AI Automation

AI Automation

Configure how Keva's AI handles your support tickets

Keva's AI is highly configurable. You control how autonomous it is, what actions require approval, and how it learns from your preferences.

Core Concepts

Autonomy Level

How independently Keva operates, from fully manual to fully autonomous. The autonomy slider is the primary control for AI behavior.

Learn about Autonomy Levels →

Trust Controls

Additional safeguards that require confirmation for sensitive actions, regardless of autonomy level.

Learn about Trust Controls →

Action Limits

Daily caps on actions Keva can take, preventing runaway automation.

Learn about Action Limits →

Key Features

How AI Processes Tickets

When a ticket arrives, Keva:

  1. Analyzes - Understands the request, intent, and sentiment
  2. Researches - Checks knowledge base, customer history, connected platforms
  3. Decides - Determines the best response or action
  4. Acts - Drafts, queues for approval, or executes based on autonomy level

Quick Configuration

SettingValueWhy
Autonomy Level3Handles routine tickets, escalates complex
Trust ControlsOnProtects sensitive actions
Action LimitsDefaultPrevents runaway automation

As You Build Confidence

WeekAutonomyNotes
1-2Level 2-3Review most actions
3-4Level 3-4Trust routine handling
5+Level 4-5Minimal human intervention

AI Settings Location

All AI configuration is at Settings → AI:

  • Autonomy Level - Main slider
  • Trust Controls - Toggle sensitive action confirmations
  • Action Limits - Daily caps
  • System Prompt - AI persona customization
  • Escalation Rules - When to flag for humans

Monitoring AI Performance

Track AI effectiveness in Analytics:

  • Resolution rate - % of tickets resolved by AI
  • First response time - Speed of AI replies
  • Escalation rate - How often humans needed
  • Customer satisfaction - CSAT for AI-handled tickets
  • Accuracy - How often AI responses are edited

Improving AI Over Time

Add Knowledge Base Content

The more information Keva has, the better responses:

  • FAQs
  • Product documentation
  • Policy documents
  • Common scenarios

Review AI Reasoning

Check the Why Panel to understand decisions:

  • Correct good behavior
  • Catch mistakes early
  • Identify training gaps

Provide Feedback

When editing AI responses:

  • Explain what was wrong
  • Show the correct approach
  • AI learns from edits

Adjust Gradually

Increase autonomy incrementally:

  • Start conservative
  • Verify quality at each level
  • Step back if issues arise