What Are Collectives?
In Genie, a Collective is a group of specialized AI agents that work together toward a common purpose. Think of them as departments in a company, each with expert team members.The Two Core Collectives
Genie ships with two fundamental collectives:Code Collective
34 Agents - Software development, testing, git operations, debugging, architecture
Create Collective
9 Agents - Research, writing, editing, content creation, shape-shifting
Code Collective (34 Agents)
The Code Collective handles all software development activities. It’s organized into specialized roles:Core Development Team
| Agent | Role | Key Capabilities |
|---|---|---|
| implementor | Primary developer | TypeScript, React, Node.js, clean code |
| tests | Testing specialist | Unit, integration, E2E, TDD |
| planner | Architecture & planning | System design, task breakdown |
| investigator | Code analysis | Performance, security, quality review |
Support Specialists
| Agent | Role | Key Capabilities |
|---|---|---|
| git | Version control | Commits, branches, conventional commits |
| debug | Troubleshooting | Error analysis, root cause investigation |
| audit | Security review | Vulnerability scanning, best practices |
| optimizer | Performance | Code optimization, profiling |
Infrastructure Team
| Agent | Role | Key Capabilities |
|---|---|---|
| docker | Containerization | Dockerfile, docker-compose, best practices |
| ci-cd | Automation | GitHub Actions, pipelines, deployment |
| deployer | Production ops | Cloud deployment, monitoring |
| database | Data layer | SQL, NoSQL, migrations, queries |
Full Code Collective Roster (34 Agents)
Full Code Collective Roster (34 Agents)
Core Development (8 agents):
implementor- Primary feature developertests- Testing specialistplanner- Architecture and planninginvestigator- Code analysis and reviewreviewer- Code review and qualityrefactor- Code improvementdocumenter- Documentation writerarchitect- System design
frontend- UI/UX implementationbackend- API and server logicdatabase- Data layer specialistapi- API design and implementationsecurity- Security specialistperformance- Performance optimizationmobile- Mobile developmentweb- Web technologies
git- Version controldocker- Containerizationci-cd- Automation pipelinesdeployer- Production deploymentmonitor- System monitoringbackup- Data backup and recovery
debug- Debugging specialistaudit- Security auditingoptimizer- Performance tuningvalidator- Input validationtester- Test executionqa- Quality assurance
helper- Utility functionsmigrator- Database migrationsseeder- Data seedinggenerator- Code generationscaffold- Project scaffoldingcleanup- Code cleanup
Agent Selection Logic
Agent Selection Logic
Create Collective (9 Agents)
The Create Collective handles research, writing, content creation, and creative tasks:| Agent | Role | Key Capabilities |
|---|---|---|
| researcher | Information gathering | Web research, data analysis, summarization |
| writer | Content creation | Articles, docs, copy, storytelling |
| editor | Content refinement | Proofreading, style, clarity, tone |
| shape-shifter | Adaptive communication | Persona matching, voice adaptation |
| analyst | Data interpretation | Insights, patterns, recommendations |
| strategist | Planning & approach | Content strategy, audience targeting |
| designer | Visual concepts | Layout ideas, design principles |
| storyteller | Narrative craft | Compelling stories, engagement |
| curator | Information organization | Categorization, tagging, structure |
The shape-shifter agent is particularly powerful - it adapts its communication style to match your needs, from technical documentation to creative storytelling.
Create Collective Workflows
Agent File Structure
Every agent is defined in a markdown file with consistent structure:Examples
Feature Implementation Request
User: “Implement user authentication with JWT” Response:- Load specifications from @planner
- Implement auth service with TypeScript
- Add proper type definitions
- Include error handling
- Delegate to @tests for test coverage
- After tests pass, delegate to @git for commit
Code Organization
Why Delegation Matters
Why Delegation Matters
Without Delegation:With Delegation:
Orchestration Boundary
Orchestration Boundary
Each agent has a boundary of direct execution vs orchestration:Direct Execution: Things you’re explicitly designed for
Orchestration: Everything else - coordinate specialists
Advisory Teams
Beyond individual agents, Genie supports Advisory Teams - groups of agents that collaborate on complex decisions:Tech Council
Creating Custom Teams
Creating Custom Collectives
You can create your own collectives ingenie-personal:
1
Create Collective Directory
2
Define Agents
3
Configure Collective
4
Register Collective
Example: Data Science Collective
Agent Collaboration Patterns
Sequential Hand-off
Parallel Execution
Collaborative Review
Best Practices
Single Responsibility
Each agent should have ONE clear purpose. Don’t create generalist agents.
Clear Boundaries
Define exactly what each agent does and doesn’t do. Use delegation rules.
Consistent Structure
Follow the standard agent file structure for predictability.
Document Thoroughly
Include examples, edge cases, and delegation rules in agent files.
Common Anti-Patterns
God Agent: One agent that tries to do everythingSolution: Create specialized agents and use delegation.
Unclear Boundaries: Agents with overlapping responsibilitiesSolution: Clear separation - implementor writes code, tests writes tests.

