aiwg
Version:
Cognitive architecture for AI-augmented software development with structured memory, ensemble validation, and closed-loop correction. FAIR-aligned artifacts, 84% cost reduction via human-in-the-loop, standards adopted by 100+ organizations.
46 lines (35 loc) • 1.78 kB
Markdown
# `Discipline` Guidelines Template
## Purpose
Capture standards, conventions, and best practices for a specific discipline (e.g., use-case modeling, design,
programming, testing) to ensure consistency across agents and teams.
## Ownership & Collaboration
- Document Owner: Environment Engineer
- Contributor Roles: Project Manager, System Analyst
- Automation Inputs: Discipline-specific standards, tooling references
- Automation Outputs: `<discipline>-guidelines.md` adhering to sections 1–8
## Completion Checklist
- Scope and applicability defined
- Standards referenced or embedded with examples
- Review cadence and ownership established
## Document Sections
1. **Introduction**
- Define the guideline scope, audience, and relationship to other standards.
2. **Principles**
- List key principles guiding the discipline.
3. **Standards and Conventions**
- Provide detailed rules (naming, formatting, modeling notation, coding conventions, etc.).
4. **Examples and Anti-Patterns**
- Include good vs. poor examples to illustrate expectations.
5. **Tooling and Automation**
- Reference tools, templates, or scripts that enforce the guideline.
6. **Review and Compliance**
- Describe how compliance is assessed (peer review checklists, automated checks).
7. **Change History**
- Track updates, authors, and rationale.
8. **Appendices**
- Include extended references, glossary terms, or resource links.
## Agent Notes
- Replace `<Discipline>` in the title once instantiated.
- Keep instructions concise; favor bullet lists and examples over prose.
- Align with relevant artifacts (e.g., Supplementary Specification, Test Strategy) to avoid conflicting guidance.
- Verify the Automation Outputs entry is satisfied before signaling completion.