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 to quickly download and run example code? Check out the GL AIP Cookbook for ready-to-run implementations.

Choose Your Path

• 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

When to use: You are coding in Python, iterating from notebooks or applications, and want typed helpers during development.

1

Install or Upgrade the Package

pip install --upgrade glaip-sdk

2

Launch the Slash Command Palette (new CLI entrypoint)

aip

This opens the interactive palette so you can test your connection, browse agents, or run prompts without memorising longer commands. From here, try /status to confirm connectivity or /agents to jump into an agent session. See the CLI Slash Palette reference for screenshots and full command coverage.

3

Configure Credentials

Create a .env file in your project directory with your AIP API credentials (the Python SDK reads these environment variables):

# Create .env file in your project directory
echo "AIP_API_URL=https://your-aip-instance.com" >> .env
echo "AIP_API_KEY=your-api-key-here" >> .env

Note: The Python SDK Client() only reads from environment variables (AIP_API_URL, AIP_API_KEY).

4

Verify Connectivity

python -c "from glaip_sdk import Client; print('✅ Connected!') if Client().ping() else print('❌ Connection failed')"

5

Create and Run Your First Agent

from glaip_sdk import Client

client = Client()

agent = client.create_agent(
    name="hello-world-agent",
    instruction="You are a friendly AI assistant."
)

response = agent.run("Hello! How are you today?")
print(response)

agent.delete()

Optional Next Steps

• Attach a tool (see the Tools guide) and rerun the agent.

• Upload a file with agent.run(..., files=["/path/to/file.pdf"]) and follow the File processing guide.

• Persist conversation context with chat_history or agent_config.memory (covered in the Agents guide).

---

CLI Path

When to use: You need zero-code validation, quick demos, or scripted runs that operate from any shell.

1

Install or Upgrade the Package

pip install --upgrade glaip-sdk

Or use uv tool install glaip-sdk if you prefer uv.

2

Launch the Slash Command Palette (new CLI entrypoint)

aip

This opens the interactive palette so you can try /status, /agents, or /help without recalling full command syntax. It is the fastest way to verify setup and run agents inline. See the CLI Slash Palette reference for screenshots and deeper guidance.

3

Configure Credentials

aip configure

4

Verify Connectivity

aip status

Tests connection to AIP platform. Expected output shows connection status and resource counts. You can run the same command from the palette with /status once credentials are in place.

5

Create and Run Your First Agent

# Create agent
aip agents create \
  --name "hello-world-agent" \
  --instruction "You are a friendly AI assistant."

# List agents (shows agent details)
aip agents list

# Or use --simple for a plain table without interactive features
aip agents list --simple

# Run the agent (replace <AGENT_REF> with the value from the list)
aip agents run <AGENT_REF> --input "Hello! How are you today?"

# Clean up
aip agents delete <AGENT_REF>

This creates and runs your first agent using the CLI. After creating the agent, use aip agents list to see its details. Copy the agent ID or name and use it in the run command.

In the commands above, replace <AGENT_REF> with either your agent ID or name. If you have multiple agents with similar names, use the full ID to avoid confusion.

Optional Next Steps

• Add a tool with aip tools create and aip agents update --tools ... (details in the Tools guide).

• Attach files during runs with aip agents run <AGENT_REF> --input "Review" --file report.pdf and consult the File processing guide.

• Reuse context by passing --chat-history JSON; see the Agents guide for examples.

• For prompt/export iteration, jump to the Configuration management guide which walks through the full export → edit → import loop.

---

Troubleshooting

Issue	Solution
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 config show
Connection refused	Confirm the AIP backend is reachable
uv not found	Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh

---

Next Steps

1. Practice with the Hands-on examples to explore tools, files, and multi-agent flows.

2. Deepen lifecycle control in the Agents guide.

3. Wire up native and custom tooling via the Tools guide.

4. Explore orchestration strategies in the Multi-Agent System Patterns overview once you need repeatable playbooks.