Vector embedding, fine tuning and task-specific language models are examinable topics on this credential, sitting in its heaviest domain. Most study material still describes the syllabus that came before them.
Sixty correct answers from seventy-five, across six domains weighted within five points of each other. There is no topic you can write off, and the biggest one is retrieval rather than prompting.
Every objective on GCP-GAIL starts with describe or identify, never configure. A working read of the four domains, the twenty five named Google products, and who the credential is really for.