# AI and Agent System Relevant source files - [.agents/skills/add-telemetry/SKILL.md](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1) - [.mcp.json](https://github.com/warpdotdev/Warp/blob/81910e24/.mcp.json) Warp is an AI-native terminal that integrates large language models directly into the command-line experience. The AI system is built around a sophisticated agent architecture that allows for both interactive conversations and autonomous task execution. This system leverages the **Model Context Protocol (MCP)** to interact with the local file system and external tools, supported by a robust **Skills System** and a cloud-based execution platform known as **Oz**. ### System Architecture Overview The AI capabilities in Warp are distributed across several layers, from the UI conversation model to the low-level protocol integrations. Title: AI System Component Interaction ``` ``` Sources: `app/src/ai/agent/mod.rs`, `app/src/ai/skills/mod.rs`, `app/src/ai/mcp/mod.rs` * * * ## [Agent Conversations and Task Execution](/content/warpdotdev/Warp/4.1-agent-conversations-and-task-execution/index.html) The core of Warp's AI is the Agent system located in `app/src/ai/agent/`. This subsystem manages the lifecycle of an AI interaction, from the initial user prompt to the final execution of terminal commands or file edits. - **Conversation Model**: Managed via `AIConversationId`, the system maintains a linearized history of agent steps, including thought processes, tool calls, and outputs. - **Task Store**: Tracks the state of long-running autonomous tasks and their execution progress. - **Ambient Agents**: Located in `app/src/ai/ambient_agents/`, these agents provide "always-on" assistance, such as proactive command suggestions or error explanations, without requiring a dedicated chat session. - **Execution Profiles**: Define the constraints and capabilities of an agent session (e.g., local vs. cloud execution). - **Computer Use & Voice**: Integrates screenshot-based automation via the `computer_use` crate and voice transcription in `app/src/ai/voice/`. For details, see [Agent Conversations and Task Execution](/content/warpdotdev/Warp/4.1-agent-conversations-and-task-execution/index.html). Sources: `app/src/ai/agent/mod.rs`, `app/src/ai/ambient_agents/mod.rs` * * * ## [MCP (Model Context Protocol) Integration](/content/warpdotdev/Warp/4.2-mcp-(model-context-protocol/index.html)-integration) Warp implements the **Model Context Protocol (MCP)** to provide a standardized way for AI agents to access tools and data. The integration in `app/src/ai/mcp/` allows Warp to act as an MCP host. - **MCP Server Manager**: Handles the lifecycle of MCP servers, including file-based watchers that detect new server configurations. - **Tool Exposure**: Automatically discovers tools provided by MCP servers and exposes them as executable "skills" to the AI agent. - **Reconnecting Peer Logic**: Ensures robust connections to external MCP servers. - **Bundled Skills**: Warp includes several pre-configured MCP skills in `resources/bundled/mcp_skills/` for common terminal operations. - **External Config**: External MCP servers can be configured via `.mcp.json` at the project root [.mcp.json1-12](https://github.com/warpdotdev/Warp/blob/81910e24/.mcp.json#L1-L12) For details, see [MCP (Model Context Protocol) Integration](/content/warpdotdev/Warp/4.2-mcp-(model-context-protocol/index.html)-integration). Sources: `app/src/ai/mcp/mod.rs`, `crates/warp_cli/src/mcp.rs`, [.mcp.json1-12](https://github.com/warpdotdev/Warp/blob/81910e24/.mcp.json#L1-L12) * * * ## [Skills System and Bundled Resources](/content/warpdotdev/Warp/4.3-skills-system-and-bundled-resources/index.html) The Skills System in `app/src/ai/skills/` is the extensibility layer for Warp's AI. A "Skill" is a discrete capability that an agent can invoke to perform an action. - **Skill Resolution**: The `SkillManager` resolves natural language intents to specific executable logic or MCP tools. - **Bundled Skills**: Located in `resources/bundled/skills/`, these include built-in capabilities like `add-mcp-server`, `modify-settings`, `oz-platform`, and `create-skill`. - **Agentic Development**: Warp uses internal skills like `add-telemetry` to assist developers in instrumenting the codebase [.agents/skills/add-telemetry/SKILL.md2-4](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L2-L4) - **Channel Gating**: Skills can be restricted to specific release channels (e.g., Dev or Preview) to allow for safe testing of new AI features. For details, see [Skills System and Bundled Resources](/content/warpdotdev/Warp/4.3-skills-system-and-bundled-resources/index.html). Sources: `app/src/ai/skills/mod.rs`, [.agents/skills/add-telemetry/SKILL.md1-50](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L1-L50) * * * ## [Telemetry System](/content/warpdotdev/Warp/4.4-telemetry-system/index.html) Warp uses a trait-based telemetry framework to monitor the performance and usage of AI features while respecting user privacy. This system ensures that instrumentation is domain-specific and follows strict data-handling rules. - **TelemetryEvent Trait**: Defined in `warp_core`, this trait ensures all events have a name, payload, and description [.agents/skills/add-telemetry/SKILL.md32-34](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L32-L34) - **UGC Filtering**: The system explicitly checks for User Generated Content (UGC) via the `contains_ugc()` method to ensure sensitive data is not accidentally logged [.agents/skills/add-telemetry/SKILL.md81-87](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L81-L87) - **Enablement States**: Events can be gated by `FeatureFlag` or `Channel` using the `EnablementState` enum [.agents/skills/add-telemetry/SKILL.md49-54](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L49-L54) - **Registration**: Events are registered via the `register_telemetry_event!` macro and dispatched using `send_telemetry_from_ctx!` [.agents/skills/add-telemetry/SKILL.md127-147](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L127-L147) Title: Telemetry Data Flow and Code Entities ``` ``` Sources: [.agents/skills/add-telemetry/SKILL.md10-120](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L10-L120) [.agents/skills/add-telemetry/SKILL.md127-147](https://github.com/warpdotdev/Warp/blob/81910e24/.agents/skills/add-telemetry/SKILL.md?plain=1#L127-L147) For details, see [Telemetry System](/content/warpdotdev/Warp/4.4-telemetry-system/index.html).