Who should use the Explain model predictions workflow?
Teams or solo builders working on development tasks who want a repeatable process instead of one-off tool experiments.
Execution Map
7-step pipeline — follow each step in order
1Setup · Step 1 of 7
Open task pageTrain AI models
Prepare inputs and settings through Train AI models before running explain model predictions.
Why this matters
Train AI models sets up the foundation for explain model predictions; clean inputs here reduce downstream rework.
What you get
Inputs, context, and settings are ready so the workflow can move into execution without blockers.
2Input · Step 2 of 7
Open task pageEvaluate AI Models
Use Evaluate AI Models to build supporting assets that improve explain model predictions quality.
Why this matters
Evaluate AI Models strengthens explain model predictions by feeding better supporting material into the pipeline.
What you get
Supporting assets from evaluate ai models are prepared and connected to the main workflow.
More optionsCompare
3Input · Step 3 of 7
Open task pageBuild AI Models
Use Build AI Models to build supporting assets that improve explain model predictions quality.
Why this matters
Build AI Models strengthens explain model predictions by feeding better supporting material into the pipeline.
What you get
Supporting assets from build ai models are prepared and connected to the main workflow.
More optionsCompare
4Core · Step 4 of 7
Open task pageExplain model predictions
Execute explain model predictions with Explain model predictions to produce the primary final deliverable.
Why this matters
This is the core step where explain model predictions actually happens, so it determines baseline quality for everything after it.
What you get
A first-pass final deliverable is generated and ready for refinement in the next steps.
More options
5Refine · Step 5 of 7
Open task pageDevelop AI models
Refine and validate explain model predictions output using Develop AI models before final delivery.
Why this matters
Develop AI models adds quality control so issues are caught before the workflow is finalized.
What you get
The final deliverable is improved, validated, and prepared for final delivery.
More optionsCompare
6Refine · Step 6 of 7
Open task pageTrain machine learning models
Refine and validate explain model predictions output using Train machine learning models before final delivery.
Why this matters
Train machine learning models adds quality control so issues are caught before the workflow is finalized.
What you get
The final deliverable is improved, validated, and prepared for final delivery.
More optionsCompare
7Deliver · Step 7 of 7
Open task pageTrain deep learning models
Package and ship the output through Train deep learning models so explain model predictions reaches end users.
Why this matters
Train deep learning models is what turns intermediate output into a usable, publishable result for real users.
What you get
A finalized final deliverable is ready for publishing, handoff, or integration.
More optionsCompare