CAIRA Chat Modes Guide¶
🧠 CAIRA's AI Assistant System¶
CAIRA includes a number of chat modes that make working with Azure AI infrastructure as simple as having a conversation.
Available AI Assistants (Chat modes)¶
| Assistant | Purpose | Best For |
|---|---|---|
| CAIRA Assistant | Deploy and manage AI infrastructure | New users, architecture selection, deployments |
| Task Planner | Create implementation plans | Project planning, complex implementations |
| Prompt Builder | Engineer high-quality prompts | AI application development, prompt optimization |
| ADR Creation Coach | Architectural decision documentation | Enterprise governance, decision tracking |
This page will focus primarily on the CAIRA Assistant chatmode.
The CAIRA Assistant - Your Deployment Guide¶
The CAIRA Assistant is your primary guide for deploying Azure AI infrastructure.
What it does for you:
- 🔍 Smart Architecture Selection - Analyzes your requirements and recommends a relevant architecture
- 📋 Step-by-Step Guidance - Breaks down complex deployments into simple, actionable steps
- ⚡ Interactive Deployment - Can execute commands for you or guide you through manual steps
- 🛠️ Real-Time Problem Solving - Troubleshoots issues as they arise
- 📊 Complete Visibility - Shows exactly what will be deployed before you commit
Sample Conversation:
You: "I need to deploy AI infrastructure for my team"
CAIRA Assistant: "I'll help you choose and deploy the perfect AI architecture!
Let me show you the options based on your needs:
1. foundry_basic - Great for learning and simpler usage scenarios.
2. foundry_standard - Enterprise features with data sovereignty.
3. Private variants available for both with network isolation
What's your primary use case - development, production, or enterprise compliance?"
Getting Started - Your First Deployment¶
Step 1: Access CAIRA Assistant¶
In your development environment, select the caira-assistant chat mode.
Example ways to start:
- "Deploy a basic AI Foundry architecture"
- "What architecture should I choose for production workloads?"
- "I need Azure AI Foundry with private networking"
Step 2: Let CAIRA Guide Architecture Selection¶
The CAIRA Assistant will:
- Ask about your requirements (development vs. production, security needs, etc.)
- Present relevant options with clear explanations of each architecture along with key pre-requisites.
- Show deployment complexity and time estimates
- Wait for your choice - never auto-selects without your confirmation
Step 3: Interactive Deployment Options¶
Once you choose an architecture, CAIRA Assistant provides different options for interaction:
Option A: Guided Assistance (Recommended for new users)
- CAIRA executes commands for you
- Provides real-time feedback and progress updates
- Handles errors and troubleshooting automatically
- You see exactly what's happening at each step
Option B: Manual Execution
- CAIRA provides all commands with explanations
- You copy and paste commands in your terminal
- CAIRA explains what each command does
- Great for learning the underlying process
Sample Guided Deployment:
CAIRA Assistant: "I'll deploy foundry_basic for you. Here's what will happen:
1. Configure Azure authentication ✓
2. Initialize Terraform ✓
3. Create deployment plan (17 resources)
4. Deploy AI Foundry with GPT-4o model (estimated: 15-20 minutes)
Ready to proceed? This will create resources in your Azure subscription."
You: "yes"
CAIRA Assistant: "Starting deployment...
✓ Azure authentication configured
✓ Terraform initialized
✓ Creating deployment plan...
Here's what will be deployed: [shows detailed resource list]
Applying deployment... (progress updates continue)"
Additional Resources¶
- 📚 Troubleshooting Guide - Common issues and solutions
- 🛠️ Environment Setup - Development environment configuration