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.
o9 Solutionso9's agents work inside the Enterprise Knowledge Graph, o9's own planning model; a customer's data reaches that graph through o9's implementation, and whether source systems stay queried in place or are loaded into the platform stays undocumented on the pages reviewed [1][2].
Lima JunoYour rows stay where they are. Juno registers tables from the planning suite, the ERP and the other systems through the Lima data fabric and reads them in place, joining them 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.
o9 Solutionso9 positions itself as the planning system that holds the data, so reach into SAP, Oracle or a separate planning suite runs through o9's own implementation; specific connector detail stays undocumented on the pages reviewed [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.
o9 Solutionso9 calls its approach neurosymbolic: a language model paired with the symbolic Enterprise Knowledge Graph, so o9 states each reasoning step stays traceable back to the graph. The graph itself is built and maintained through o9's implementation process, and a customer self-service option for extending it stays undocumented on the pages reviewed [3][1].
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.
o9 SolutionsComposite agents chain together smaller atomic agents for tasks such as forecast build, root-cause analysis and month-on-month change review; o9's APEX preview in June 2026 showed an agent writing an executive narrative from a demonstration on excess stock. Whether business users can also type an open question in plain language stays undocumented on the pages reviewed [1][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.
o9 Solutionso9 builds composite and atomic agents from planning experts' recorded working patterns and ongoing user feedback, refined inside the Enterprise Knowledge Graph; a public studio for business users to define their own agents stays undocumented on the pages reviewed [1][2].
Lima JunoA planner writes the policy in plain language; the Planner Agent turns it into a reviewable planning table, simulated on past data, and the Lima Rules Engine executes the published version the same way every time. That is how the one agent in production, the PO cancellation agent, runs; Lima’s agent blueprint designs 960 further roles, 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.
o9 Solutionso9 states that its 2026 APEX direction will progressively automate well-governed decisions and workflows, though a graded, numbered autonomy setting comparable to Lima's A0 to A4 scale stays undocumented on the pages reviewed [6].
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.
o9 SolutionsAB InBev is cited as running 90 percent of its planning processes through o9 on its own, yet a path for an agent's action to write into an outside ERP, with an acknowledgement recorded, stays undocumented on the pages reviewed [4].
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.
o9 Solutionso9 describes its neurosymbolic design as keeping every reasoning step traceable to the knowledge graph behind it, and composite agents learn from planning experts' recorded patterns; a record tying one person's individual accepted or overridden recommendation to a later audited outcome stays undocumented on the pages reviewed [3][1].
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.
o9 SolutionsA public pricing unit or self-serve trial stays undocumented on the o9 pages reviewed. Gartner names o9 a Leader in both its 2026 quadrants for Supply Chain Planning Solutions and a Niche Player in its 2026 quadrant for Decision Intelligence Platforms, and o9 was the sole Customers' Choice in the 2025 Peer Insights review of supply chain planning [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.