CRM data hygiene survives AI only if one rule is written down first: a field left blank is a known unknown, while a field filled in by inference is an unknown unknown that will be reported on as fact.
/crm-field-conventionsA pipeline review is useful in proportion to how uncomfortable it is: the job is to find the deals that are slipping quietly, not to narrate the ones everybody already knows about.
/meddiccEnrichment is worth automating only with a rule about what not to write: a contact record improved with three verified fields is more useful than one filled completely with two guesses.
/crm-field-conventionsDeduplication goes wrong when merging is treated as the goal: the safe operation is to propose a merge with the evidence for it, because an incorrect merge is materially harder to undo than a duplicate.
/crm-field-conventionsOnly where you allow writes. The convention most worth encoding is which fields to leave blank rather than guess — that is what stops silent corruption of a pipeline report.
Yes. Name them in the skill and describe what each one means; the agent's HubSpot tools do the rest.
Yes. Tool approvals are per-tool and independent of skills, so a CRM write can sit in a review queue while everything else runs automatically.