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.
ServiceNowServiceNow's AI Agents draw on data already inside the Now Platform: workflow records and the configuration management database that anchors IT, HR and customer service cases [1]. Knowledge 2026 added thirty connectors so AI Control Tower can see agents and models running on AWS, Google Cloud, Azure, SAP, Oracle and Workday [3].
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.
ServiceNowAI Control Tower's 2026 connectors give visibility into agents and models running on SAP, Oracle, Workday and the major clouds, so ServiceNow can list and govern them centrally [3]. Reaching into a specific SAP or Oracle transaction for a workflow is a build task carried out by the client or a partner through ServiceNow's own integration tools [2].
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.
ServiceNowServiceNow's shared reference point is the configuration management database, extended by each workflow's own data model for IT, HR or customer service [1]. A semantic model mapped specifically to supply chain meaning across SAP, Oracle or a planning system stays a project the client or a partner builds on top [2].
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.
ServiceNowEmployees reach ServiceNow's agents through the request or case they raise in IT, HR or customer service, with roles and tools coordinated by an AI Agent Orchestrator behind the scenes [1]. A shared conversational box for open supply chain questions, and a reasoning trace shown with each answer, stay undocumented on the pages reviewed [1].
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.
ServiceNowAgents are assembled in AI Agent Studio from prebuilt roles, tools and out-of-the-box agents, coordinated by an AI Agent Orchestrator; an AI Agent Advisor suggests where an agent could take on the next task [1]. The platform team configuring each workflow does this definition work, using the building blocks AI Agent Studio supplies [1].
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.
ServiceNowKnowledge 2026 added a kill switch for a compromised agent and token-cost dashboards inside AI Control Tower, which also blocks prompt injection and tracks value against a stated goal [3]. Named approval steps and execution modes for each agent stay undocumented on the product pages reviewed, beyond the kill switch itself [2].
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.
ServiceNowPages reviewed describe Action Fabric letting outside agents such as Claude or Copilot trigger governed ServiceNow actions through an MCP server, which is the reverse direction from writing into an ERP [1]. How a write specifically reaches SAP or Oracle, and its acknowledgement, stay undocumented on the pages checked [1].
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.
ServiceNowAI Control Tower tracks value and return on investment, meters token cost per team, and ships content packs for the EU AI Act and the NIST AI Risk Management Framework [3]. How ServiceNow's agents learn from a person's override of a recommendation stays undocumented on the pages reviewed [3].
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.
ServiceNowServiceNow prices AI Agents through consumption units called assists, with per-action values kept private [4]; product pages point to a demo booking and a value calculator, with a self-service trial absent from the pages reviewed [1]. Analysts place ServiceNow as a Leader in Gartner's first quadrant for Business Orchestration and Automation Technologies and in ISG's 2025 AI Agents study [5][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.