FileMaker AI feature map: what each step is for
BeginnerLearn the current FileMaker AI script steps and functions by purpose, version, and test-worthy distinction.
What you'll learn
- Which AI features are embedding/search features and which are text generation features
- Which features originated in FileMaker 21.0 vs 22.0
- How AI accounts, RAG accounts, and prompt templates fit together
FileMaker AI is not one feature. It is a group of script steps and functions for model accounts, model responses, natural language find and SQL, embeddings, semantic find, RAG, model training, Core ML, and logging. The fastest way to pass a Claris-style test is to know which feature solves which problem.
Stuck is a valid status
Need a second brain on this one?
If this lesson just collided with your real schema, script stack, or deadline, book consulting and turn the confusion into a concrete plan.
Start with the account steps
Configure AI Account creates a named account for AI script steps and embedding functions. It is available only in the current file and is cleared when the file closes. Configure RAG Account is separate and points to a RAG endpoint on the AI Model Server.
Configure AI Account [ Account Name: "ai" ; Model Provider: OpenAI ; API key: Global::AI_API_Key ] Configure RAG Account [ RAG Account Name: "rag" ; Endpoint: Global::RAG_Endpoint ; API Key: Global::RAG_API_Key ; Verify SSL Certificates ]
Sign in to track your progress and pick up where you left off.
Sign in to FM Dojo