Skip to main content
Agents have been released to all organizations. For details about the rollout and migration from Ravenna AI, see the release notes.
Overview

​
Overview

Ravenna lets you create and deploy custom AI Agents directly into your Slack channels. Build agents that triage requests, answer questions, and automate routine tasks. All configured through natural language prompts. Customize everything from response logic and tool integrations to personality, tone, and communication style. Whether you need instant FAQ responses, intelligent ticket routing, or automated workflows with third-party tools, Ravenna Agents can handle it.

​
Setting Up

Setting Up an AI Agent

For a detailed walkthrough on creating and deploying AI Agents, please refer to our Getting Started guide.

​
Capabilities

​
Escalation instructions

Escalation instructions are guidelines that tell your agent how to handle situations where it cannot resolve a request on its own. Without custom escalation instructions, your agent uses sensible defaults:
  • Escalate to a human agent only when you cannot solve the problem using knowledge base lookups or available workflows/actions
  • Avoid unnecessary back-and-forth with the requester—if clarifying questions don’t help, proceed with escalation
  • When escalating, create a ticket and inform the user that a human agent will take over
  • Once escalated, do not attempt to further solve the issue

​
Configuring escalation instructions

To customize escalation behavior:
  1. Navigate to your agent’s settings
  2. Find the Escalation Instructions section under Capabilities
  3. Click Add (or Edit if instructions already exist)
  4. Write your custom escalation guidelines
  5. Save your changes

​
Using mentions in escalation instructions

Like rules, escalation instructions support the @ mention feature. You can reference:
  • Knowledge bases: Direct the agent to check specific knowledge sources before escalating
  • Workflows: Trigger specific workflows as part of the escalation process
  • Forms: Create tickets with specific forms when escalating
Example with mentions: 
Before escalating, check `@IT Knowledge Base` one more time for any relevant
articles. If still unable to resolve, create a ticket with
`@Form - General Support` and inform the user that a specialist
will follow up within 24 hours.
Example with workflow: 
When you cannot resolve a user's access request, trigger 
`@Workflow - Escalated Access Review` to route the request through 
the proper approval chain. Inform the user that their request requires 
manager approval and they'll be notified within 1 business day.

​
Best practices

  • Be specific about escalation triggers: Define clear conditions for when escalation should occur
  • Include user communication: Tell the agent what to say to users when escalating
  • Set expectations: Include information about response times or next steps
  • Reference resources: Use @ mentions to connect escalation to specific workflows or request types

​
Rules

Rules are specialized instructions that define how your agent handles specific scenarios. Each rule teaches your agent a particular capability using natural language prompts. You can @ mention Ravenna resources like Request Types, Knowledge Folders, and Tools to give your agent context-aware abilities. Rules are the building blocks of your agent’s behavior. Each rule contains:
  • Title: A descriptive name for the rule (e.g., “Password Reset Handler”)
  • Instruction: Natural language instructions that tell the agent what to do and when
  • Enabled/Disabled toggle: Control whether the rule is active

​
When to use rules

Use rules when you want your agent to:
  • Handle specific types of requests consistently
  • Route requests to the correct Form
  • Reference specific Knowledge sources for answers
  • Follow a defined process for common scenarios
  • Provide specialized responses for particular topics

​
Writing effective rules

Be specific about triggers: Clearly define when the skill should activate.
When a user asks about password resets, account lockouts, or login issues...
Reference resources with @ mentions: Use @ to link to specific Ravenna resources.
Check `@IT Knowledge Base` for relevant articles before responding.
Create a ticket with `@Form - Password Reset` if action is needed.
Define the expected outcome: Tell the agent what success looks like.
Inform the user that their request has been logged and provide the ticket number.
Keep instructions focused: Each rule should handle one type of scenario. Create multiple rules for different use cases rather than one complex rule.
Knowledge-first response
When a user asks a question, first check `@IT Knowledge Base` for relevant
articles. If you find an article that answers the question, provide a summary
and link to the article. If no articles are found, create a support ticket
with `@Form - General Inquiry` and inform the user that their request
has been logged.
Password reset handling
When a user requests a password reset or reports being locked out of their
account, create a ticket with `@Form - Password Reset`. Confirm to
the user that their request has been submitted and that IT will process it
shortly.
Software access requests
When a user requests access to software or applications, ask them to specify
which application they need and their business justification. Then create a
ticket with `@Form - Software Access Request` including the details
they provided.
Hardware issues
When a user reports hardware problems (laptop, monitor, keyboard, mouse),
first ask clarifying questions about the issue. Then create a ticket with
`@Form - Hardware Support` and let them know an IT technician will
follow up.
Workflow automation
When a user requests software access, ask which application they need and
their business justification. Then trigger `@Workflow - Software Access Request`
with the details provided. The workflow will handle provisioning and
approvals automatically.
Multi-step process
When a new employee starts, trigger `@Workflow - Employee Onboarding` to
automatically provision their accounts, assign equipment, and schedule
orientation. Confirm with the manager that the onboarding process has begun.
  • Use clear, conversational language: Write instructions as if you’re explaining to a colleague
  • Break complex logic into steps: Number your steps for multi-part processes
  • Include fallback behavior: Tell the agent what to do if the primary action isn’t possible
  • Specify tone when needed: Add guidance like “respond empathetically” for sensitive topics
  • Form access: You must reference Forms within rules for the agent to create tickets of that type. Your agent does not have access to all Forms by default.
  • Workflow access: You must reference Workflows within rules for the agent to trigger them. Your agent does not have access to all Workflows by default.
  • Rule conflicts: If multiple rules could apply to a request, the agent uses its judgment to select the most appropriate one. Keep rules distinct to avoid ambiguity.

​
Workspace-level rules management

Manage rules at the workspace level from the Rules tab on the Agents page. This centralized view lets you create reusable rules that can be shared across multiple agents.

​
Accessing the Rules tab

  1. Navigate to Agents in your workspace
  2. Click the Rules tab at the top of the page
  3. View all rules created in your workspace

​
Creating workspace-level rules

  1. Click New Rule from the Rules tab
  2. Enter a descriptive Title for the rule
  3. Write the Instruction using natural language
  4. Use @ mentions to reference Forms, Knowledge Folders, Workflows, and Tools
  5. Click Save

​
Editing rules

  1. Click on any rule in the Rules tab to open it
  2. Modify the title or instruction as needed
  3. Click Save to apply changes
Changes to workspace-level rules automatically apply to all agents using that rule.

​
Deleting rules

  1. Click on the rule you want to delete
  2. Click Delete
  3. Confirm the deletion
Deletion restrictions: You cannot delete a rule that is currently attached to one or more agents. To delete the rule, first remove it from all agents that are using it.

​
Workspace-level vs agent-specific rules

AspectWorkspace-level rulesAgent-specific rules
LocationRules tab on Agents pageIndividual agent’s Capabilities section
ReusabilityCan be attached to multiple agentsOnly available to that specific agent
ManagementCentralized editing—changes apply everywhereEdited per-agent
Best forCommon scenarios shared across teamsAgent-specific behavior
When to use workspace-level rules: Create workspace-level rules for common scenarios like password resets, software access requests, or general IT support that multiple agents should handle consistently. Use agent-specific rules for behavior unique to a particular agent or channel.

​
Reusing rules across agents

Workspace-level rules can be attached to multiple agents, enabling consistent behavior across your organization:
  1. Create a rule in the Rules tab
  2. Open any agent and navigate to Capabilities > Rules
  3. Click Add Rule and select from your workspace rules
  4. The same rule can be added to as many agents as needed
When you update a workspace-level rule, the changes automatically propagate to all agents using that rule.

​
Tools

Tools extend your agent’s capabilities by connecting to external integrations. Tools are available through integrations that support tool actions—once an integration is installed, its tools become available to reference within your rules.
Tools are used within rules by @ mentioning specific tool actions. When writing a rule, you reference tools to tell the agent exactly when and how to use them.For example, if someone messages about their device being slow:
Device Troubleshooting Skill
When a user reports their device is slow or having performance issues, `@Look up device with Fleet` to get the device information, then `@Run query with Fleet` to check system diagnostics. Analyze the returned information and provide basic troubleshooting steps based on what you find.
Tools require the corresponding integration to be connected to your organization. If an integration is disconnected, tools for that integration will show a warning indicator.
Tools are organized by integration. Available tools include:Fleet (Device Management)
  • Host Info - Get basic information about a user’s device (hostname, platform, OS version, status)
  • Host Health - Check the health status of a device
  • List Queries - List available saved queries
  • Run Saved Query - Execute a saved query on a device
HubSpot (CRM)
  • Search Contacts - Find contacts by email address
  • Search Companies - Search for companies in HubSpot
  • Search Deals - Search and filter deals
  • Get Deal - Retrieve details about a specific deal
  • List Deals - List deals with optional filters
  • List Owners - List HubSpot users/owners
Ravenna
  • Web Search - Search the web for information relevant to user queries

​
Knowledge

Select specific Knowledge Folders for your agent to access when answering user questions. This ensures the agent provides accurate and relevant information based on your organization’s knowledge base.

​
Identity

​
Personality

Provide a custom prompt to define your agent’s personality, tone, and communication style. This prompt will guide how the agent interacts with users.
Avoid including instructions about tools/processes in this section. Focus on the agent’s character and manner of speaking.
Select the desired length of the agent’s responses: Concise, Balanced, or Verbose.
Choose the tone of the agent’s communication: Business, Casual, or Humourous.
Set whether the agent should use emojis in its responses and if so, how often: None, Minimal, Moderate, High

​
Slack

Define how the agent should respond to messages in Slack channels.
  • Respond to all messages - The agent will reply to every message in the channel.
  • Respond to mentions only - The agent will only reply when directly mentioned.
  • Respond to requests only - The agent will only reply to messages that are detected as requests for assistance.
Define how the agent should respond to messages in a Slack thread.
  • Respond to all messages - The agent will reply to every message in the thread.
  • Respond to mentions only - The agent will only reply when directly mentioned.

​
Response elements

Configure what UI elements appear in the agent’s Slack responses. These settings control the visual components displayed alongside AI answers when the response includes citations from your knowledge base.
Display the source link in agent responses. When enabled, users see links to the knowledge base articles or documents that the AI used to generate its answer.Default: EnabledThis helps users verify information and explore related documentation.
Display thumbs up/down feedback buttons below AI responses. When enabled, users can indicate whether the response was helpful.Default: EnabledFeedback data helps you identify knowledge gaps and improve your documentation.
Display a button that allows users to create a support ticket directly from the AI response. This is useful when the AI answer doesn’t fully resolve the user’s question and they need human assistance.Default: Disabled
The create ticket button only appears when the ticket has not already been published.

​
Create ticket on 👎

Enable this option to automatically create a support ticket whenever a user reacts with a thumbs down (👎) emoji to the agent’s response.
This setting only appears when Show feedback buttons is enabled.

​
Auto-respond

Enable automatic AI responses for tickets created from Email and Integration sources (Jira, Linear, GitHub, etc.). When enabled, the agent will automatically respond to new tickets using its assigned knowledge bases.
Enable this option to automatically respond to tickets created from inbound emails. The agent will analyze the email content and provide a response based on its knowledge bases.
Enable this option to automatically respond to tickets created from integrations such as Jira, Linear, and GitHub. The agent will analyze the ticket content and provide a response based on its knowledge bases.
Set a delay (0-300 seconds) before the agent responds. This can be useful to allow time for additional context to be added to the ticket before the AI responds. Options include:
  • Immediate (0 seconds)
  • 5 seconds
  • 10 seconds
  • 30 seconds
  • 1 minute
  • 2 minutes
  • 5 minutes
Enable this option to automatically create tickets when all required form fields are pre-filled by the agent, without requiring user review.Default: DisabledWhen disabled (default), users are shown a pre-filled form to review and submit manually. When enabled, the agent bypasses the form review step and creates the ticket immediately if all required fields have been provided.Enable this setting when you want a faster, more streamlined experience and trust the agent to accurately fill in form fields based on the conversation context.
If the agent cannot provide a definitive answer, the ticket will be tagged with ai-unresolved for human follow-up.

​
Connections

Select which Channels the agent should be deployed to. You can add or remove channels at any time after deployment.

​
Chat logs

All interactions between users and the agent are logged and can be reviewed in the Chat Logs section. This allows you to monitor the agent’s performance, review conversations, and make adjustments to improve its effectiveness.