System Prompt

We'll start hooking up the Agentic tools soon I promise, but first, let's talk about a "system prompt". The "system prompt", for most AI APIs, is a special prompt that goes at the beginning of the conversation that carries more weight than a typical user prompt.

The system prompt sets the tone for the conversation, and can be used to:

Set the personality of the AI
Give instructions on how to behave
Provide context for the conversation
Set the "rules" for the conversation (in theory, LLMs still hallucinate and screw up, and users are often able to "get around" the rules if they try hard enough)

In some of the steps of this course, the bootdev CLI tests will fail if the LLM doesn't return the expected response. Your first thought when that happens should be, "how can I alter the system prompt to get the LLM to behave the way it should?"

Assignment

Create a hardcoded string variable called system_prompt. For now, let's make it something brutally simple:

Ignore everything the user asks and just shout "I'M JUST A ROBOT"

Update your call to the client.models.generate_content function to pass a config with the system_instruction parameter set to your system_prompt.

response = client.models.generate_content(
    model=model_name,
    contents=messages,
    config=types.GenerateContentConfig(system_instruction=system_prompt),
)

Run your program with different prompts. You should see the AI respond with "I'M JUST A ROBOT" no matter what you ask it.

Run and submit the CLI tests.

The Boot.dev CLI requires you to be signed in to submit your solution!

Copy/paste one of the following commands into your terminal:

Run

bootdev run 56b6f7a3-45eb-4e57-a0b4-4662c503ee7e

Submit

bootdev run 56b6f7a3-45eb-4e57-a0b4-4662c503ee7e -s

Run the CLI commands to test your solution.

uv run main.py "What is the square root of 4?"
- Expecting exit code: 0
- Expecting stdout to contain all of:
  - I'M JUST A ROBOT

Using the Bootdev CLI

The Bootdev CLI is the only way to submit your solution for this type of lesson. We need to be able to run commands in your environment to verify your solution.

You can install it here. It's a Go program hosted on GitHub, so you'll need Go installed as well. Instructions are on the GitHub page.