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.
UiPathUiPath's agents and robots operate inside Automation Cloud, acting through APIs, user interfaces and the systems a company already runs, with Maestro holding the case and process data that ties a run together [1]. Source data for a specific task stays wherever the underlying application keeps it.
Lima JunoYour rows stay in the systems that hold them. Juno registers each table through the Lima data fabric and reads it in place through the federated query engine, joining several sources 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.
UiPathUiPath's robots and APIs are built to work with legacy user interfaces and mainframes across a client's estate, alongside orchestration for process and case data in Maestro [1]. The pages reviewed describe this reach in general terms; a named SAP or Oracle connector and its exact fields stay a design choice made inside a client's own automation.
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.
UiPathPublic pages describe Maestro's case and process models, built in BPMN and flow notation, as the shared structure agents and robots follow through a run [1]. A broader semantic model or ontology spanning a client's systems, such as a common definition of a supply chain order, stays outside what the pages reviewed describe.
Lima JunoLima’s supply chain ontology arrives filled in: materials, plants, suppliers, orders, stock and the relationships between them. Juno proposes a mapping for each registered column, and your team confirms 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.
UiPathBusiness users describe a goal or an exception inside a process case, and UiPath's governance layer records every agent action, human decision and policy at business-transaction level for later review [1]. An open conversational box for ad hoc supply chain questions is a use a client builds on the platform, separate from Maestro's case-driven flow.
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.
UiPathProcess and automation teams define agents in Agent Builder and shape orchestration in Maestro through BPMN and case models, with agency set at design time and enforced when the process runs [1]. A registry then catalogues, versions, pauses and rolls back both UiPath's own agents and third-party ones.
Lima JunoOne agent runs in production, the PO cancellation agent, built from a policy a planner stated in plain language. Lima’s agent blueprint designs 960 further roles across five chains, yet to be built the same way: a planner states the intent and the Planner Agent drafts the rules for review. 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.
UiPathUiPath frames autonomy as controlled agency: what an agent may decide is fixed at design time in Maestro and enforced at run time, with human steps built into the process where the design calls for one [1]. A named, numbered autonomy ladder across levels is a structure the pages reviewed leave to the client to define.
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.
UiPathActions travel from UiPath's robots and APIs through to the system underneath, including screens on legacy applications, so an approved change can reach SAP or Oracle the same way a person would enter it [1]. A named confirmation step logged against each ERP write is a detail the pages reviewed leave to a client's own design.
Lima JunoWrite-back uses each ERP’s own released interfaces: 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. 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.
UiPathUiPath's registry captures every agent action, human decision and policy at business-transaction level, giving auditors one trail across people, robots and agents [1]. How an agent's own behaviour changes after a person edits or overrides one of its actions stays undocumented on the pages reviewed.
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.
UiPathUiPath's Community tier is free, Basic starts at $25 a month, and Standard offers a 60-day trial for building and running agents; Enterprise pricing is available on request [2]. Gartner named UiPath a Leader in its 2026 Business Orchestration and Automation Technology quadrant, after seven years leading the RPA quadrant, and its listing is the only one with ratings in Gartner's newer market for AI agent development platforms [3][4][6].
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.