Skip to main content

Common Workflows

Step-by-step guides for common administrative tasks in Outermind.

Overview​

This guide provides detailed workflows for common tasks you'll perform as an Outermind administrator. Each workflow includes prerequisites, step-by-step instructions, and verification steps.

Agent Management Workflows​

Creating a New Agent​

Goal: Set up a new specialist agent for email processing

Prerequisites:

  • Active LLM provider
  • Understanding of agent's purpose
  • List of tools agent will need

Steps:

  1. Navigate to Workforce > Agents > Agents & SMEs
  2. Click Add Agent
  3. Fill in basic information:
    • Name: Descriptive name (e.g., "Sales Inquiry Agent")
    • Description: Brief purpose summary
  4. Select LLM model based on task complexity
  5. Set temperature (0.7 recommended for most cases)
  6. Write instructions following the template in Agents documentation
  7. Click Improve with AI for suggestions
  8. Select required tools
  9. Click Save

Verification:

  • Agent appears in list with "Active" status
  • Test by sending email to assigned mailbox
  • Review execution for expected behavior

Cloning an Existing Agent​

Goal: Create a new agent based on an existing one

Steps:

  1. Go to Workforce > Agents > Agents & SMEs
  2. Find the agent to clone
  3. Click the clone icon (or open and copy settings)
  4. Modify name and description
  5. Adjust instructions as needed
  6. Update tool assignments if different
  7. Save the new agent

When to clone:

  • Creating similar agents for different teams
  • Testing instruction changes safely
  • Setting up development/production pairs

Updating Agent Instructions​

Goal: Improve agent behavior through instruction changes

Prerequisites:

  • Identified issue or improvement area
  • Example executions showing current behavior

Steps:

  1. Go to Workforce > Agents > Agents & SMEs
  2. Click on the agent to edit
  3. Review current instructions
  4. Make targeted changes:
    • Add specific guidance for problem scenarios
    • Clarify ambiguous instructions
    • Add examples if helpful
  5. Click Improve with AI for suggestions (optional)
  6. Save changes
  7. Test with a representative email

Best practices:

  • Make one change at a time
  • Document what you changed and why
  • Test before and after with same input
  • Monitor for unintended effects

Mailbox Management Workflows​

Adding a New Monitored Mailbox​

Goal: Start monitoring a new email address

Prerequisites:

  • Microsoft 365 shared mailbox created
  • Active agent to assign
  • Appropriate Azure AD permissions

Steps:

  1. Navigate to Workforce > Agents > Monitored Mailboxes
  2. Click Add Mailbox
  3. Enter mailbox email address
  4. Set display name
  5. Select the agent to process emails
  6. Configure options:
    • Auto-reply enabled/disabled
    • Include thread context (recommended)
  7. Save the mailbox
  8. Click Manage Subscriptions
  9. Click Create Subscription
  10. Verify subscription shows "Active"

Verification:

  • Send test email to the mailbox
  • Check executions within 1-2 minutes
  • Verify response if auto-reply enabled

Changing an Agent Assignment​

Goal: Switch which agent processes a mailbox

Steps:

  1. Go to Workforce > Agents > Monitored Mailboxes
  2. Click on the mailbox
  3. Change the assigned agent
  4. Save changes

Note: Changes take effect immediately for new emails. In-progress executions use the previous agent.

Pausing Email Processing​

Goal: Temporarily stop processing emails

For one mailbox:

  1. Go to the mailbox settings
  2. Set status to inactive
  3. Save

For all mailboxes:

  1. Go to Administration > Account > Settings
  2. Enable "Pause Agent Execution"
  3. Save

Note: Emails received while paused will not be processed. They won't be automatically picked up when resumed.

Troubleshooting Workflows​

Investigating a Failed Execution​

Goal: Understand why an execution failed

Steps:

  1. Go to Governance > Activity History > Agent Executions
  2. Filter by status: "Failed"
  3. Click on the failed execution
  4. Review the timeline:
    • What was the input?
    • Where did it fail?
    • What error message appeared?
  5. Click Troubleshoot with AI for analysis
  6. Identify the root cause
  7. Take corrective action

Common causes:

  • LLM provider unavailable
  • Tool configuration error
  • Invalid response format
  • Timeout

Finding Expensive Executions​

Goal: Identify high-cost executions for optimization

Steps:

  1. Go to Governance > Activity History > Agent Executions
  2. Sort by cost (descending)
  3. Review top executions:
    • Were they legitimate complex tasks?
    • Are there patterns (same agent, same type)?
  4. For high-cost executions:
    • Check token counts
    • Review tool calls (many calls = higher cost)
    • Check response length
  5. Identify optimization opportunities:
    • Shorter instructions
    • Smaller model for simple tasks
    • Fewer unnecessary tool calls

Comparing Agent Performance​

Goal: Determine which agent version performs better

Steps:

  1. Create a clone of the agent
  2. Make the changes to the clone
  3. Set up A/B test:
    • Route some traffic to original
    • Route some to clone
  4. Collect execution data over time
  5. Compare metrics:
    • Success rate
    • Cost per execution
    • Response quality (manual review)
  6. Choose the better performer
  7. Deactivate or delete the other

VIP Management Workflows​

Adding VIP Contacts​

Goal: Ensure important contacts receive priority handling

Steps:

  1. Go to Boardroom > VIPs
  2. Click Add VIP
  3. Enter contact information:
    • Email address (required)
    • Display name
  4. Set the privilege level: medlevel, highlevel or admin (a closed set, not an ordinal scale)
  5. Add notes about special handling
  6. Save

VIPs are added one at a time; there is no bulk CSV import.

Usage in agents: VIP status is resolved automatically during execution setup and appears in the agent's prompt inside the === SENDER IDENTITY === block. There is no tool to assign. Add to agent instructions:

Read the === SENDER IDENTITY === block on every message.
If Classifications includes VIP (Admin) or VIP (High Level), prioritize the
request and ensure a thorough, personalized response.

Knowledge Management Workflows​

Adding a Search Index​

Goal: Make new content searchable by agents

Steps:

  1. Prepare your content (documents, web pages, etc.)
  2. Go to Capabilities > Knowledge (Sources tab)
  3. Add the source:
    • SharePoint: Connect to document library
    • Web: Provide URLs to crawl
    • Upload: Upload files directly
  4. Configure crawl settings
  5. Start initial crawl
  6. Go to Search Indexes
  7. Create or update index with new source
  8. Verify by testing searches

Re-indexing Content​

Goal: Update search index with new or changed content

Steps:

  1. Go to Capabilities > Knowledge (Scans tab)
  2. Find the relevant source
  3. Click Rescan or Full Index
  4. Monitor progress
  5. Verify changes in search results

System Administration Workflows​

Reviewing System Health​

Goal: Ensure all components are working properly

Daily check:

  1. View Governance > Live Operations > System Diagram
    • All components should show connected
  2. Check LLM Providers
    • All should show green status
  3. Check Monitored Mailboxes
    • Subscriptions should be active
  4. Review Governance > Activity History > Agent Executions
    • Check for unusual failure rates
  5. Check Usage
    • Verify costs are expected

Setting Up a New Administrator​

Goal: Grant admin access to a new user

Steps:

  1. Ensure user has Azure AD account
  2. Go to Account Settings > Team > Users
  3. Click Add User
  4. Select the Azure AD user
  5. Assign the "Admin" role
  6. Save

User will need to:

  • Sign in with their Azure AD credentials
  • Accept any consent prompts
  • Access the Admin Console URL

Backing Up Configuration​

Goal: Preserve system configuration for recovery

Recommended backup items:

  • Agent configurations (instructions, tool assignments)
  • VIP lists
  • Search index configurations
  • Provider settings (excluding API keys)

Manual backup:

  1. Export agent instructions to documents
  2. Export VIP list to CSV
  3. Document search index settings
  4. Store in version control or SharePoint

Workflow Checklists​

New Deployment Checklist​

  • LLM Provider configured and tested
  • At least one agent created
  • Agent instructions reviewed and tested
  • Monitored mailbox added
  • Subscription active
  • Test email processed successfully
  • VIP contacts imported (if applicable)
  • Knowledge sources connected (if applicable)
  • User access configured
  • Monitoring in place

Weekly Maintenance Checklist​

  • Review failed executions
  • Check provider health
  • Review cost trends
  • Update knowledge indexes if needed
  • Address any user feedback
  • Update agent instructions if needed

Monthly Review Checklist​

  • Full cost analysis
  • Agent performance review
  • Search index effectiveness
  • User access audit
  • Provider pricing verification
  • Documentation updates