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.
Google CloudLooker's conversational layer reads through LookML models across more than fifty SQL databases, while BigQuery's own conversational analytics covers tables, views, graph data and federated sources such as AlloyDB, Cloud SQL, Spanner and SAP Datasphere, up to 100 knowledge sources per agent [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.
Google CloudBigQuery's federated queries reach SAP Datasphere directly, and Looker connects to more than fifty SQL databases through LookML; a named, direct route into SAP or Oracle transaction tables beyond Datasphere stays unstated on the pages reviewed [2][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.
Google CloudA LookML model, written by developers, comes first for Looker, and G2 reviewers name its learning curve as the platform's most-cited drawback. BigQuery agents draw on business glossaries and verified queries that a data team maintains alongside the model [3][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.
Google CloudPeople type a question in Looker or BigQuery's chat interface; Looker answers with a chart or number and an explanation of how it was worked out, while BigQuery shows its reasoning and labels each job for a SQL audit. Google's own documentation states that an answer can look plausible yet still be mistaken [3][5].
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.
Google CloudLooker and BigQuery agents are configured by data teams through business glossaries, default filters, hidden fields and verified reference queries; a business user builds an agent through Gemini Enterprise's guided workflow builder or the open-source Agent Development Kit for custom code [3][4][6].
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.
Google CloudGemini Enterprise applies a Semantic Governance Policy that states tool-call limits in plain language, together with Model Armor screening and customer-managed keys; a graded, numbered autonomy setting matching Lima's ladder is undocumented on the pages reviewed [6][7].
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.
Google CloudBigQuery's conversational agents keep to read-only queries; Looker's marketing mentions triggering downstream actions, and the mechanism for a confirmed write into an ERP stays unstated on the pages reviewed [3][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.
Google CloudAgent instructions, business glossaries and verified queries are the documented feedback path for both Looker and BigQuery, refined by a data team over time. A record tying an individual person's accepted or overridden recommendation to a later outcome stays unstated on the pages reviewed [3][4].
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.
Google CloudLooker prices by quote per edition; its conversational layer runs free during a promotional period, then meters tokens with a Standard allowance of 60 million input and 1.2 million output tokens monthly. Gemini Enterprise starts at $21 to $30 per seat monthly with a 30-day trial, and Gartner names Google a Leader in its 2026 Analytics and Business Intelligence and Conversational AI Platform quadrants [4][9][10].
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. 