> ## Documentation Index > Fetch the complete documentation index at: https://docs.intelligence-management-platform.com/llms.txt > Use this file to discover all available pages before exploring further. # Agent workbench > All eight workbench sections for configuring an agent: basics, instructions, knowledge, tools, chat experience, appearance, access, and developer. export const RightsCallout = ({right, flags}) => Who sees this: requires {right === "none" ? "no special rights — available to every signed-in user" : `the ${right} right (or super admin)`}. {flags && flags !== "none" ? ` Only visible when the server enables ${flags}.` : ""} ; IMP agent workbench showing the section navigation rail with Basics selected, the Basics form with name, category, description, and model fields, and a Save Bar at the bottom with unsaved changes ## Opening the workbench From the [agents list](/building/agents/overview), click any agent row to open its detail panel, then click **Edit**. You can also navigate directly to `/agents/edit/{id}`. ## Header actions The workbench header shows the agent's name with a breadcrumb back to **Agents**. The action bar on the right has: * **Active / Inactive toggle** — flip the agent between active (available to users) and inactive (hidden from chat). * **Test in chat** — opens a new conversation with this agent in `/chat/{id}/new` so you can try changes without leaving the workbench. If you have unsaved edits, IMP prompts you to confirm before navigating. * **Save** — commits all staged changes. The Save Bar also appears at the viewport bottom whenever there are unsaved edits. * **Overflow menu (⋯)** — **Duplicate**, **Copy ID**, **Copy slug** (when a slug is set), and **Delete** (destructive, requires typing a confirmation phrase). Changes are staged locally until you click **Save**. Navigating away with unsaved edits triggers a confirmation guard. ## Basics The Basics section sets the agent's identity and the model it uses. | Field | What it does | | --------------- | ---------------------------------------------------------------------------------------------------------------------------- | | **Name** | The display name shown in the agent picker and conversation header. Required. | | **Category** | Optional label (marketing / sales / finance / hr / coding / support / research / knowledge / product) for organizing agents. | | **Description** | A short summary shown in the agent detail panel. | | **Model** | The LLM this agent uses. Searchable selector with a badge showing the current model and provider. | Below the model selector, **modality tiles** (Text, Images, Files, Audio, Video) show which input types the selected model supports. Tap a tile to see the allowed MIME types. ## Instructions The Instructions section defines what the agent knows to do. * **Custom instructions** — the main markdown editor. Write system-prompt text here: persona, tone, task constraints, examples. Supports headings, lists, and code blocks. This is the primary place to shape agent behavior. * **System instructions** (read-only, when set) — collapsed disclosure showing instructions injected by a developer via the backend SDK. You cannot edit these from the UI; they come from code. * **Prompt templates** — a panel listing prompt templates assigned to this agent. Users can insert these from the chat composer's **＋** menu. Click **Manage** to open the prompt browser and add or remove templates. Prompt templates are a good way to give users pre-written starting points without baking that text into the system prompt. ## Knowledge & memory The Knowledge & memory section controls what the agent can retrieve and remember. **Agentic retrieval** (when the `agentic_context_search` tool is installed on this deployment): a toggle that enables a tool-loop retrieval mode. When enabled, the agent decides when to search and which knowledge bases to query. Enabling opens the **Configure knowledge search** wizard, which walks through Sources, Routing, Vocabulary, Memory, and Behavior steps. You can re-open the wizard at any time by clicking the summary card. **Long-term memory**: a context combobox. Select a context to give the agent a personal memory store — it reads from and writes items to that context per user over time. Set to "None" to disable memory. See [Knowledge overview](/building/knowledge/overview) for how contexts, items, and embeddings work. ## Tools and skills The Tools & skills section lists every tool and skill available on this deployment and lets you toggle them per agent. * **Search** — filter the tool list by name or description. * **Category filter** — narrow by tool category. * **Expand all / Collapse all** — control the accordion state of all category groups. * **Result count** — shows how many tools are found (if filtered) or available. For detailed guidance on tool configuration, sub-agents, and skills, see [Tools and skills](/building/agents/tools-and-skills). ## Chat experience The Chat experience section controls what users see in the conversation. | Setting | What it does | | ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | **Welcome message** | Text shown when a user opens a new chat before sending a message. Supports plain text; leave blank for no message. | | **Follow-up suggestions** | Toggle to enable auto-generated follow-up chips after each agent reply. | | **Feedback collection** | Toggle to enable thumbs-up / thumbs-down feedback buttons on agent messages. | | **Default agent** | Toggle to make this the agent that loads automatically when a user opens Chat (instead of the agent picker). Only one agent can be default at a time. | | **Sandbox** | Toggle to give the agent a sandboxed code execution environment for running code snippets. | | **Max tool steps** | Maximum number of sequential tool calls the agent may make before stopping (0–50). Prevents run-away tool loops. | ## Appearance The Appearance section controls the agent's visual identity. * **Avatar** — displays the current avatar image (or initial monogram if none is set). Click **Generate avatar** (when available on this deployment) to open the AI avatar generator: describe the look, choose a style, and apply the result. The generator produces a square image stored in your file storage. * **Idle animation** — upload a Lottie JSON file that plays while the agent is waiting for input (S3-gated; only shown when S3 is configured). A preview appears after upload. * **Responding animation** — upload a Lottie JSON that plays while the agent is generating a reply. Preview appears after upload. ## Access The Access section controls who can chat with this agent. The **RBAC control** lets you choose one of four sharing modes: | Mode | Who can use the agent | | ----------- | ------------------------------------------- | | **Private** | Only you. | | **Users** | Specific users you pick from the directory. | | **Roles** | All users assigned a specific role. | | **Public** | Every signed-in user in the organization. | Select a mode, then add the users or roles. Changes take effect after saving. For a full guide to sharing and team-level access, see [Access](/building/agents/access-and-safety). ## Developer The Developer section exposes integration identifiers and a ready-to-use API snippet. * **Agent ID** — the stable UUID for this agent. Copy it for use in API calls or backend configuration. * **Slug** (when set) — the human-readable path component. Displayed as `agents/{slug}/run/{id}` for easy copy-paste into URLs. * **Endpoint** — the full streaming endpoint URL for this agent, formed as `{BACKEND}/agents/{slug}/run/{id}`. * **curl snippet** — a ready-to-run curl command that sends a test message to the endpoint. * **TypeScript snippet** — an equivalent `fetch` call with typed headers and a streaming body reader. Set `EXULU_API_TOKEN` in your environment and you can run the curl snippet directly. The TypeScript snippet is production-ready with `crypto.randomUUID()` for session and request IDs.