Name and description
Give your agent a name, icon, and short description. The description helps others quickly understand what the agent does.Triggers
A Trigger is an event that automatically starts an Agent, transforming it from an on-demand tool into a proactive agent running in the background. You can set up Triggers to run Agents based on a schedule, specific events in your other software, or incoming webhooks.A Trigger is not required if you only plan to run an Agent manually.
Based on a schedule
This trigger runs an Agent on a recurring, time-based interval. You can set it to run daily, weekly, or monthly.Based on a knowledge event
This trigger runs an Agent automatically when synced knowledge changes in one of your connected systems. After you choose a Source, the Trigger when menu shows source-specific options such as Opportunity updated, Deal updated, Call created, Thread created, or Thread reply added. For updated events, add at least one Filter condition. The Agent runs when that field changes to the value you configured. For example, use Source = Salesforce, Trigger when = Opportunity updated, and If Stage equals Closed Won to run when an Opportunity moves to Closed Won.Based on a webhook
This trigger runs an Agent when it receives an HTTP request from an external system. This is a powerful way to integrate with internal tools or any third-party platform that can send webhooks, even if it doesn’t have a direct integration with Realm.For detailed step-by-step instructions on setting up each trigger type, see Creating triggers.
Agent instructions
Instructions are the most important part of an agent. They define how the agent behaves, what it should do, and how it should approach the task. You can write them manually or ask the Operator panel in the editor to draft or rewrite them. Specificity improves results. Clear goals, step-by-step guidance, relevant context, and explicit references to tools or documents all help the agent perform more reliably. The key concepts in agent instructions are:- Purpose: Start by clearly describing what the agent is meant to do. For example: “Your task is to help me prepare for discovery calls. Gather relevant background information and produce a concise summary that helps me understand who the customer is, what they do, and how we might fit.”
- Step-by-step guidance: Break the workflow into numbered steps. This makes the agent’s process easier to follow and improves consistency.
- References to the right context: You can point the agent to specific documents, integrations, tools, or other agents. For example, you might ask it to review a specific document in one step, check HubSpot in another, or call another agent as part of the workflow. To insert these references, type the
@character in the instructions field or click the insert icon. To add a subagent, select the agent from that selector. - Variables for reusable workflows: Use
{{ }}to define variables the user fills in when running the agent, such as{{Customer}}or{{Deal}}. This is useful for reusable workflows like a Customer Health agent, where the agent can run against any company based on the input provided.
For prompting best practices and how to delegate work to other Agents, see Writing instructions.
Tools
Tools allow agents to take actions in external systems, such as sending emails, updating CRM records, creating tickets, or posting messages. Realm includes built-in tools and also supports integrations via MCP (Model Context Protocol). In the agent editor, you can control which tools an agent can use and configure how each action behaves. For each action you can choose:
You can also configure parameters for each action:
- Preset parameters: Lock a parameter to a fixed value (for example, always post messages to a specific Slack channel).
- Hidden parameters: Hide parameters from the model so they cannot be modified or accessed by the agent.
For more details on managing tools across your organization, see Admin guide: Tools.
Knowledge
The Knowledge section defines what indexed context the agent can access when running. When you add knowledge to an agent, it becomes searchable. The agent can use it when it’s relevant, but it won’t read everything by default. If you need the agent to always consider a specific source, tag it. Tagged content is included every time the agent runs. Untagged content is only used when the agent decides it’s relevant.Allow all
The agent can access all connected knowledge sources. Existing document permissions are respected, so users only see information they already have access to.Limited
Restrict the agent to specific folders, channels, or files. Selecting a folder includes all subfolders and content within it. Use this when the agent should only work with a defined set of sources.No knowledge
The agent runs without access to internal company data and behaves like a general-purpose AI. You can also control whether the agent can use Web Search. Set it to always enabled, turn it off, or leave it user selectable. User selectable starts on; if the user turns it off, the browser remembers that choice for the agent for the rest of the session. In the web chat UI, Research thinking mode always uses Web Search, even for an agent that has it turned off; the public API does not apply this override, so a Research request against an agent with Web Search turned off does not use it. Additionally, you can upload files directly from your computer to include them in the agent’s knowledge.Advanced settings
Advanced settings allow you to control how the agent reasons, performs research, and processes information.- Thinking mode: Controls how deeply the agent reasons about a task. Fast prioritizes speed, Research performs deeper multi-step reasoning for complex tasks, and Auto lets Realm decide the best mode.
- Image generation: Allows the agent to generate or edit images using AI. Enable this if the agent needs to create visuals as part of its workflow.
- Skip search: Allows the agent to answer questions directly from the selected knowledge without running a search step. This setting is only available when the agent’s knowledge base is small and clearly defined, typically less than 20 documents.
- Search filters: Defines default filters used when the agent searches for information. Filters can restrict results by attributes such as author, date, project, or other metadata.
- Override model: By default, Realm selects the best language model automatically. You can enable Override model to choose a specific model (for example, Claude Sonnet 5 or Gemini 3.7 Flash) for the agent’s final answer.
Testing and iterating
The agent editor provides a side-by-side chat view, allowing you to test your agent with different queries and see the results in real time. Refine the instructions, adjust knowledge sources, and tweak the configuration until the agent performs exactly as needed. After publishing, the agent page summarizes the instructions, connected tools, knowledge, and capabilities that users rely on when they run it. The side panel also shows recent trigger runs, Chat usage for the last 30 days, configured Slack channels, access, and triggers. Use this page to verify what an agent can reach and how it has been used before changing its configuration.Version history
Realm keeps a version history of every agent. Each time you publish, the previous configuration is preserved, so you can always see how an agent has changed over time and go back to an earlier setup. Open the history from the clock icon in the agent editor. The panel lists every version with its name, when it was created, and who created it. The published version is tagged Up to date, and unpublished edits appear at the top as a Modified version. From the menu on a version you can:- Show difference: See what changed, both compared to the currently published version and compared to the version that came right before it. Changes cover the agent’s configuration, including instructions, knowledge, and advanced settings.
- Restore version: Make that version the published one again. The restored version becomes immediately available to everyone using the agent. If the agent is published and you have unpublished edits, Realm asks whether to publish or discard them first.
Sharing agents with your team
Share an agent with your team so others can use it directly or customize their own copy. By default, team members with access can run the agent from the shared link or the agent page, and you can also give individual users access with User or Editor permissions. You can control who can access the agent from the sharing menu:- Restricted: Only people who already have access can use it through the link.
- Anyone in Realm: Anyone in your Realm workspace can use the agent.
- Specific people: Add individual teammates and choose whether they are a User or Editor.