Install & Configure

Install with a coding agent

The fastest way to set up Giskard Checks. Paste a single URL into your coding agent and it handles everything — dependency installation, LLM provider configuration, and environment setup.

How it works

Paste the URL into any coding agent (Claude Code, Cursor, Windsurf, Copilot, etc.)
The agent reads the installation instructions from this page
The agent installs giskard-checks and configures your LLM provider
You review the changes and start writing checks

Install the Python package

Giskard Checks requires Python 3.12 or higher. Install using pip:

pip install giskard-checks

Configure the default LLM judge model

Some checks require calling an LLM (LLMJudge, Groundedness, Conformity). To use them, you’ll need configure an LLM provider. Giskard Checks supports any LiteLLM-compatible provider (Azure, Anthropic, etc.). See the LiteLLM documentation for details. For example, to use OpenAI, you can set the OPENAI_API_KEY environment variable:

export OPENAI_API_KEY="your-api-key"

Preferably, you should set these environment variables in your .env file. To load them in Python, install and use python-dotenv:

pip install python-dotenv

from dotenv import load_dotenv

load_dotenv()  # loads .env from the current directory

Then you can set your preferred LLM judge model like this:

from giskard.agents.generators import Generator
from giskard.checks import set_default_generator

# Create a generator with giskard.agents
llm_judge = Generator(model="openai/gpt-5-mini")

# Configure the checks to use this judge model by default
set_default_generator(llm_judge)

We use the giskard-agents library to handle LLM generations.

Next Steps

For a step-by-step lesson with no API key, try Your First Test first. Or head to the Quickstart for a single example.