Active AI
Active AI proactively recommends fixes and next actions based on your terminal errors, inputs, and outputs.
Last updated
Active AI proactively recommends fixes and next actions based on your terminal errors, inputs, and outputs.
Last updated
Active AI features can be disabled in Settings > AI with the Active AI toggle.
Prompt Suggestions are contextual, AI-powered suggestions that activate Agent Mode. These banners will provide suggestions for what to ask Agent Mode in specific scenarios, similar to how Warp already suggests commands to run.
If you press CMD-ENTER (on Mac), CTRL-SHIFT-ENTER (on Linux/Windows), or click on the chip, the suggestion will be auto-populated into your input and run against Agent Mode (with the most recent block attached).
Prompt Suggestions use an LLM to generate prompts based on your terminal session, specifically the most recent block. These AI requests do not contribute towards your AI limits, however, any accepted prompts run in Agent Mode contribute as normal. Visit Settings > AI > Agent Mode, if you'd like to turn it off. * Please note that Secret Redaction is automatically applied to any content sent to Active AI features to prevent any sensitive data being leaked.
Next Command uses AI to suggest the next command to run based on your active terminal session and command history. It uses your active terminal session contents and an LLM to generate commands.
Next Command is an LLM-based feature which utilizes your command history (enriched with git branch, exit code, and directory metadata) as well as recent block input and output to generate the next command suggestions.
Please note that Secret Redaction is automatically applied to any content sent to Active AI features to prevent any sensitive data being leaked.
To disable, please visit Settings > AI > Next Command
In order to use a next Command Suggestion, please use the TAB key , → key , or CTRL-F to add the suggested next command to your input buffer. ENTER executes the accepted command.
For the latest information on limits, visit warp.dev/pricing. A Next Command only counts toward your limit if you explicitly accept the suggestion. If you enter a command that matches a suggested Next Command by typing it manually or rerunning it from your history, it will not count toward your usage.
