/5 CONNECTED STEPS
Bring a source into an AI data product
Implement ingestion whose records survive bad refreshes and are actually queryable by the intended AI consumer.
Download complete workflow .md ↓Use with your AI
Complete workflow download included with library membership. Try the free starters without signup.
What you need
Source access, a destination, source field definitions and an identified consumer.
Why these fit together
A probe establishes real shape; the contract fixes grain and keys; the write gate preserves good data; consumer wiring closes the gap between stored data and useful answers.
Follow this order
Scope an Ingestion Source Before Loading
Choose the source scope, canonical root, consumer and schedule.
Probe real records before building a pipeline
Check actual fields, keys and pagination.
Harden ingestion with keys and contracts
Define grain and choose a supported write strategy.
Guard destructive refreshes before writing
Block invalid replacement before existing rows change.
Wire a dataset into an AI-facing data layer
Register and query the actual consuming layer.
Give this task to your AI
Use the Bring a source into an AI data product workflow. My task and inputs are supplied below. Read the prerequisites and check your available tools. Follow the core steps in order, passing the actual output of each step to the next. Adapt installation and commands to this environment; do not copy another agent's configuration blindly. If a required tool or input is missing, identify it before that step. Run the completion check and report observed results and unresolved work.
Setup to provide or build
One supported storage and connector stack, sample source, normalizer, write guards and an actual query entry point.
Check the result
A duplicate preserves entity grain, a renamed field and empty pull cannot destroy good rows, and the real consumer returns the expected sourced value.
Curated implementation workflow. End-to-end execution must be verified in your environment.
Optional additions
Load these only when your task needs them.