Reference

A generated summary field is more dangerous than a stale one, because it's fresh, fluent, and it asserts things. The two failure modes, compounding fabrication, vocabulary decay, and the controls that contain them.

Three things that get substituted for each other and answer different questions. Why embedding your field descriptions doesn't work, and where a semantic layer genuinely overlaps.

Authority is a ladder that doesn't bend; specificity breaks ties among equals. Where a live user instruction sits, and what to do when two active rules genuinely contradict.

Eleven ways this gets built wrong, starting with dumping your CRM schema into the prompt. What each one looks like, why it fails, and what to do instead.

Every term used across this site, defined once: context layer, rule categories, phased retrieval, hard and soft controls, resolution states, and the failure modes each one prevents.

What has to be true before a CRM AI agent answers for real users: enforcement in code, always-load rules, phased retrieval, disclosure, and attributable logging. Every item is done or not done.

Your CRM AI gave a confident wrong answer. A symptom-to-cause index for the twenty failures that actually happen, what each one means, and the rule that prevents it recurring.

A regression suite for your context layer: targeted and broad questions, an evaluation rubric that goes beyond pass/fail, and a 30-question starter set as executable YAML.

MCP standardizes how an AI application connects to your CRM. A context layer defines what the data means and what the agent may touch. You need both, and one will not do the other's job.

What actually happens between a question and an answer: phase-1 payload, rule index, selection, query plan, tool-boundary validation, and the audit log. Plus the same question failing on purpose.

Object, field, and row scope; running as the asking user; why a permission-suppressed null looks exactly like a blank; who is allowed to edit the rules; and a five-level model for letting an agent act.

A canonical schema for CRM AI context entries: the governance envelope, field entries, rule entries, the thirteen rule categories, and a JSON Schema file you can validate against.