Back to guide/General Productivity

Integration Mapper

Categorizing mappings by complexity (direct, transform, computed) prioritizes implementation effort. The test checklist prevents going live with untested edge cases.

how-to-automate-with-aisystem_asystem_bschema_a
Edit View
Prompt
Map data between {{system_a}} and {{system_b}} to build an integration.\n\nSystem A schema:\n{{schema_a}}\n\nSystem B schema:\n{{schema_b}}\n\nIntegration direction: {{direction}}\n\nGenerate a complete field mapping:\n\n| System A Field | System B Field | Transform | Notes |\n|---|---|---|---|\n\nFor each mapping:\n- **Direct**: Fields that map 1:1 with no transformation\n- **Transform**: Fields that need conversion (date formats, units, enums)\n- **Computed**: Target fields that require combining multiple source fields\n- **Unmapped source**: Source fields with no target equivalent (log and skip)\n- **Missing required**: Target required fields with no source data (provide defaults)\n\nAlso provide:\n1. Sample request/response payloads for the integration\n2. Error handling for each transformation that could fail\n3. A test checklist: specific data scenarios to validate before going live

Variables to customize

{{system_a}}{{system_b}}{{schema_a}}{{schema_b}}{{direction}}

Why this prompt works

Categorizing mappings by complexity (direct, transform, computed) prioritizes implementation effort. The test checklist prevents going live with untested edge cases.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Task Decomposition Agent

Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.

Tool Selection Agent

The ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.

Prompt Compressor

Explicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.

Memory Management Agent

Explicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.