> For the complete documentation index, see [llms.txt](https://alludium.gitbook.io/alludium-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://alludium.gitbook.io/alludium-docs/administration/3.-agent-builder/3.1-agent-details.md). # Agent Details To access Agent Details, open your agent in Agent Builder, click **Configuration**, then select the **Details** sub-tab. This is where you set the agent's name, description, category, and icon. Every agent starts with three fundamentals: **Name** — Clear and functional. Reflects the agent's responsibility, not its personality. Example: Campaign Status Reporter, not CampaignBot. **Description** — States purpose and scope. What does it do, when is it used, when is it not? **Category** — Organizes agents by function. Select from predefined categories or create custom ones. *** ### Name The agent name appears in My Agents, Agent Builder, dashboards, and notifications. Make it immediately clear what the agent does. **Good names:** * Research Agent: B2B SaaS Companies * Weekly Portfolio Report Generator * Post-Meeting Summary and Follow-up * Investor Outreach Drafter **Avoid:** * Vague names: "Agent 1", "New Agent" * Overly long names: "The Agent That Researches Companies and Writes Summaries and Drafts Emails" **Naming conventions for teams:** Use consistent patterns to make agents easy to find: * `[Function]_[Scope]` — Research\_EarlyStageSaaS * `[Output]_[Frequency]` — WeeklyReport\_Portfolio * `[Process]_[Department]` — LeadQualification\_Sales **Character limit:** 100 characters *** ### Description The description explains what the agent does, when to use it, and what it doesn't handle. This appears when browsing agents and helps team members choose the right agent for their task. **Structure:** 1. **Purpose** — What the agent does (1 sentence) 2. **Use cases** — When to invoke it (2-3 bullets) 3. **Scope boundaries** — What it doesn't do (1 sentence) **Example description:** > Researches early-stage B2B SaaS companies and produces structured profiles. > > Use for: Initial target screening, pre-meeting research, competitive intelligence > > Does not evaluate fit against investment thesis or make recommendations. **What to include:** * Primary function * Expected inputs * Output format * Typical use cases * Explicit exclusions **Character limit:** 500 characters *** ### Category Categories organize agents by function, making them easier to find and filter in My Agents and Agent Builder. **How to use:** Select from the dropdown in Agent Details. If none fit, type a new category name to create it. Custom categories appear in the dropdown for all future agents. **Best practices:** * Use predefined categories when possible for consistency * Create custom categories sparingly (too many reduces discoverability) * Use categories that reflect function, not department * Keep category names short (1-2 words) **Filtering by category:** In My Agents and Agent Builder, filter agents by category to quickly find relevant agents. Categories also appear in workspace analytics and usage reports. *** ### Icon Icons provide visual distinction in agent lists and help users quickly identify agents in My Agents. **Selection:** Choose from the provided icon library. Icons should be: * Recognizable at small sizes * Distinct from other agents in your workspace * Related to the agent's function (e.g., magnifying glass for research, envelope for outreach) **Default behavior:** If no icon is selected, Alludium assigns a default based on agent type. *** ### When to Update Agent Details **Update the name when:** * Agent scope changes significantly * Original name is causing confusion * Consolidating multiple agents and need new naming **Update the description when:** * Agent behavior is modified * New use cases emerge * Team members are unclear about scope * Exclusions need clarification **Update the icon when:** * Multiple agents look too similar * Agent function changes * Rebranding workspace organization *** ### Discoverability Agent details directly affect how easily team members find and use agents: **Searchable fields:** * Name appears in search results * Description is indexed for keyword search * Both appear when filtering agents **Best practice:** Include key terms users might search for in the description (e.g., "research", "report", "outreach", "analysis"). *** ### Next Steps With agent details configured, continue to **Prompt and Instructions** to define how your agent thinks, responds, and produces outputs. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## 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://alludium.gitbook.io/alludium-docs/administration/3.-agent-builder/3.1-agent-details.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.