Oracle and SAP HANA. Rows stay in the connected system, and ThoughtSpot's documentation states that joins across separate connections stay unsupported [1].
Lima JunoYour rows stay in the systems that hold them. Juno registers tables through the Lima data fabric and reads them in place, so a warehouse sits beside SAP, Oracle and planning data in one answer. 2 · How far does it reach into SAP, Oracle and planning systems?
A complete answer names the interface used for each system and says which of them are live today.
ThoughtSpotPublic pages list Oracle and SAP HANA among ThoughtSpot's warehouse connectors, alongside Snowflake, BigQuery, Databricks and Redshift, so ERP-adjacent data reaches Spotter once it sits in one of these systems. Direct connections into planning suites or SAP's own transaction tables stay undocumented on the pages reviewed [1][3].
Lima JunoMore than 40 connectors cover SAP ECC and S/4HANA, Oracle Fusion and E-Business Suite, planning suites, warehouse systems, lakes, databases, files and REST services. One question can join several of them, and the one agent in production, the PO cancellation agent, runs on federated ERP data the same way. 3 · How is the shared meaning, the semantic model or ontology, built, and by whom?
A complete answer says what arrives ready, what your team builds, and how long that modelling work takes.
ThoughtSpotA semantic model comes first: ThoughtSpot's documentation calls for data-model readiness before Spotter is turned on for a given model. SpotterModel, generally available in early 2026, builds these models from plain-language instructions, and G2 reviewers describe substantial preparation work before search-driven answers become reliable [4][9].
Lima JunoLima’s supply chain ontology arrives filled in: materials, plants, suppliers, orders and stock. Juno proposes a mapping for each registered column with a confidence and a reason; your team confirms, adjusts and extends it. 4 · How do business users ask questions, and is the working shown?
A complete answer shows the question, the query that ran, the sources read and the access rules applied.
ThoughtSpotPeople type or speak a question in ThoughtSpot's search bar; Spotter 3 plans multi-step analysis, checks its own steps, and can run inside Claude or ChatGPT through MCP. The search tokens and generated SQL stay visible beside every answer, which ThoughtSpot markets as a verifiable, source-checked result [1][4].
Lima JunoPeople ask ChatLima in plain language. Each answer shows its working: the ontology terms used, the systems read, the seconds taken and the query itself, under the asking person’s row and column access. 5 · How are agents and rules defined, and by whom?
A complete answer says who writes a rule, in which language, and how it is reviewed before it runs.
ThoughtSpotSpotter answers each question fresh from search tokens and a model; ThoughtSpot's public material describes reference questions, business-term glossaries and model instructions that data teams and administrators maintain to steer its answers over time, plus personal memory that individual users build up through their own sessions [4].
Lima JunoA planner writes the policy in plain language, and the Planner Agent turns it into a reviewable planning table of tasks, data and rules. The PO cancellation agent, built this way, runs in production; Lima’s agent blueprint designs 960 further roles across five chains, the other supply chain task agents among them, yet to be built. 6 · How is autonomy set, and how do approvals work?
A complete answer gives the levels available, who approves what at each one, and how a level is raised and lowered.
ThoughtSpotThoughtSpot's pages, reviewed through February 2026, describe search-driven answers and analysis; a graded autonomy setting or an approval queue for actions is undocumented there. Spotter plans and runs its own analysis steps, and a person reviews the result ahead of acting on it [1][5].
Lima JunoEach agent carries a level you set, A0 to A4. At A2 a named person approves every action; at A3 the agent acts inside value, budget and confidence limits and sends exceptions to people. The level is one of eight settings on an agent, each set by a named person. 7 · How do actions reach the ERP, and is each write confirmed?
A complete answer names the interface for each ERP and says where the acknowledgement of a write is kept.
ThoughtSpotPublic reporting through February 2026, including a TechTarget review of the Analyst Studio update, describes ThoughtSpot as an analysis and answer layer; a path for actions to reach an ERP, with acknowledgement, stays undocumented on the pages reviewed [5].
Lima JunoWrite-back uses each ERP’s own supported interfaces: released APIs and BAPIs for SAP, REST resources and interface tables for Oracle. It starts per application after a confirmed test write, and every write keeps the acknowledgement. The PO cancellation agent in production writes back this way, under human approval. 8 · How does it learn from people’s decisions, and what is audited?
A complete answer says what is recorded for each decision and how that record shapes the next recommendation.
ThoughtSpotThoughtSpot's documented feedback loop centres on people teaching Spotter: saved reference questions, corrected business terms and memory built from Liveboards and past conversations, with coaching that administrators can publish across an organisation. A record of individual decisions and an audit trail for actions stay undocumented on the pages reviewed [4][8].
Lima JunoEvery accept, edit and override is stored with the rule version, the facts at that moment and the outcome, so the next recommendation improves. The audit trail holds signal, reasoning, limits, approval, action and acknowledgement for each run; in production, 100% of the cancellation agent’s actions trace to a rule. 9 · What is the pricing unit, is there a trial, and where do analysts place it?
A complete answer names the unit of charge, the route to try it, and the analyst reports that cover the category.
ThoughtSpotEssentials costs $25 and Pro $50 per user each month, with Pro capped at 25 Spotter queries per user monthly and Enterprise priced by quote; a 14-day trial is offered card-free. Gartner names ThoughtSpot a Leader in both its 2026 and 2025 quadrants for Analytics and Business Intelligence Platforms [6][7].
Lima JunoJuno is licensed with the Lima platform and priced per engagement. The token manager budgets and meters every model call, per agent and per team. Twenty use cases are worked through on this site, one page each, and the analyst guide sets out the markets these products sit in. 