--- title: Anatomy of an agent description: "Every part of an agent, where it lives in the workspace, and which parts change with the agent's modality and prompt type." --- An agent is one object with a fixed shape: identity, a language and a voice or a model, a prompt, tools, variables, outcomes, a speech pipeline and privacy settings. This page maps each part to the section of the **agent workspace** where you set it. :::note[When to read this] Read this once, before the deeper pages. Every other page in **Build** covers one of the parts named here. ::: ## The workspace Open an agent from **AI Agents** and it opens at `/agents/edit/`. The header carries the agent's name, its version (`v0.3`), **Agent info**, **More actions** on a single-prompt agent, **Share agent**, **Save** and **Publish**. The sidebar lists the sections in four groups. | Group | Sections | Notes | |---|---|---| | **Build** | **Settings**, **Advanced**, **Flow**, **Tools**, **Outcomes**, **Memory** | **Flow** appears for flow agents only | | **Testing** | **Chat**, **Call**, **Evaluation** | **Call** appears for voice agents only, **Chat** for text agents only | | **Improve** | **Recommendations**, **Change Requests** | Suggested next steps, and prompt changes drafted from feedback | | **Release** | **Publish**, **Widget**, **Deployments**, **Versions** | **Publish** holds the launch checklist; **Deployments** appears for text agents only | ![The workspace sidebar of a voice agent with a single prompt.](/media/build/agent-workspace-sidebar.webp) **Agent info** opens an audit card: **Created by**, **Updated by**, **Updated at** and the **Agent ID**. **Share agent** opens one dialog for the public link and the embed code, both behind the **Agent Visibility** switch; see [Share link](/deploy/widget-and-embed/share-link). **More actions** holds **Migrate to Flow Agent**, which turns the prompt, tools, outcomes and knowledge bases into a flow on a new agent named after the original with `(Flow)` added. The original is not changed, so its campaigns and numbers keep running; see [Choosing a prompt type](/build/choosing-a-prompt-type). ## The parts ### General The top card of **Settings**. It shows the chips **Modality** and **Prompt type**, which are fixed at creation, and the fields you can change: **Name**, **Description**, **Language**, and for voice agents the voice and **Background audio**. Text agents have a **Model** card instead of a voice. ![The General card of a voice agent.](/media/build/general-card.webp) - Modality: [Choosing a modality](/build/choosing-a-modality) - Prompt type: [Choosing a prompt type](/build/choosing-a-prompt-type) - Language: [Languages](/build/voice-and-audio/languages) - Voice: [Choosing a voice](/build/voice-and-audio/choosing-a-voice) - Model: [LLM configuration](/build/llm-configuration) ### Prompt Single-prompt agents have a **Prompt** card with three fields: **Agent Identity**, **Tasks** and **Guardrails**. Three buttons sit above it: **Variables**, **Manage tools** and **Generate With AI**. Flow agents have no Prompt card; their instructions live in nodes under **Flow**. - Writing it: [Prompting guide](/build/prompting/prompting-guide) - Drafting it: [Generate with AI](/build/prompting/generate-with-ai) - Placeholders: [Dynamic variables](/build/dynamic-variables) - Actions: [Tools overview](/build/tools/overview) ### Conversation Voice agents, single prompt or flow, have a **Conversation** card with **Who talks first** and **First message**. Text agents do not; the person always writes first. See [First message and conversation](/build/prompting/first-message-and-conversation). ### Advanced For voice agents, **Advanced** holds the speech pipeline in five cards: **Voice activity**, **Turn detection**, **Noise reduction**, **AMD** and **Reminders**, followed by **Privacy**. For text agents, **Advanced** is the **Privacy** card alone. - [Voice activity detection](/build/speech-pipeline/voice-activity-detection) - [Turn detection](/build/speech-pipeline/turn-detection) - [Noise suppression](/build/voice-and-audio/noise-suppression) - [Answering machine detection](/build/speech-pipeline/answering-machine-detection) - [Silence, reminders and call duration](/build/speech-pipeline/silence-reminders-and-call-duration) - [Data retention](/build/privacy/data-retention), [PII redaction](/build/privacy/pii-redaction), [Storage destination](/build/privacy/storage-destination), [Memory](/build/memory) ### Tools The actions the agent can take besides talking: end or transfer the call, call your APIs, book a meeting, hand off to another agent. **Add tool** adds one, and each configured tool is listed with its description, which is what the model reads to decide when to use it. See [Tools overview](/build/tools/overview). ### Outcomes The structured fields the agent fills after every conversation, each with a variable name, a description and optional fixed values. See [Outcomes](/build/outcomes). ### Memory What the agent remembers about each contact. Pick a contact to see it, and forget anything that should be cleared. The switch that turns memory on is in **Advanced**. See [Memory](/build/memory). ## Improve **Recommendations** ranks next steps for the agent by expected impact and is re-evaluated after every revision. **Change Requests** holds prompt changes drafted by AI from thumb-down feedback, to review and accept as a new revision. See [Recommendations](/test-and-improve/recommendations) and [Change requests](/test-and-improve/change-requests). ## Saving and versions Editing any field enables **Save** and shows a bar reading **You have unsaved changes** with a count, **Undo Changes** and **View Changes**. Saving creates a new revision; the counter in the header moves from `v0.2` to `v0.3`. Every version is kept under **Versions**, with a diff and rollback. See [Versions](/test-and-improve/versions). ## What changes with the agent type | Part | Voice, single prompt | Voice, flow | Text | |---|---|---|---| | Voice and Background audio | Yes | Yes | No | | Model picker | No | No | Yes | | Prompt card | Yes | No, nodes instead | Yes | | Conversation card | Yes | Yes | No | | Speech pipeline cards | Yes | Yes | No | | Privacy card | Yes | Yes | Yes | | Call test | Yes | Yes | No | | Chat test | No | No | Yes | | Deployments | No | No | Yes | ## Related - [Core concepts](/get-started/core-concepts) - [Choosing a modality](/build/choosing-a-modality) - [Choosing a prompt type](/build/choosing-a-prompt-type) - [Testing in the browser](/test-and-improve/testing-in-the-browser) - [Versions](/test-and-improve/versions)