BRAND & POSITIONING
WEBSITE & CONVERSION
MARKETING & CONTENT
MOTION & STORYTELLING

AVAILABLE FOR FREELANCE
FULL-TIME / PART-TIME

Email: CONTACT@AVAARTJOURNEY.COM

RelayOS Case Study | Ava Liu
Self-Directed Product · RelayOS · Case Study 01

RelayOS — Multi-Agent AI Workforce Orchestration Platform

I designed and built a multi-agent operations platform where a Relay Manager coordinates specialist agents, manages AI-to-AI and human-in-the-loop handoffs, persists workflow state, governs tool access, and verifies work before completion.

Multi-Agent SystemsMCPHITLFastAPIPostgreSQLDockerOpenAI API
1 Manager + 3 SpecialistsMulti-agent orchestration
AI → AI → Human → AIManaged handoffs + approvals
Agent manages agentsRouting · priority · verification
01 / Problem & Context

Coordinating work across agents and humans.

The coordination problem

As multiple AI agents take on connected work, the system needs clear ownership, priorities, handoffs, human approval, shared workflow state, and verification before work is considered complete.

The orchestration model

I designed Relay Manager as the orchestration layer above the specialist agents. It assigns work, evaluates structured reports, resolves the next owner, calculates priority, creates handoffs, resumes approved work, and runs completion verification.

RelayOS turns separate agent capabilities into one managed workflow with explicit ownership, handoffs, approvals, persistent state, and completion rules.
02 / System Architecture

A full-stack orchestration layer for specialist agents.

AssignManager → specialist
EvaluateStructured agent reports
HandoffAgent ↔ agent ↔ human
VerifyBefore completion
03 / Multi-Agent Orchestration

A manager agent coordinates specialist agents and human decisions.

RELAY MANAGERASSIGN SPECIALISTEVALUATE REPORTROUTE NEXT OWNERHUMAN APPROVAL WHEN REQUIREDRESUME + VERIFY

Agent → Agent

The Social Agent diagnoses campaign performance and can recommend Design work. Relay Manager resolves the next assignment, persists the Social → Design handoff context, dispatches Design, and verifies the resulting brief.

Agent → Human → Agent

External-facing work creates a reviewer-bound approval. The workflow pauses in WAITING_FOR_HUMAN, records the decision and reviewer identity, then resumes exactly once and returns the approved context to the agent.

Manager-controlled priority

The LLM cannot set final priority. Relay Manager persists bounded business inputs and calculates P0–P3 through a deterministic formula so urgency is inspectable and reproducible.

Completion verification

Completion requires a valid structured report, artifacts, evidence, and no unresolved blockers. Verification results are persisted; only PASS can transition work to COMPLETED.

04 / Governed MCP

Governed MCP tool access with auditable execution.

RelayOS implements an official FastMCP stdio server plus a transaction-aware governed registry. The V1 tool is deliberately read-only and allowlisted: get_campaign_performance accepts a constrained campaign ID, returns fictional local metrics, and logs sanitized success/failure events.

What MCP enables

  • Standardized tool contract for agent access
  • Explicit allowlist rather than arbitrary execution
  • Pydantic argument validation
  • Auditable invocation events tied to workflow state

Governance

Tool access is constrained to the registered capability. The agent does not receive filesystem, shell, direct SQL, credential, or unrestricted network access, and invocation results are recorded as sanitized audit events.

05 / Persistence & Runtime Infrastructure

Persistent data and a containerized full-stack runtime.

PostgreSQL + SQLAlchemy + Alembic

SQLAlchemy 2.x models persist WorkItems, agent runs, reports, assignments, handoffs, approvals, verification results, priorities, and append-style activity events. Alembic owns schema evolution; PostgreSQL 16 runs as the production-like relational store.

Docker + Docker Compose

The Next.js frontend, FastAPI backend, and PostgreSQL database run as isolated Docker Compose services with health-dependent startup, migrations, explicit service configuration, and persistent database storage.

06 / Engineering Scope

Built across AI orchestration, backend, frontend, and infrastructure.

Agent systems

  • Multi-agent orchestration
  • MCP implementation
  • Human-in-the-loop approval/resume
  • OpenAI structured runtime
  • State machine + deterministic routing
  • Persistent audit traces

Full-stack engineering

  • FastAPI backend
  • Next.js / React / TypeScript frontend
  • PostgreSQL + SQLAlchemy
  • Alembic migrations
  • Docker + Docker Compose
  • Cross-service runtime debugging
07 / Cloud Architecture

Mapped the containerized stack to an AWS deployment architecture.

I designed an AWS deployment plan that maps container images to ECR, the FastAPI service to ECS Fargate behind ALB, PostgreSQL to RDS, application secrets to Secrets Manager, observability to CloudWatch, and DNS/TLS to Route 53 and ACM.

Ava Liu · Forward Deployed Engineer · Design + Full-Stack + AI Systems