Gemini CLI

Install Gemini CLI using the current package or platform instructions from Google, then authenticate with a supported Google account or API configuration. Run it from the project directory whose files should be available as context. Begin with read-only exploration or a small coding task before enabling broader tool use. Review file edits and commands, keep secrets out of prompts and repositories, and use project instructions or extensions where appropriate to make the agent follow the team's conventions.

For a first evaluation, keep the scope small enough that you can compare the AI-assisted result with a known baseline. Record the configuration, model or workflow choices that produced the result so successful tests can be reproduced. If the product connects to external systems or private data, grant the minimum permissions required and review the provider's current security and data-handling documentation before expanding access.