⌚ Now on Apple Watch
🏋️
benharveyfit ai
Harvey AI LLC · Live on the App Store
A full AI fitness coach, shipped end-to-end and live on the App Store: chat-first
coaching, photo-based meal logging with instant calorie estimation, and a 0–100 Physique
Score that scans your progress and hands you the next step. Built on SwiftUI + Supabase with a
Gemini-powered coaching engine, StoreKit billing, and an automated QA + self-improvement loop.
The v3.1 release adds a native Apple Watch app — Today protocol,
quick-log, Physique Score, and a watch-face complication — bundled right inside the iOS app.
App StoreLive · v3.1
iPhone + WatchNative Apps
AI CoachGemini-Powered
0–100Physique Score
SwiftUI
watchOS
Supabase
StoreKit
Gemini
Edge Functions
💰 5.0 ★ on the App Store
💸
BHarv Finance AI
Harvey AI LLC · Live on the App Store
An AI money coach, live on the App Store: connects to your real accounts via
Plaid, reads actual spending, spots the leaks, and coaches you toward your goals
in plain conversation — not spreadsheets. Chat-first coaching over live transaction data, a
money score, and freedom-number projections. Built on SwiftUI + Supabase Edge Functions with an
LLM-powered coaching engine.
App StoreLive · 5.0 ★
PlaidReal Bank Data
AI CoachChat-First
0–100Money Score
SwiftUI
Plaid
Supabase
Edge Functions
LLM Coaching
🤖
Oracle Protocol
Harvey AI LLC · Autonomous AI Systems
Autonomous multi-agent coding framework with a four-tier hierarchy: Oracle → Manager → Lead → Coder.
Each layer operates with phase-gated execution — agents can't advance without presenting evidence of completion.
A SQLite-backed code knowledge graph over the entire Python source tree lets agents reason about
cross-file dependencies and promote learning across runs. Resumable workflows survive session failures.
Resolved three classes of deep reliability bugs: runaway self-recursion in agent spawning, inter-agent
communication deadlocks, and venv bootstrap failures — making fully autonomous, unsupervised coding
runs reliably production-safe.
4-tierAgent Hierarchy
SQLiteKnowledge Graph
Evidence-GatedExecution
ResumableWorkflows
Python
Multi-Agent AI
LLM Orchestration
SQLite
RAG
Autonomous Systems
🗺️
App Flow Graph
Mobile Platform Engineering
Zoomable production map of a large-scale mail application — 134 screens, 220 navigation edges —
derived from instrumentation source code rather than hand-drawn diagrams. Won an internal A/B
test against the legacy tool and shipped to production. Includes static-analysis parsers
(Compose wireframe extraction, ScreenGraph parsing, Android manifest deep-link resolution, Flux
navigation extraction) and a live emulator capture engine that drives the UI over ADB, self-heals
from ANRs, and verifies captures against element inventories.
134Screens Mapped
220Nav Edges
Python
ADB
Static Analysis
Emulator Automation
Jetpack Compose
📱
Trial Reels & Instagram Platform
Meta / Instagram · Staff Android Technical Lead
Technical lead for Trial Reels on a 25+ engineer cross-functional team at Instagram.
Launched Q1 2024 — drove 180M new user acquisitions in a single quarter.
Simultaneously led the platform-wide migration of 15M+ lines of code to
Kotlin + Jetpack Compose across the entire 2B+ user application — crashes down 42%, startup
time up 35%. Built the coroutine networking framework that was adopted by 8 product teams,
processing 10K+ requests per second at 99.99% uptime with 28% latency reduction.
Mentored 12 senior engineers through the migration.
180MNew Acquisitions
2B+User Platform
-42%Crash Rate
+35%Startup Speed
-28%API Latency
Kotlin
Jetpack Compose
Coroutines
Android SDK
Staff Lead
Cross-Functional
🔥
Crash Detection Platform
Meta · Infrastructure
Crash detection infrastructure processing 500M+ daily events across the
Instagram Android app. Reduced mean time to detect (MTTD) from 6 hours to 15 minutes.
Estimated annual engineering cost savings of $50M through faster incident response.
ML-powered crash analysis surfacing patterns across 40+ product teams.
500M+Daily Events
6hr→15minMTTD
$50MEst. Annual Savings
ML
Event Processing
Android
Infrastructure
⚡
Beachbody Super-App
Beachbody · Principal Engineer
Unified super-app consolidating 3 separate legacy fitness apps (12M combined users) into one.
Infrastructure redesign cut costs by $2.3M/year. AWS backend supporting
50K+ concurrent users at 99.95% uptime with <100ms p95 latency for 8M+ DAU.
$2.3MAnnual Savings
50K+Concurrent Users
Kotlin
AWS
Android
App Consolidation
☁️
Cloud Emulator Infrastructure
Cloud Infrastructure Engineering
Containerized Android emulator running on nested-virtualization GCE instances, driven over
an IAP tunnel. Serial-agnostic capture pipeline for automated UI testing at cloud scale —
enables headless Android test execution at Google Cloud speed without physical devices.
GCP
Nested Virt
Docker
IAP
ADB
Android Emulator
💬
AI Chat Application — ChatGPT Integration
Harvey AI LLC · Independent
Built a full AI-powered chat application and automation layer on top of the ChatGPT API. Includes a custom interface, persistent conversation context, intelligent response routing, and automated workflow triggers — designed for real-world deployment with session handling, streaming responses, and extensible tool integrations. Shipped end-to-end: backend API, frontend UI, and cloud deployment.
ChatGPT API
Python
JavaScript
REST API
Automation
Full-Stack
🌐
Client Website — Freelance
Harvey AI LLC · Client Work
Designed and shipped a full production website for an independent client. Handled the complete engagement — requirements, custom design, responsive development, and live deployment. Delivered on time with a clean handoff and zero post-launch issues.
HTML / CSS
JavaScript
Responsive Design
Freelance
Harvey AI LLC
