Ontology Operating Principles

Ontology Operating Principles is the reference document to read before using the ontology features in EXAWin+. It does not enter or modify data. It explains how EXAWin+ understands sales reality and how Decision Console, Ontology Inspector, and Ontology AI operate on that structure.

Location: Sidebar → Ontology → Ontology Operating Principles

What The Ontology Means

In EXAWin+, the ontology is not just a database table or a visual graph. It is a structure that connects sales projects, customers, contacts, activity records, selected signals, stages, Bayesian snapshots, recommendations, and execution results into one sales world that can be judged.

A normal CRM stores records. The EXAWin+ ontology makes those records explainable as relationships. A deal is connected to the customer, contacts, stage, activity timeline, signals, Bayesian updates, and recommendation history. Because this connected structure exists, the system can explain why a deal specified by project code and deal name is in its current state, which evidence affected the judgment, and where the next action should be found.

Why It Is Needed

The goal of ontology is not to show an impressive graph. The goal is to improve decision quality and execution quality.

In sales, the same number can mean different things in different contexts. The same P(Win) should be read differently when recent customer response is strong versus when a deal has been silent for a long time. The same strong-positive signal can have a different meaning depending on the stage, the contact involved, and the follow-up action that came with it.

Ontology keeps this context connected. EXAWin+ therefore does not stop at showing probability. It connects the probability to the evidence that created it and to the next evidence the team should confirm.

What EXAWin+ Connects

The EXAWin+ ontology connects objects created in actual sales operations.

Customer and contact records provide the business and human context. Projects sit on top of that context and carry stage and company-level Bayesian settings. Activities create the timeline. Users record meetings, calls, emails, and online sessions, then select the signals observed in those interactions.

Selected signals become input to Bayesian updates. Updates produce P(Win), alpha, beta, confidence, silence, momentum, and decision impedance. Decision Console reads this structure to explain bottlenecks and next evidence candidates. Ontology Inspector lets users inspect the object relationships and JSON projection in read-only mode. Ontology AI uses work data, documents, theory, and evidence graphs within the permission scope to provide natural-language evidence analysis.

People And AI Read The Same Decision World

The ontology is not only for people and not only for AI. It creates one operating world that both people and AI can read.

Users record activities and select signals in Activity War Room. The system connects those records to Bayesian judgment. Decision Console presents the judgment in a form people can review. Ontology AI uses the same evidence structure to answer user requests.

AI does not freely read raw database tables and act on them. The server prepares a controlled judgment context with permission, evidence, validation, and audit boundaries. Ontology is therefore not a loose data dump for AI. It is a decision structure that people can review and the server can govern.

When To Read This Document

Read this document when a new user needs to understand the ontology menu, when a product evaluator asks where Decision Console judgments come from, when the meaning of Ontology Inspector nodes must be explained, or when the evidence scope of Ontology AI must be clarified.

It is especially useful when explaining how EXAWin+ differs from a record-centered CRM. EXAWin+ does not merely store records. It connects records, judgment, recommendations, and execution outcomes into one operating structure.

Relationship With Other Ontology Screens

Ontology Operating Principles is the baseline document. Ontology Inspector shows the principles with actual data by projecting deals, activities, and belief snapshots into read-only relationships and JSON.

Decision Console uses the same structure in live decision work. It shows the selected deal's Bayesian state, bottlenecks, next evidence candidates, similar context, recommendation adoption, and follow-up tracking. AI analysis is included inside Decision Console as an explanation layer for judgment.

Ontology AI is the natural-language evidence analysis panel opened from the right side of the screen. It can use the project selected in the panel, a project code and deal name included in the request, screen-identification context such as path and title, all projects, official documents, and blog/theory documents. Current-screen scope identifies the screen and explains purpose or review order; it does not automatically analyze every piece of visible data or a selected deal unless the project context is explicit.

Principles Users Should Remember

Ontology does not enter data for the user. Sales activities, customer information, contacts, stages, and signals must be recorded accurately in the operating screens.

Ontology does not automatically finalize sales judgment. The system connects evidence and explains judgment, but people decide which action to adopt and execute.

Ontology does not cross permission boundaries. Data from another company, tenant, or unauthorized project is outside the answer scope.

Ontology is not a natural-language data editing tool. If data must be changed, the user must change it in the relevant operating screen.

Read Next

To inspect actual ontology relationships, read Ontology Inspector.

To review deal judgment with AI analysis, read Decision Console.

To use natural-language evidence analysis, read Ontology AI.