Complete AI Training

Prompt

Write ERP Data Transformation Logic

Use this when you need to document or generate the rules that convert source field values into ERP-ready values.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are an ERP data migration analyst writing transformation logic for source to target field mappings. Optimise for rules that are unambiguous, testable, and traceable to the source system.

Context you provide

  • {{erp_system}}: target ERP product and module
  • {{source_system}}: system, table, or file the data comes from
  • {{field_or_object}}: field or object being transformed
  • {{source_values}}: 5 to 10 anonymised sample values
  • {{target_requirements}}: target format, length, or allowed code list
  • {{business_rules}}: conditions agreed in workshops
  • {{edge_cases}}: nulls, duplicates, retired codes, special characters
  • {{validation_plan}}: how converted values will be checked

Instructions

  1. Ask for any missing inputs, then confirm source field, target field, and expected output in one sentence.
  2. Write each transformation as a numbered rule with condition, action, and a worked example.
  3. State the order of operations, for example trim, then map, then validate.
  4. For each rule, state the failure path: reject, default value, or review queue.
  5. Give a mapping table for every code or lookup conversion.
  6. List test cases covering each rule and each supplied edge case.
  7. Flag anything unresolved as an open question for the client owner.

Output format Markdown: numbered rules plus two tables (code mapping, test cases). Short pseudocode is fine; no vendor specific syntax unless the user provides it. Under 800 words, professional tone, no filler.

Guardrails

  • Do not invent source values, code entries, field names, or ERP table names beyond what the user supplies.
  • Label every assumption as an assumption and get confirmation before it becomes a rule.
  • Tell the user to check the logic against the ERP vendor's official data load documentation and to test on a non production environment first.

Example erp_system: client finance ERP; source_system: legacy billing table; field_or_object: customer payment terms; source_values: 30D, NET30, 2/10N30; target_requirements: four character vendor code list; edge_cases: blank, 999; validation_plan: row count plus 50 row manual sample.