Colony is Fliiq’s multi-agent system. Five specialized agents — Intelligence, Research, Scout, QA, and Governance — coordinate autonomously to tackle objectives that benefit from breadth of exploration, competing perspectives, and self-critique.
Quick Start
fliiq colony start --mission "build the 50 most useful skills for freelancers"
# Dry run — 15-minute test to preview how agents approach the mission
fliiq colony start --mission "..." --dry-run
# Check progress
fliiq colony status
# View results
fliiq colony report
fliiq colony report --html
The Five Agents
| Agent | Role | What It Does |
|---|
| Intelligence | Research Analyst | Scans the landscape for relevant prior art, tools, and developments. Produces structured Intelligence briefs that other agents consume. |
| Scout | Product Manager | Identifies opportunities and breaks the mission into concrete deliverables. Runs demand-sensing (community signals) and demand-generation (persona-based ideation). |
| Research | CTO | Evaluates technical feasibility and drafts detailed proposals. Reads Intelligence briefs and Scout’s proposals to ground ideas in reality. |
| QA | QA Lead | Tests changes, monitors metrics, catches regressions. Establishes baselines before changes ship and validates after. |
| Governance | Staff Engineer | Final decision-maker. Reviews proposals, approves or rejects, manages the codebase. The only agent with git write access. |
This is not a democracy. Governance has final authority. QA opposition is a strong negative signal. Intelligence produces knowledge but doesn’t vote. Research and Scout propose and advocate.
How Missions Work
Give Colony a mission and all five agents focus on that objective:
fliiq colony start --mission "research every AI agent framework and map the competitive landscape"
- Duration: Up to 1 hour (hard cap)
- Cooldowns: 5–10 minutes between agent cycles for fast iteration
- Output: A
mission-deliverable.md with approved proposals, rejected proposals with reasoning, key findings, and completion stats
- Completion: Three layers — duration ceiling, stall detection (3 empty cycles → auto-shutdown), and Governance declaration when the objective is met
Missions are designed for iteration — run a mission, review the deliverable, refine the objective, run again.
How It Works
Agents coordinate through shared state on the filesystem — no databases, no message queues:
.colony/
├── state/
│ ├── proposals/ # One YAML file per proposal
│ ├── intelligence/ # Research briefs
│ ├── votes/ # Agent vote records
│ ├── reflections/ # Per-agent learning logs
│ ├── metrics/ # QA baselines and results
│ └── governance_decisions.jsonl
└── reports/
└── mission-deliverable-001.md # Your mission results
When to Use Colony vs Regular Fliiq
Colony is for WHAT and WHY. Regular Fliiq is for HOW.
| Question | Use |
|---|
| ”What should we build?” | Colony |
| ”Build this thing” | Fliiq |
| ”Which approach is best?” | Colony |
| ”Implement this approach” | Fliiq |
| ”What are we missing?” | Colony |
| ”Fix what’s broken” | Fliiq |
| ”Explore this problem space” | Colony |
- Breadth of exploration — many options to consider before committing
- Competing perspectives — genuine tension between approaches
- Curation at scale — filtering a large space to the best subset
- Self-critique — output benefits from adversarial review before delivery
Mission Categories
Colony handles a range of mission types:
- Curation & prioritization — “Map every API that would be useful as a Fliiq skill, categorized by domain”
- Strategy & decision-making — “Should the business model be subscription, usage-based, or freemium? Argue both sides.”
- Creative divergence → convergence — “Propose 5 different onboarding flows and pick the most compelling”
- Research & synthesis — “Research how 10 different AI products handle memory and personalization”
- System design — “Design the architecture for a skill marketplace with tradeoffs”
- Adversarial review — “Review our current security model and identify every attack vector”
CLI Reference
| Command | Description |
|---|
fliiq colony start --mission "..." | Start a colony mission |
fliiq colony start --mission "..." --dry-run | 15-minute test run |
fliiq colony status | Check current colony status |
fliiq colony report | Generate text report |
fliiq colony report --html | Generate HTML report |
fliiq colony stop | Stop the colony early |
.fliiq/ directory. Run fliiq init --project first if you haven’t already. 
