← Back
03 · System design

How it's built.

Before a single line of code was written, I designed a multi-agent system to build this portfolio. Three agents, three mandates, eighteen concrete artifacts, three human validation gates. Here's the architecture.

System diagram

The build architecture.

00 · Orchestrator
Agent 0 / Orchestrator

Designed the full system, scoped each agent's mandate, defined sequential handoff rules, held every validation gate. Remained active between every phase — not just at the start.

Always active ↕
01 · Agent

Narrative & Content

Everything to do with the story.

6 artifacts
  • A1-1 — Thesis & Positioning
  • A1-2 — Audience & Tone Map (3 personas)
  • A1-3 — Narrative Arc: Visitor Journey (flowchart)
  • A1-4 — Section-by-Section Content Plan (9 sections × 7 columns)
  • A1-5 — AI Assistant Knowledge Base
  • A1-6 — Handoff Brief → Agent 2
Reviewed all 6 artifacts before releasing Agent 2.
G1
Human gate
02 · Agent

Design & Visual

Take Agent 1's output and produce two genuinely distinct visual concepts.

6 artifacts
  • A2-1 — Concept Overview (editorial serif vs. operational monospace)
  • A2-2 — Design Token Tables (11 tokens per concept)
  • A2-3 — Section-by-Section Layout Plan (9 sections)
  • A2-4 — Wireframes / Layout Sketches (5 screens per concept)
  • A2-5 — Component Upgrade List (8 components)
  • A2-6 — Handoff Brief → Agent 3
Reviewed both concepts, chose a direction, approved before Agent 3.
G2
Human gate
03 · Agent

Addons & Features

Floating scheduler, how-it's-built section, formation pins, supplementary features.

4 artifacts
  • A3-1 — Floating Scheduler Integration
  • A3-2 — How It's Built page
  • A3-3 — Formation Pins
  • A3-4 — Supplementary feature implementations
In progress — current phase.
Artifact layer
Shared Board — Miro

Single source of truth. Every artifact lives here — not in the chat history. The board is the audit trail, not the session log.

18 artifacts

Hover agent nodes to expand artifacts

Agent breakdown

Three mandates.

01 · Agent

Narrative & Content

Everything to do with the story.

  • A1-1 — Thesis & Positioning
  • A1-2 — Audience & Tone Map (3 personas)
  • A1-3 — Narrative Arc: Visitor Journey (flowchart)
  • A1-4 — Section-by-Section Content Plan (9 sections × 7 columns)
  • A1-5 — AI Assistant Knowledge Base
  • A1-6 — Handoff Brief → Agent 2
Reviewed all 6 artifacts before releasing Agent 2.
02 · Agent

Design & Visual

Take Agent 1's output and produce two genuinely distinct visual concepts.

  • A2-1 — Concept Overview (editorial serif vs. operational monospace)
  • A2-2 — Design Token Tables (11 tokens per concept)
  • A2-3 — Section-by-Section Layout Plan (9 sections)
  • A2-4 — Wireframes / Layout Sketches (5 screens per concept)
  • A2-5 — Component Upgrade List (8 components)
  • A2-6 — Handoff Brief → Agent 3
Reviewed both concepts, chose a direction, approved before Agent 3.
03 · Agent

Addons & Features

Floating scheduler, how-it's-built section, formation pins, supplementary features.

  • A3-1 — Floating Scheduler Integration
  • A3-2 — How It's Built page
  • A3-3 — Formation Pins
  • A3-4 — Supplementary feature implementations
In progress — current phase.
Design decisions

Why this structure.

Sequential, not parallel: each agent needed the previous phase's decisions as hard constraints — running them in parallel would have produced incoherent output across narrative, design, and implementation layers.

Artifacts on a board, not in chat history: chat history is ephemeral and agent-local. A shared board forced every decision into a persistent, reviewable form — and made my validation gate meaningful rather than ceremonial.

Explicit out-of-scope rules: without them, agents drift. Agent 1 would have made design decisions; Agent 2 would have rewritten the narrative. Scope boundaries preserved the separation of concerns.

This took longer than prompting a single model. The payoff: coherent output across all layers because each agent had full context of the previous phase's decisions — not a summary, the actual artifacts.

Runtime

The runtime stack.

The runtime stack is simpler than the build process.

ComponentTechnology
LLMGroq — llama-3.3-70b-versatile
FrameworkTanStack Start
APITanStack Start server routes
HostingCloudflare Workers
Talk to the assistant