Skip to content
đŸ€– AI-optimized docs: llms-full.txt

CIS Configuration

Configure Creative Intelligence Suite workflows, output behavior, and agent preferences.

CIS configuration is stored in:

_bmad/cis/config.yaml

If the file doesn’t exist, CIS uses default values.

SettingDescriptionDefault
output_folderWhere workflow outputs are saved./_bmad-output/
user_nameName used in workflow facilitationUser
communication_languageLanguage for agent responsesenglish

Where workflow results are saved.

Absolute or relative path. Workflow outputs are named {workflow-name}-{date}.md.

Example:

output_folder: "./creative-outputs"
# or
output_folder: "/Users/name/Documents/creative-work"

Relative paths are resolved from project root.

How agents address you during facilitation.

Used for personalized interaction. Agents weave your name into their responses.

Example:

user_name: "Alex"
# Carson might say: "Alex, let's try a different angle..."

Language for workflow facilitation.

Agents communicate in the specified language while maintaining their distinctive personalities.

Supported values:

  • english (default)
  • spanish
  • french
  • german
  • italian
  • portuguese

Example:

communication_language: "spanish"
# Maya facilitarå en español manteniendo su estilo jazzístico

If no config file exists, CIS uses:

output_folder: "./_bmad-output/"
user_name: "User"
communication_language: "english"

Create or edit _bmad/cis/config.yaml:

# CIS Configuration
output_folder: "./_bmad-output/"
user_name: "Your Name"
communication_language: "english"

Some workflows accept additional context via command-line flags:

Pass context documents to workflows:

Terminal window
workflow design-thinking --data /path/to/user-research.md
workflow innovation-strategy --data /path/to/market-analysis.md
workflow problem-solving --data /path/to/problem-brief.md
workflow storytelling --data /path/to/brand-guidelines.md

Context files should be markdown. Agents incorporate this information into facilitation.

Some agents maintain persistent data in sidecar directories:

Sophia (Storyteller) remembers your preferences and story history:

_bmad/_memory/storyteller-sidecar/
├── story-preferences.md # Your storytelling preferences
└── stories-told.md # History of stories created

Critical actions (automatically called):

  1. Load preferences before storytelling
  2. Update history after story creation

This enables Sophia to learn your style and build consistent narratives over time.

CIS respects these environment variables:

VariablePurposeExample
BMAD_OUTPUT_DIROverride output folderBMAD_OUTPUT_DIR=./outputs
BMAD_USER_NAMEOverride user nameBMAD_USER_NAME=Jordan
BMAD_LANGUAGEOverride languageBMAD_LANGUAGE=spanish

Environment variables take precedence over config file settings.

Check output folder path is valid:

Terminal window
# Test path resolution
ls ./_bmad-output/

Ensure the folder exists or CIS can create it.

Verify user_name in config file. For Sophia, ensure sidecar files exist and are readable.

Confirm communication_language uses supported values. Custom languages require agent prompt updates.