Your build starts here
Replace bracketed details with your own goal, context, and checks. Keep the first build small enough to inspect.
Build an importer from [source] into [destination] using the existing project conventions. Identify stable record IDs, update markers, deletion behavior, and the checkpoint boundary. Define how retries and late records are handled. Create a small test dataset containing new, updated, duplicated, invalid, late, and deleted records. Verify that running the import twice gives the intended final state and that interruption can be recovered. Report accepted and rejected counts, checkpoint behavior, and any source assumptions that could cause missing data.Make this prompt yours
Replace bracketed fields with your goal, current behavior, and relevant evidence. Keep requirements that affect the task. Check the result against the acceptance criteria you supplied.
The docs behind it
These references explain the underlying concepts and APIs. The prompt templates and project plans are original examples to adapt to your own setup.
- AWS Glue — Tracking processed data with job bookmarks
- SQLite — Transactions and rollback
- SQLite — UPSERT conflict handling
Documentation links checked .
Editorial review · October 28, 2026
Limited: Original instructional template; not executed. Rerunnable-import prompt asks for source assumptions and recovery checks; no completed importer or delivery guarantee is claimed.