Salesforce Dictionary - Free Salesforce GlossarySalesforce Dictionary
Full Einstein Vision entry
How-to guide

How to migrate an existing Einstein Vision integration

Einstein Vision is retired. The steps below cover migrating an existing consumer to a modern path; do not build new integrations against the retired API.

By Dipojjal Chakrabarti · Founder & Editor, Salesforce DictionaryLast updated May 16, 2026

Einstein Vision is retired. The steps below cover migrating an existing consumer to a modern path; do not build new integrations against the retired API.

  1. Inventory every Vision API call

    Search the codebase for the Einstein Platform Services base URL or the predict, train, and dataset endpoints. List each consumer with the dataset it depends on and the downstream consumer of the prediction.

  2. Map each call to a use case category

    Sort calls into damage assessment, document OCR, visual product matching, asset counting. The replacement depends on the category, not on which Vision endpoint was called.

  3. Pick the modern replacement

    Field service image classification often moves to embedded Field Service intake. Document OCR often moves to Salesforce OCR services in Cloud or Files. Visual product matching often moves to Commerce Cloud Einstein. Truly custom needs go to BYOM in Einstein Studio.

  4. Train or register the replacement model

    Embedded features need their own dataset configuration. BYOM needs an external training pipeline and registration in Einstein Studio with an exposed endpoint.

  5. Cut over with parallel-run validation

    Run the new path alongside the old call for one to two weeks. Compare predictions on a hand-graded sample. Cut over when the new path meets or beats the old accuracy.

Embedded Field Service intakeremember

The replacement for technician photo classification in Field Service. Damage assessment lives in the work order workflow.

Commerce Cloud Einsteinremember

The replacement for visual product matching and visual search use cases in commerce contexts.

Files visual searchremember

For visual search inside a Salesforce org, the Files feature offers indexed similarity search without separate API plumbing.

Bring Your Own Modelremember

The fallback for custom vision needs. Train externally, register in Einstein Studio, call from flows or prompts.

Multimodal foundation modelsremember

Some Prompt Builder paths accept image inputs alongside text, letting a foundation model classify or describe images directly.

Gotchas
  • Einstein Vision is retired. New connected apps cannot register. Existing apps should plan a migration even if calls currently succeed.
  • BYOM requires owning the model lifecycle: training, retraining, monitoring, and refresh. The platform does not manage these for custom models.
  • Embedded replacements carry their own data model. The output may need transformation to match what the original Einstein Vision integration consumed.
  • Direct Apex callouts to external vision models bypass the Einstein Trust Layer. Wrap calls in prompt templates if Trust Layer governance is required.
  • Older Trailhead modules and developer docs still reference Einstein Vision. Confirm against current release notes before quoting them as guidance.

See the full Einstein Vision entry

Einstein Vision includes the definition, worked example, deep dive, related terms, and a quiz.