AI-103: Generative AI & Agentic Solutions
Generative AI & Agentic Solutions is one of the skill areas tested on the Developing AI Apps & Agents on Azure (AI-103) exam. Below are free AI-103 practice questions with worked answers and a concept diagram — each with a plain-language explanation. Practice the first 10 questions of AI-103 free, no signup.
The concept, in one picture
2 free AI-103 Generative AI & Agentic Solutions questions
Scenario: A support agent must ground its answers on a library of PDF product sheets held in a blob container. The team requires an indexing pipeline that supports both semantic and vector retrieval so the agent can respond to free-form product questions, and all processing must stay inside the EU region. You need to recommend the service that lets the agent retrieve and use the information in those PDFs. What should you include in the recommendation?
- ✓ Azure AI Search
- Azure Translator in Foundry Tools
- Azure Document Intelligence in Foundry Tools
- Grounding with Bing Search
Azure AI Search ingests content from sources like Azure Blob Storage, builds searchable indexes, and supports keyword, semantic, hybrid, and vector retrieval for RAG. Its integrated vectorization can chunk documents and produce embeddings during indexing, so the agent can vector-search the PDFs and answer natural language product questions. Translator handles language translation, not retrieval; Document Intelligence extracts document layout and structure but is not the retrieval index; Grounding with Bing Search pulls public web results rather than the private PDFs in the container.
Scenario: You are building an Azure AI Search indexing pipeline over lengthy PDF product documents so an agent can perform semantic and vector retrieval in a RAG solution. You need to choose the built-in skills that chunk the documents and generate the vector embeddings. Which two built-in skills should you use? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.
- Language Detection
- Entity Recognition
- Merge
- ✓ Azure OpenAI Embedding
- ✓ Text Split
- key phrase extraction
A RAG pipeline over long PDFs must split content into chunks and then vectorize each chunk. In Azure AI Search integrated vectorization, the skillset uses the Text Split skill to chunk the text and the Azure OpenAI Embedding skill to generate embeddings for those chunks. Language Detection, Entity Recognition, and key phrase extraction only enrich text and produce no vectors; Merge joins OCR output with document text and does not provide the required vector embeddings.
Practice AI-103 free
The first 10 questions of every exam are free. No signup, no email wall.
Start practicing →Get a free AI-103 study plan by email
A short plan to work through AI-103 by skill area, plus a note when we add new questions. Optional — the practice above stays free. No spam, unsubscribe anytime.