2nd place at Tetrate buildathon.
Workflow IQ
System designed to make AI agents useful in real workflows while maintaining control, safety, and predictable behavior through structured inputs, outputs, and execution paths.
1 / 6
Project summary
Agent-based workflow system using DAG architecture to safely constrain and orchestrate AI agents.
System designed to make AI agents useful in real workflows while maintaining control, safety, and predictable behavior through structured inputs, outputs, and execution paths.
What needed to be solved
AI agents are powerful but risky when they have too much access, too little structure, or unclear boundaries.
- Too much access leads to unsafe behavior.
- Too little structure leads to unreliable output.
- Agents are difficult to integrate into real systems without constraints.
How it was built
Key implementation decisions, system behavior, and workflow structure.
- Built a DAG-based workflow system where nodes represent steps in execution.
- Used conditional paths to control flow.
- Constrained agents with strict input and output contracts.
- Defined allowed actions per agent to make them usable in real applications without giving them full system access.
Tools and platform choices
Core technologies used in the project.
- Next.js
- Supabase
- TypeScript
- AI APIs
What mattered during implementation
Challenges, tradeoffs, and takeaways from the project.
Challenges / Tradeoffs
- Designing constraints without limiting usefulness.
- Balancing flexibility vs safety.
- Defining clear boundaries for agent behavior.
Outcome / Lessons
- Unconstrained agents are not production-ready.
- Structure and contracts are essential.
- DAG-based orchestration is a strong model for AI workflows.
Related projects
More systems and applied AI work in the portfolio.
1 / 11
Coding Your Career
AI-powered learning platform with a custom LMS, AI teaching assistant, and automated content generation.
Custom LMS with AI teaching and grading workflows.
1 / 12
Sunday Go Lessons
Go learning platform combining structured lessons, problem training, and AI-powered game analysis using KataGo.
Structured teaching plus AI-powered game analysis.
1 / 6
Journey to the Middle Kingdom
A time-travel adventure comic inspired by Chinese mythology. Action, humor, culture, and meaningful life lessons for curious young readers and families.
Long-term storytelling project with its own world, tone, and visual identity.