This page provides two demonstrations of how an AI agent interacts with information. The first is a conversation with a public AI agent, such as ChatGPT, which is powered by a Large Language Model (LLM). This interaction highlights the difference between the agent's trained knowledge and its ability to use tools. The second will showcase a custom AI agent designed for a specific purpose.
First, the user asks a question about an event within the AI's training data. The AI answers using its internal knowledge base.
What do you know about the 2023 Super Bowl?
I can provide a good amount of detail on that game, as it occurred before my knowledge cutoff.
The 2023 Super Bowl, officially known as Super Bowl LVII, was a highly anticipated matchup between the Kansas City Chiefs and the Philadelphia Eagles. The Chiefs won a close game with a final score of 38-35.
Here are some of the key details from the event:
Next, the user asks about an event that occurred after the AI's knowledge cutoff. The agent first states its limitations. In response to a follow-up question, it then uses a web search tool to find and provide the current information.
What do you know about the 2024 Super Bowl?
The 2024 Super Bowl occurred after my last knowledge update in early 2023, so I do not have the results of the game, including who won or the final score. I can tell you that it was scheduled to be played at Allegiant Stadium in Paradise, Nevada. For the specific details of the game, I would recommend a quick search on Google.
Who won the 2024 Super Bowl?
The Kansas City Chiefs won the 2024 Super Bowl (Super Bowl LVIII).
They defeated the San Francisco 49ers 25-22 in overtime.
This section will feature an interactive demonstration of a custom-built AI agent designed to perform a specialized task.