# Warp Agents - [Warp Agents overview](https://docs.warp.dev/agent-platform/warp-agents/warp-agents.md): Powerful AI features like agents, code review, voice, and active AI recommendations, fully integrated into the Warp Agentic Development Environment. - [Capabilities](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview.md): Core capabilities and configuration options that shape how agents behave, what context they have access to, and how they execute tasks. - [Slash commands](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/slash-commands.md): Use Slash Commands in Agent Mode or Auto-Detection Mode to quickly run built-in actions or saved prompts without leaving the input field. - [Skills](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/skills.md): Create reusable instruction sets that teach agents specific tasks and share expertise across your team. - [Planning](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/planning.md): Turn requests into structured, editable plans that agents execute step-by-step with version control. - [Task lists](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/task-lists.md): Track and manage complex Agent workflows with automatic task lists that break requests into clear, actionable steps and update progress in real time. - [Model choice](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/model-choice.md): Choose from a curated set of top LLMs for Warp's Agents (or let Warp auto-select the best model). - [Rules](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/rules.md): Create reusable Global or Project Rules to ensure Warp’s agents follow your coding standards, project conventions, and personal preferences. - [Agent notifications](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/agent-notifications.md): Warp surfaces notifications from coding agents, both in-app and via desktop alerts, so you know exactly when an agent needs your attention. - [Full terminal use](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/full-terminal-use.md): Full Terminal Use means Warp's agents can interact with active terminal apps to monitor live output and run commands. - [Computer use](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/computer-use.md): Let agents interact with desktop GUIs in sandboxed cloud environments for automated UI testing and validation. - [Codebase Context](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/codebase-context.md): Warp indexes your Git-tracked codebase to help Agents understand your code and generate accurate, context-aware responses. No code is stored on Warp servers. - [Profiles & permissions](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/agent-profiles-permissions.md): Agent Profiles let you customize how your Agent behaves, from its models and autonomy to the tools and permissions it can use. - [Web search](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/web-search.md): Warp’s web search lets agents pull in real-time information, documentation, and cited sources whenever it improves an answer. - [Session sharing](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/session-sharing.md): Share live agent sessions so collaborators can view, steer, and interact with agent activity from any device — in real time or asynchronously. - [Cloud-synced conversations](https://docs.warp.dev/agent-platform/warp-agents/capabilities-overview/cloud-conversations.md): Sync agent conversations to the cloud to access them across devices, share with teammates, and continue past conversations from anywhere. - [Interacting with agents](https://docs.warp.dev/agent-platform/warp-agents/interacting-with-agents.md): Manage agent conversations across sessions with follow-ups, context blocks, and multi-thread support. - [Terminal and Agent modes](https://docs.warp.dev/agent-platform/warp-agents/interacting-with-agents/terminal-and-agent-modes.md): Warp provides two distinct modes: a clean terminal for commands, and a dedicated conversation view for multi-turn agent workflows. - [Conversation forking](https://docs.warp.dev/agent-platform/warp-agents/interacting-with-agents/conversation-forking.md): Branch into a new agent thread with full context to explore alternatives without altering the original conversation. - [Code diffs](https://docs.warp.dev/agent-platform/warp-agents/interacting-with-agents/code-diffs.md): How to review, refine, and apply code changes generated by Warp’s Agents with the built-in diff editor in Agent Conversations. - [Voice](https://docs.warp.dev/agent-platform/warp-agents/interacting-with-agents/voice.md): Voice enables natural language interaction with Warp, letting you speak commands and queries directly to your terminal. - [Agent context](https://docs.warp.dev/agent-platform/warp-agents/agent-context.md): How to attach various forms of multi-modal context directly to Warp's Agent within a prompt. - [Blocks as context](https://docs.warp.dev/agent-platform/warp-agents/agent-context/blocks-as-context.md): Attach blocks from your terminal as context so Warp’s Agent can understand errors, outputs, or previous commands when responding to your queries. - [Images as context](https://docs.warp.dev/agent-platform/warp-agents/agent-context/images-as-context.md): Attach screenshots, diagrams, or other images to your prompt so Warp’s Agent can use visual context when generating responses. - [URLs as context](https://docs.warp.dev/agent-platform/warp-agents/agent-context/urls-as-context.md): Attach a public URL to your prompt so the agent can reference that page's content. - [Selection as context](https://docs.warp.dev/agent-platform/warp-agents/agent-context/selection-as-context.md): Attach text or diffs directly from Warp’s editor or Code Review panel as context for your Agent prompts. - [Using @ to add context](https://docs.warp.dev/agent-platform/warp-agents/agent-context/using-to-add-context.md): Use @ to reference files, folders, code symbols, and Warp Drive objects as agent context. - [Model Context Protocol (MCP)](https://docs.warp.dev/agent-platform/warp-agents/agent-context/mcp.md): Configure MCP servers in the Warp desktop app to extend local agents with custom tools and data sources through a standardized interface. - [Interactive code review](https://docs.warp.dev/agent-platform/warp-agents/interactive-code-review.md): Review agent-generated code, leave inline comments, and have Warp's native agent or any supported third-party CLI agent apply your feedback. - [Active AI recommendations](https://docs.warp.dev/agent-platform/warp-agents/active-ai.md): Active AI Recommendations proactively suggest fixes and next actions based on your command line errors, inputs, and outputs. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.warp.dev/agent-platform/warp-agents.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.