A Generative AI Engineer is creating an agent-based LLM system for their favorite monster truck team. The system can answer text based questions about the monster truck team, lookup event dates via…

Question

Options

• AIngest PDF documents about the monster truck team into a vector store and query it in a RAG
• BWrite a system prompt for the agent listing available tools and bundle it into an agent system that
• CInstruct the LLM to respond with "RAG", "API", or "TABLE" depending on the query, then use text
• DBuild a system prompt with all possible event dates and table information in the system prompt.

• A
  3% (1)
• B
  89% (32)
• C
  8% (3)

Explanation

Option B correctly describes an agent architecture: the system prompt declares available tools (text Q&A, API lookup, SQL query), and an agent framework allows the LLM to autonomously select the appropriate tool based on the user's query. This is the standard pattern for multi-capability agents. Option A (RAG only) cannot handle API calls or SQL queries. Option C (LLM as a router with text parsing) is fragile and adds unnecessary complexity. Option D (stuffing all data into the system prompt) does not scale and cannot support dynamic API calls.

No community discussion yet for this question.