Skip to main content

Overview

KaireonAI includes a built-in AI assistant accessible from every page in the platform. Open it by clicking the AI icon in the top navigation bar. The assistant can:
  • Query any entity — “Show me all active offers in the cross-sell category”
  • Analyze your setup — “Why aren’t customers getting the premium card offer?”
  • Build new entities — “Create a qualification rule targeting customers with balance over $10,000”
  • Simulate changes — “What would happen if I lowered the email frequency cap to 2 per week?”

Guided Autonomy

When the AI assistant needs to create or modify something, it follows a preview → approve → execute flow:
  1. Preview — The assistant shows exactly what it plans to create or change in a preview card
  2. Approve or Cancel — You review the details and click Approve or Cancel
  3. Execute — Only after your approval, the change is applied
This ensures you stay in control while letting the AI handle the complexity.
Read operations and analysis run immediately — no approval needed. Only mutations (create, update, delete, publish) require your confirmation.

Conversation History

Your conversations are automatically saved and can be resumed later:
  • Click the History icon in the AI panel header to see past conversations
  • Click any conversation to resume it
  • Start a New conversation to begin fresh
  • Conversations are shared across your tenant — team members can see shared history

Context-Aware Prompts

The assistant adapts based on which page you’re on:
PageAvailable Tools
Studio pagesOffer management, decision flows, channels, qualification rules, contact policies
Data pagesSchemas, connectors, pipelines, transforms
Algorithm pagesModels, experiments, scoring
Dashboard pagesMetrics queries, health checks
Any pageIntelligence tools (explain, simulate, analyze)

Example Prompts

Building

  • “Create a new email channel with batch delivery mode”
  • “Set up a cross-sell offer for credit cards targeting premium customers”
  • “Build a decision flow that filters by credit score and ranks by propensity”

Analyzing

  • “Why didn’t customer C-1234 receive the home loan offer?”
  • “Which offers have declining conversion rates this week?”
  • “Are there any conflicts in my contact policies?”

Simulating

  • “What happens if I change the minimum credit score from 700 to 650?”
  • “How many more customers would I reach if I increase the SMS cap to 5 per week?”

AI Configuration

Configure the LLM provider in Settings > Integrations > AI / LLM Provider:
ProviderModels
AnthropicClaude Sonnet, Claude Opus
OpenAIGPT-4o, GPT-4
GoogleGemini Pro, Gemini Ultra
Amazon BedrockAny Bedrock-hosted model
Ollama / LM StudioSelf-hosted models