Designing Clarity from Heartbreak · Pre-Order Now
ARC/02 // IDLE
Available for Hire

A Human-Governed City-Intelligence Platform

I designed and shipped a live consumer application and operator platform that turns Events, city Signals, cultural context, and permanent Spots into explainable recommendations.

My Role
Founder, Product Designer, Systems Designer, Builder

Owned product strategy, UX architecture, consumer experience, admin tooling, AI ingestion workflow, governance model, and launch direction.

Angel Compass Shipped Product UI Mockup

Why it matters

Angel Compass proves I can design both sides of an AI-native system: the consumer experience people trust, and the operator layer that keeps the intelligence reviewed, governed, and explainable.

My Role

Founder · Lead Product Designer · Systems Designer · Product Architect

End-to-end product architecture, UI/UX systems design, technical data modeling, and release engineering.

Responsibilities
Product strategy UX architecture Interaction design Information architecture AI workflow design Operator tooling Data modeling Design systems Visual direction Frontend implementation QA governance End-to-end product ownership

The City-Information Problem

Standard navigation platforms and mapping services are architected around static listing data. Yelp, Google Maps, and directory guides tell users when a business is open, where it is located, and its cumulative review score.

However, the real-world utility of a city spot fluctuates dynamically. A neighborhood lounge that is cozy at 7:00 PM on a Tuesday becomes overcrowded during a concert let-out nearby at 9:30 PM on a Friday. A patio cafe is less viable when a sudden downpour hits, and a retro cocktail spot's appeal shifts based on travel distance, door policy, and the traveler's energy level.

The design problem was not simply displaying locations. It was constructing a living systems architecture that could capture, normalize, verify, and explain these shifting city conditions in real-time, helping users make decisions before committing to a trip.

Spot, Event, Moment, and Signal

To solve this, I modeled the city as a relationship between four structural primitives, transforming abstract data points into clear recommendations.

1. Spot Permanent Spatial Node

The static venue baseline (105+ curated spots in Atlanta). Holds location coordinates, neighborhood tags, acoustic profiles, and physical layout data.

2. Event Scheduled Programming

A discrete, scheduled occurrence linked to a Spot (e.g., Friday Jazz, a concert, or a DJ set) defined by specific timing boundaries.

3. Moment Time-Bound Condition Overlay

A dynamic overlay that flags temporal shifts (e.g., Event Surge, Patio Risk, Scene Shift, Transit Delay) affecting nearby Spots.

4. Signal Telemetry Ingestion Input

Physical data inputs (e.g., weather reports, road closures, wait times) crawled by the parser to trigger or modify active Moments.

The Consumer and Operator Split

When building location products, there is a dangerous temptation to build fully autonomous pipelines: letting web scrapers dump data straight to the user app, or letting an LLM publish signals on the fly.

This case study establishes a strict boundary: AI proposes and structures, but the human operator controls consequential publication.

To protect trust, the system architecture is separated into a consumer app and an operator console, enforced by server-side rules:

Public Trust Boundaries

A typecheck passing does not mean real-world behavior is verified. An HTTP 200 return code does not mean crawled content is useful.

Therefore, no Event or Moment candidate in storage is visible to users until an administrator has reviewed, verified, and explicitly promoted it.

Data Isolation

Row-Level Security (RLS) policies completely isolate the administrative candidate queue from public API reads.

The consumer client queries isolated database views that only contain active, approved, and chronologically valid records.

Governed Ingestion Architecture

The ingestion engine crawls trusted venue domains, formats unstructured text via a structured prompt parser, and delivers a sanitized payload to the gateway.

EVENT PIPELINE (LOOKAHEAD) Trusted Sources Automated Discovery Structured Normalization Quarantine & Time Check Human Review Public-Safe Feed MOMENT & SIGNAL PIPELINE (REAL-TIME) City Conditions Moment / Signal Intake Promotion Live Context Consumer Decision Support

The ingestion pipeline enforces Deno-hosted endpoint security, parses metadata parameters, runs URL de-duplication routines, and isolates incoming content. The human-governed step provides the ultimate quality check on the database boundary, before anything reaches public client views.

Control Room, Ingestion, and Governance

I designed a unified administrative console—the Control Room—that gives operators complete operational visibility over the ingestion and publication engine. No crawled candidate or AI-structured condition is served to users until it has been inspected and promoted, ensuring strict editorial control over the city-intelligence graph.

System Event Publication Lifecycle (Workflow Model)

An Event candidate transitions through five structured publication lifecycle states to assure platform trust:

Pending Ingested, unverified candidate

Approved Verified details, parent Spot linked

Ready Scheduled, lookahead checks pass

Published Active, visible in recommendations

Expired / Archived Time window closes, archived

System Data Payload (Raw Ingestion Log)

admin_event_review_queue.json CANDIDATE LOG
{
  "review_id": "rev-spot-uuid-high-museum",
  "event_name": "Friday Jazz",
  "parent_venue_name": "High Museum of Art",
  "event_date": "2026-07-12",
  "start_time": "18:00:00",
  "status": "candidate",
  "verification_status": "unverified",
  "confidence": "high",
  "needs_human_review": false,
  "review_status": "pending_review",
  "dedupe_key": "28d9f68f0cf0e5f987aa5286205133a...",
  "source_health": {
    "fetch_health": "good",
    "content_health": "event_rich"
  }
}

Shipped Control Room Interfaces

Control Room: Event Review Queue Interface Screenshot
Event Review Queue “A governed review surface for inspecting extracted evidence, resolving timing and source ambiguity, controlling publication, and recording explicit operator decisions.”
Control Room: Moment Intake Console Interface Screenshot
Moment Intake Console “A structured intake workflow that separates source evidence, public-safe language, geographic impact, lifecycle timing, and administrative reasoning before a Moment can become live.”
Control Room Dashboard Screenshot
Control Room Dashboard “One operating surface for review, ingestion, source health, spatial coverage, recommendation diagnostics, content operations, learning, and access verification.”
Moment Coverage Map Screenshot
Moment Coverage Map “Spatial observability for understanding where live Moments originate, which Spots they affect, how far influence extends, and whether the city-intelligence layer has meaningful coverage.”

Consumer Intelligence and Routing

The consumer mobile application translates verified platform governance into a map interface. When a Moment is promoted by an operator, the map renders active influence fields (pulsing domes indicating surge or delay boundaries) rather than static pins.

Explore Map: Pulsing domes indicating active localized Moments Explore Map Pulsing domes for active Moments
Route Generator: Tonight's Move multi-stop optimizer Route Generator Tonight's Move multi-stop optimizer
Venue Profiles: Vibe metrics, busy windows, and hours info Venue Profiles Vibe metrics & timing windows
Contextual Influence: Active events, weather status, and alert diagnostics around a Spot Contextual Influence Vibe alerts & event impact around a Spot

Tonight’s Move Routing Optimizer

Instead of hijacking travel plans, Tonight’s Move uses a two-pass routing engine to generate itineraries structured by Warm-up, Prime, and After-hours stops.

The engine computes an absolute arrival timestamp, applying exponential decay curves to dynamic vibe scores based on distance travel times, closing warnings, and active Moments. If a patio risk is active, the first stop is penalized; if a concert surge is nearby, the prime stop receives a routing weight boost to align with high energy intent.

Data Boundaries & AI Limitations

To build a location product that respects trust, the systems architecture defines strict user-privacy and engineering constraints:

Public-Safe GPS Fallbacks

If the user denies foreground GPS permissions, the app does not break or lock up. It automatically falls back to base coordinates in Midtown Atlanta, keeping the search interface fully functional without compromising privacy.

Constrained Natural Language

The conversational chat interface (Ask Cheesy) is restricted from hallucinating recommendations. It converts raw natural-language queries into structured filters, querying only the verified, operator-approved venue graph database.

The systems design reflects a core architectural philosophy: AI assists the operator and processes context, but the human remains the final validator of truth.

System Outcomes

Live iOS App Shipped Authenticated native distribution on the public App Store (ID 6757201587).
v2.0 Released Production build approved and delivered in July 2026.
Admin Suite Built Complete Control Room dashboard, intake console, diagnostics, and mapping.
GPT Ingestion Pipeline AI-assisted domain crawl, structural parsing, and de-duplication are active.
Human Review Defined Structured candidate review queues, RLS boundaries, and operator controls.
Consumer Routing Model Established Tonight's Move optimization, time-decay curves, and alert domes.
SuperCrew Integration Social Weather and Moments pipeline connected directly back to SuperCrew.

Measured Ingestion Audit (July 12, 2026 Run)

The performance of the ingestion-to-publication engine was audited across a lookahead sweep of the target venue graph.

70 Total candidates
10 Inside active window
54 Future events cached
6 Past/Stale events rejected
22 Missing start times flag
0 Exact or fuzzy duplicates
App Store Connect Build Submission Proof
Figure: Sanitized App Store Connect build delivery proof (Version 2.0 release approval)

Why This Matters

Angel Compass became an exercise in designing living systems rather than isolated screens. Every recommendation depends on data provenance, operator judgment, AI assistance, publication governance, and user trust. The consumer experience succeeds because the internal platform makes the intelligence maintainable, accountable, and explainable.

Reflection

Building Angel Compass changed how I think about AI products. The hardest challenge was not generating more recommendations. It was deciding which recommendations deserved to become product truth. Designing the operator experience became as important as designing the consumer experience, because trust is not created by AI alone. It is created by the systems that govern it.

Case Study Thesis

I designed the consumer experience, the platform that feeds it, and the governance that keeps both trustworthy.