Native ERP AI, BI, a managed platform or custom MCP: how to choose

The right route is the one that answers an agreed business question with approved data, clear definitions and an operating owner. Sometimes that is a feature already available in the ERP or CRM. Sometimes it is BI, a managed platform or a purpose-built MCP connection. Sometimes the right decision is to fix a prerequisite or not build.

Start with the question, not the technology

Define one recurring question, who needs the answer and what decision it supports. Name the systems likely to contain the answer and a report, calculation or known result that the business already trusts. This makes the options comparable on practical grounds.

A route is suitable only when it can apply the agreed business meaning, respect source permissions, return enough evidence to check the answer and be maintained as systems and definitions change.

Compare the smallest useful routes

Native ERP or CRM capability

Start here when the question stays within one source system and its built-in assistant or analytics feature can use the right records, definitions and user permissions. The main checks are data coverage, answer quality, plan availability, provider processing and who will maintain the configuration.

Existing BI

BI is often the simplest route when approved models already combine the required data and business definitions. It can provide a stable comparison layer and preserve familiar access rules. Confirm that the intended assistant can reach it safely and that the model answers the actual question rather than only reproducing a fixed dashboard.

Managed platform

A managed platform can fit when several approved sources need to be brought together and the customer wants one party to own implementation, monitoring, support and controlled change. Review what the platform stores, how identity and permissions are enforced, which assistants it supports and how data and configuration can be handed over or removed at exit.

Purpose-built MCP connection

Model Context Protocol, or MCP, is one way for a compatible AI assistant to call approved tools. It can be useful when existing products do not provide the required read path or business-specific operations. MCP does not supply the business definitions, permissions, testing or ongoing ownership by itself. Those still have to be designed and operated.

Prerequisite work or no build

Do not add another service when the source data is unreliable, the definition is disputed, access cannot be approved or an existing tool already answers the question well enough. A useful assessment can recommend correcting the prerequisite, using the current route or stopping.

Use the same decision criteria for every option

  • Coverage: Does the route reach the required systems, records, history and dimensions?
  • Business meaning: Can it apply approved definitions for measures, periods, ownership, currency and exceptions?
  • Access: Does each user have an explicit identity path and only the operations and data they need?
  • Evaluation: Can representative answers be checked against trusted reports or known results?
  • Operation: Who monitors availability, investigates failures, rechecks answers and manages change?
  • Compatibility and exit: Which assistant plans, provider settings and hosting choices are required, and how can the route be changed or closed?

Make the route decision before the build decision

The AI Analytics Assessment compares these options for one use case. It records the source and access review, the evaluation plan, the preferred route, material assumptions and the factors that would determine the scope of any later work.

If a build is justified, the work then follows Assess, Build, Run: agree the route, implement and test only what is needed, then maintain it as a managed service. This keeps the technology choice tied to the business question throughout its life.