bryce cole

hey i'm working on products to analyze, archive, and backtest market data through my own scraping methods, local agents, and iOS tools.

Blog

Recent writing.

Projects

Selected product demos and experiments.

Agents

Ongoing write-ups for the systems I have running, what they watch, and what they are trying to automate.

TradingAgents Command Center

Runs scheduled market feeds, Discord-facing stock analysis, and local report capture so trading research stays short where I need action and detailed where I need records.

Current focus: clearer buy, sell, trim, and hold recommendations, better listener recovery, and durable logs for long-running analysis jobs.

Brain Feed Curator

Turns market notes, source checks, and taste signals into a personal feed biased toward macro, AI, security, biotech, and high-conviction edge cases.

Current focus: recency-first selection, stricter dedupe, and a generate-then-judge pass before anything enters the queue.

Hermes Automation Layer

Keeps local scheduled agents visible through cron jobs, a menu bar companion, and remote experiments on a Raspberry Pi host.

Current focus: healthier job status, fewer ambiguous long-running tasks, and simple recovery paths when a command or listener stops responding.

Hermes Siri Chat

Builds a native SwiftUI chat client and Mac bridge for talking to the local Hermes agent from iPhone-style session views.

Current focus: reliable session history, LAN bridge fallbacks, rich message rendering, and keeping stale snapshots from hiding live conversations.

iOS Tweak and Deploy Loop

Builds jailbreak tweaks and sideloaded app experiments for my own devices, with quick install, crash-check, and signing workflows.

Current focus: native-feeling UI changes, fast device smoke tests, and keeping clean baseline artifacts after experiments.

Native Terminal Experiments

Explores iOS terminal UI, session control, keyboard input, and rendering polish through local NewTerm changes.

Current focus: cleaner tab controls, steadier terminal scenes, and native interaction patterns that hold up on device.

Personal Notes App

Builds a SwiftUI notes workspace around notebooks, reminders, search, local storage, and faster editing flows.

Current focus: tightening the core writing surface while keeping folder navigation and reminders simple enough to use daily.

Institutional Flow Agent

Watches screener outputs and unusual fund activity, then turns raw signals into alerts I can review quickly.

Current focus: improving signal quality, reducing noise, and ranking activity by conviction instead of raw volume alone.

Market News Scanner

Ingests hourly news, tags the source, and scores likely market impact before it gets folded into my archive.

Current focus: better entity extraction, faster deduping, and more reliable severity scoring for catalysts.

Polymarket Monitoring Agent

Tracks unusual trader behavior and pricing shifts across prediction markets to surface patterns worth investigating.

Current focus: identifying repeat wallets, clustering suspicious moves, and tying trades back to external events.

Archive and Research Agent

Stores structured market data, scraped context, and past signals so I can backtest ideas and ask questions against my own history.

Current focus: cleaner report generation, stronger retrieval, and better long-range memory for trend comparisons.

iOS Deployment Agent

Monitors personal iOS app builds and streamlines reinstallation to my own devices over the local network so testing stays fast during active development.

Current focus: reducing manual device management, improving install reliability, and keeping test builds easy to refresh while iterating.

Housing Search Agent

Tracks housing opportunities, organizes listing requirements, and prepares application details so I can review and submit faster when new openings appear.

Current focus: better deadline tracking, cleaner document prep, and faster alerts when relevant listings match my criteria.

Experience

AI product engineer focused on browser intelligence, cross-platform apps, automation, large-scale data pipelines, and LLM-backed product workflows.

Yahoo

Software Engineer, Browser AI

Apr 2026 to Present

Building AI features for a cross-platform Chromium-based browser spanning desktop, iOS, and Android, with ownership across page-content understanding and personalized daily feed creation.

Turn browser context into useful product surfaces: extracting signals from pages, shaping model-backed summaries and recommendations, and making AI feel native inside everyday browsing flows.

LabelBox & Anthropic

AI Code Evaluator

Dec 2025 to Apr 2026

Review and improve multi-file code changes generated by Claude across real repositories, including feature work and bug fixes in established open-source codebases.

Contribute directly to coding-model quality through RLHF-style evaluation, fine-tuning feedback, and synthetic data generation across Python and Rust tasks.

Simplify

Backend Software Engineer

Mar 2025 to Oct 2025 · Remote

Maintained and improved an AI parsing pipeline processing 50 to 60 thousand job postings daily, refining prompt logic and type validation to reduce hallucination-driven data errors.

Built SEO-focused Next.js job pages and fixed SQLAlchemy n+1 issues, cutting response times from roughly 1.9s to 100 to 300ms while improving search discoverability.

BlackRock

Software Engineer Intern

Jun 2025 to Aug 2025 · New York

Built an automated KYC compliance system that searched SEC, DOL, FFIEC, NAIC, OpenCorporates, and other sources through multithreaded API, scraping, and agent workflows.

Reduced manual compliance review from about 3 hours to 5 minutes with document retrieval, confidence scoring, and cited AI-assisted verification for internal teams.

BlackRock

Software Engineer Intern

Jun 2024 to Aug 2024 · New York

Built Angular components for an internal Aladdin research chatbot and used RxJS-driven streaming to preserve screen and widget context in responses.

Reached 99% intent recognition accuracy for finance-specific queries with a custom NLP classification pipeline and multi-stage prompt routing.

Apple

Product & Technical Specialist

May 2022 to May 2024 · New York

Provided expert macOS and iOS support, resolved complex customer issues, and maintained a 99% satisfaction score while improving store throughput.