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.
SalesforceTableau Next reads from Salesforce Data 360 objects: a data model, a data lake, calculated-insight objects or uploaded files, with zero-copy access reaching into Snowflake, BigQuery, Redshift and Databricks from inside that boundary. The service runs in the cloud only, per the pages reviewed [1][2].
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.
SalesforcePublic Tableau Next and Agentforce pages describe Data 360 connectors as the route into outside systems; a named SAP or Oracle integration, and any path through MuleSoft, stays unstated 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.
SalesforceTableau Semantics models are built with AI assistance in the Semantic Model Builder, and a smart canvas reached general availability in the August 2026 release. Salesforce's pages describe the builder as an aid for data teams; whether business users can extend the model themselves stays unstated [1][4].
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.
SalesforceThree Agentforce skills sit behind Tableau Next: Data Pro prepares and models data, Concierge answers questions in plain language, and Inspector watches metrics. Whether row and column security shows up inside an answer, or the generated query is displayed, stays unstated on the pages reviewed [1][5].
Lima JunoPeople ask ChatLima in plain language, in its own screen, in Slack or in Microsoft Teams. Each answer shows its working: the ontology terms used, the systems read, the seconds taken and the query itself. 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.
SalesforceAgentforce Builder lets people describe an agent in plain language, while Agent Script configures a hybrid approach that mixes fixed workflow steps with model reasoning for more predictable runs. Salesforce positions this combination for admins and builders working inside the Agentforce 360 platform [6][7].
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.
SalesforceSalesforce names guardrails, an Einstein Trust Layer with zero data retention, and least-privilege data access as its governance layer, with escalation routes to a person; a graded, numbered autonomy setting comparable to Lima's is undocumented on the pages reviewed [7][8].
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.
SalesforceTableau Next includes a built-in workflow so a person can act at the point of insight, and Slack carries agent skills into daily work; whether an action reaches an outside ERP, and how that write is confirmed, stays unstated for Agentforce on the pages reviewed [1][8].
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.
SalesforceSalesforce documents test-case generation, session debugging and performance analytics for reviewing how an agent behaves over time, alongside audit trails from the Einstein Trust Layer; a record tying each decision to what a person later accepted or changed stays unstated on the pages reviewed [8][9].
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.
SalesforceTableau Next starts at $40 per user monthly, billed annually; Agentforce prices in parallel units, $0.10 per action or $2 per conversation, with 1-Editions from $550 per user monthly. Gartner names Salesforce a Leader in its 2026 Conversational AI Platforms quadrant, with secondary reports also placing Tableau as a Leader in the analytics quadrant [2][10][11].
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. 