SmartShoe AI Coordination Layer

The Insight: Coordination Requires Intelligence

As a program manager and AI builder, I realized coordination failures in supply chains are fundamentally an information problem, not a people problem. Teams weren't making bad decisions—they were making decisions with incomplete, conflicting, or delayed information.

What if we could:

• Harmonize conflicting data sources in real-time?
• Simulate downstream impact before decisions were finalized?
• Route approvals to the right stakeholders with full context?
• Keep a complete audit trail for compliance?

That insight led to building an agentic AI coordination layer—a system that turns email chaos into governed, data-driven orchestration.

The Solution: Multi-Agent Architecture

I designed the system with three layers and five specialized agents working in parallel:

Inputs Layer

All relevant signals flow in: marketing briefs, campaign data, demand forecasts, supplier capacity, cost history, inventory levels. No gatekeeping.

Intelligence Layer

Three agent types work in parallel to eliminate information silos:

1. Data Harmonization Agent

• Detects conflicting versions of key metrics (e.g., "Marketing's forecast: 40% demand vs. Operations: 20%")
• Resolves conflicts using predefined hierarchy
• Flags ambiguity for human review

2. Domain Agents (Two Specialists)

• Marketing Insights Agent: "Can we execute this campaign timeline? What's the brand risk?"
• Operations & Logistics Agent: "Do we have capacity? What's the supplier lead time impact? Cost implications?"

3. Synthesis & Coordination Agent

• Brings everything together into one coherent recommendation
• Surfaces three distinct options: conservative, balanced, aggressive
• Complete with trade-offs and downstream implications

Outputs Layer

Leadership sees:

• Executive Summary: One-page context with decision options
• Risk Highlights: Flagged issues that need attention
• Keyword-Based Alerts: Urgent changes surface instantly; routine changes don't clutter inboxes

The Governance Layer: Safety Through Decision Gates

An AI system is only as good as its guardrails. I designed four layers of governance to keep the system safe while keeping humans in control:

Gate 1: Keyword-Based Escalation

• If plan change includes "ASAP," "critical," "blocker" → automatic COO escalation
• High business impact signals → full context provided immediately
• No more buried emails

Gate 2: Numeric Decision Thresholds

• Demand >20% change? → COO must approve
• Cost impact >$10K? → CFO must review
• Supply risk = HIGH? → Automatic supplier notification

Clear rules. Applied consistently. No politics.

Gate 3: Supplier Alert Automation

• If change would overload supplier capacity → 48 hours advance notice
• No more surprise crisis calls
• Relationship trust rebuilds faster than expected

Gate 4: 100% Auditability

• Every decision logged with full reasoning, approver, timestamp, outcome
• Complete compliance
• No hidden decision-making

My Specific Contributions

Architecture & Design

• Defined agent roles, prompts, and routing logic
• Designed decision gates aligned to CFO/COO concerns
• Built data harmonization workflow to resolve conflicting forecasts

Product & Storytelling

• Created 3.5-minute live demo showing user experience (problem → agent analysis → approval in seconds)
• Designed governance model to address leadership's "but isn't this risky?" concern
• Led Q&A focused on metrics, adoption, and long-term sustainability

Technical Implementation

• Used StackAI to orchestrate agent workflow
• Implemented prompt engineering for domain-specific reasoning
• Built decision gate logic with escalation routing

The Impact (Modeled Scenario)

This was a graduate capstone project, so impact is modeled on case data, not production deployment. But the numbers tell a compelling story:

Metric	Before	After	Impact
Plan Changes Per Week	8–10 daily	<3/week	70% reduction
Decision Cycle Time	2–3 days (email)	30 minutes	95% faster
Cost Avoidance	–	$450K–$600K annually	From fewer expedites, rework, overtime
Coordination Failures	44% of problems	60–80% reduction	From data harmonization + gates
Supplier Satisfaction	Sentiment –0.37	Sentiment +0.10	From 48-hour notice pattern

Why This Approach Scaled

1. Data-Driven, Not Rule-Heavy

Decision thresholds (demand >20%, cost >$10K) came from analyzing what actually broke vs. what succeeded in historical data. Policies evolved based on real escalation patterns, not gut feel.

2. Humans Make Judgment Calls; Agents Handle Noise

The COO still approves demand changes >20%. The CFO still reviews cost impacts. But they do it with full context in 30 minutes instead of 3 days of email. That's the win.

3. Governance Lives in Code, Not Meetings

By embedding decision gates in the agent workflow, governance became operationalized instead of bureaucratized. One consistent policy applied to every decision. No politics.

The Bigger Picture: AI for Operations

This project reinforced something I'm passionate about: The best AI solutions solve coordination problems, not computation problems.

Computers are fast at math. Humans are slow at synthesizing information across silos. The gap between "fast computation" and "slow coordination" is where agentic AI creates value.

In supply chains, that gap is massive—and expensive. Every unvalidated plan change, every supplier surprise, every day of rework is coordination failure wearing a different name.

Key Lessons for Product Managers & AI Engineers

1. Start with the nightmare scenario – "Neon Series" moments are real. Find them, quantify them, build to prevent them.
2. Map the coordination gaps – Who's working with conflicting information? Where are decisions delayed? That's your agent's job.
3. Build governance into the system, not around it – Don't ask humans to enforce policies manually. Embed them in agent logic.
4. Let humans own judgment, agents own context – Agents gather information and surface options. Humans decide what matters.
5. Measure adoption through ease, not mandate – If your system makes someone's job harder, they won't use it. If it saves time and eliminates email chaos, adoption is automatic.

Key Takeaway: Coordination as Competitive Advantage

Most companies think about AI in supply chain as forecasting better or automating transactional tasks. But the real opportunity is coordination.

In a world where speed matters, the team that can validate a plan change in 5 minutes instead of 3 days wins. They respond to market faster. They keep suppliers happy. They avoid $420K fire drills.

Agentic AI makes that possible because it does the one thing humans struggle with: synthesizing fragmented information in real-time and surfacing it in context when it matters.

What's Next (If Deployed)

This project is a graduate capstone, but the architecture scales. If I were deploying this in a real supply chain:

• Phase 1 (8 weeks): Deploy with keyword escalation + demand gates. Measure adoption and cost avoidance.
• Phase 2 (months 3–6): Add numeric governance gates. Expand to more decision types.
• Phase 3 (month 6+): Extend to R&D planning and design innovation workflows.

The principle stays the same: Eliminate information chaos so humans can make better decisions faster.

Technical Stack & Skills

Skills Demonstrated

• Agentic AI System Design: Multi-agent architecture with parallel processing
• Product Thinking: User workflows, adoption strategy, stakeholder alignment
• Governance & Compliance: Decision gates, auditability, risk management
• Supply Chain Strategy: Understanding coordination gaps and operational constraints
• Executive Communication: Live demo delivery, Q&A handling, storytelling
• Cross-Functional Collaboration: Integrating marketing, ops, finance perspectives

Academic Context

Course: Graduate Capstone Project, Drexel University
Program: MS in Business Information Technology
Focus: Emerging Technologies & AI Applications
Semester: Fall 2025

This project demonstrated how academic learning translates into real-world product thinking—architecting solutions that balance technical innovation with business viability and operational feasibility.