Example: Atmos AI

Configure and use the Atmos AI Assistant with mock components — no cloud credentials required.

Learn more in the Atmos AI documentation.

What You'll See

• Multi-provider AI configuration (OpenAI, Anthropic, Bedrock, Azure OpenAI, Gemini, Grok, Ollama)
• Interactive chat and single-question modes
• Session management with persistent conversation history
• Tool execution — AI inspects stacks, components, and dependencies
• Project instructions via ATMOS.md for context-aware responses
• Global --ai flag — AI-powered analysis of any command output
• --skill flag — Domain-specific AI analysis with skills

Try It

cd examples/ai

# Set up at least one provider API key
export ANTHROPIC_API_KEY="your-api-key"

# Interactive chat
atmos ai chat

# Ask a single question
atmos ai ask "What stacks and components do we have?"

# Structured output for CI/CD
atmos ai exec "validate stacks" --format json

# AI-powered analysis of any command
atmos terraform plan vpc -s ue1-network --ai

# With domain-specific skill
atmos terraform plan vpc -s ue1-prod --ai --skill atmos-terraform

# Multiple skills (comma-separated)
atmos terraform plan vpc -s ue1-prod --ai --skill atmos-terraform,atmos-stacks

# Multiple skills (repeated flag)
atmos terraform plan vpc -s ue1-prod --ai --skill atmos-terraform --skill atmos-stacks

# Via environment variables
ATMOS_AI=true ATMOS_SKILL=atmos-terraform,atmos-stacks atmos terraform plan vpc -s ue1-prod

Key Files

File	Purpose
atmos.yaml	Atmos configuration with AI provider settings
ATMOS.md	Project instructions the AI reads automatically
stacks/deploy/	Environment-specific stack files
stacks/mixins/	Shared region and stage configuration
components/terraform/	Mock Terraform components (VPC, Transit Gateway)
workflows/ai-demo.yaml	Workflow demonstrating AI usage