How it works
Maker mode operates in two phases:Plan: Generate CLI commands
An LLM converts your natural language request into a JSON plan containing sequential CLI commands.
Plan structure
A plan is a JSON document with this schema:Key fields
- version: Plan format version (currently
1) - provider: Cloud provider (
aws,gcp,azure,cloudflare) - commands: Ordered array of CLI commands to execute
- produces: Maps output values to placeholders (e.g., resource IDs)
- notes: Human-readable explanations
Placeholders
Placeholders are variables that get resolved during execution:Static placeholders
<DEPLOY_ID>: Unique identifier for this deployment<REGION>: AWS region<ACCOUNT_ID>: AWS account ID<APP_PORT>: Application port (inferred from target group)
Dynamic placeholders
Commands can produce values for later use:<VPC_ID> can be used in subsequent commands:
Execution flow
When you runclanker ask --apply, this happens:
Execute commands sequentially
For each command:
- Substitute placeholders
- Run the AWS/GCP/Azure/Cloudflare CLI command
- Learn bindings from output (via
producesfield) - Handle failures with AI-powered retries
Wait for async operations
CloudFormation stacks and other long-running operations are automatically polled until completion.
AI-powered error handling
When a command fails, Clanker uses agentic fixes to automatically retry:How it works
- Analyze failure: Send the error output to an LLM
- Propose fix: LLM returns a
agenticFixJSON object - Apply fix: Execute pre-commands, update bindings, or rewrite args
- Retry: Run the fixed command
- Exponential backoff: Retry up to 3 times with increasing delays
Common fixes
| Error | AI Fix |
|---|---|
AlreadyExistsException | Set skip: true |
InvalidParameterValue: <PLACEHOLDER> | Provide bindings or rewritten_args |
ResourceNotFoundException | Add pre_commands to create missing resource |
AccessDeniedException | Add IAM policy via pre_commands |
| Invalid role ARN syntax | Extract role name from ARN in rewritten_args |
Checkpointing
Maker mode supports resumable execution via durable checkpoints:- Automatic: Checkpoints are saved after each successful command
- Resume: If a plan fails mid-execution, re-run
--applyto resume from the last checkpoint - Storage: Checkpoints are stored in
~/.clanker/checkpoints/
Multi-cloud support
Maker mode supports multiple cloud providers:- AWS
- GCP
- Azure
- Cloudflare
Uses the AWS CLI (Provider detection is automatic if your question mentions AWS services.
aws).Examples
Create a VPC with subnets
Deploy a Lambda function
Destroy resources
Next steps
Multi-cloud
Learn about multi-cloud provider support
CLI reference
Full CLI options for maker mode