Quick Start Guide
Go from zero to your first successful agent run. If you have not installed and configured the SDK yet, run pip install --upgrade glaip-sdk (or follow Install & Configure) before continuing.
When to use this guide: Choose it when you need a reproducible walkthrough to prove connectivity, create an agent, and observe responses without diving into advanced configuration.
Audience: Developers, PMs running acceptance demos, and data developers validating prompt baselines.
Want runnable code that mirrors the latest SDK behavior? Jump to the Hands-on Examples, which links to the validated projects.
Paths
Python SDK — programmatic control and notebooks.
CLI — quick experiments, scripting, and CI.
Data developers who focus on prompt iteration can skip the SDK path and follow the CLI steps exclusively. Product managers typically validate agents in GLChat; run the CLI flow here when you need verbose traces, file attachments, or to reproduce an issue for engineering.
Python SDK Path
Follow the Python SDK page for step-by-step installation, a default local agent run, and optional setup when you want to target a remote AIP server with API credentials and deployment.
CLI Path
Follow the CLI page for zero-code setup, palette usage, and running your first agent from the terminal.
Troubleshooting
command not found
Ensure pip’s script directory is on PATH, or reinstall with uv
401 Unauthorized
Run aip configure or update your environment variables
404 Not Found
Check your API URL with aip accounts show <name>
Connection refused
Confirm the remote AIP server is reachable
uv not found
Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh
Next Steps
Practice with the Hands-on examples to explore tools, files, and multi-agent flows.
Check out the GL SDK Cookbook for self-contained, multi-tool examples like the Travel Assistant.
Deepen lifecycle control in the Agents guide.
Wire up native and custom tooling via the Tools guide.
Explore orchestration strategies in the Multi-Agent System Patterns overview once you need repeatable playbooks.
Last updated