Nexusv3.4.0
Fort Lee, NJ · NYC metro
William Volodarsky

Building Agentic Systems & Full-Stack AI Software.

I'm William Volodarsky, a Software & AI Engineer (BS CS, Fordham, Magna Cum Laude). I build production web apps, agentic workflows, and internal tooling in Python, TypeScript and SQL, backed by 8+ years of real-world operations and clinical data work.

Nexus by the numbers · measured Nov 2026
Test Suite
171 passing

pytest unit + FastAPI integration tests (HITL commits, branching, engine)

Prompt-Cache Hit Rate
82.8%

129M of 156M input tokens served from cache across 476 logged runs

Tool Modules
12

Gmail, Calendar, web search, Chrome bridge, HL7 parser, ADB scraper and more

Knowledge Base
~400 notes

Markdown vault navigated with filesystem tools; no vector index

FLAGSHIP PROJECT · OPEN SOURCE

Nexus: An Agent-Integrated Knowledge OS

A full-stack LangGraph + FastAPI + Next.js system I built and run for myself to query, maintain, and automate a ~400-note Markdown knowledge base, plus my email, calendar, and documents. The engine is public; the personal vault content stays local.

Filesystem navigation instead of a vector index

Behavior lives in Master Instructions.md → Section Instructions.md → per-note YAML, editable in Obsidian and live on the next turn.

  • Grounded paths. The model sees the real folder tree and tool catalog up front, then reads whole notes with read_file and search_vault rather than retrieving 500-token chunks.
  • No re-indexing. Notes I edit by hand are visible on the very next call; there is no embedding pipeline to fall out of sync.
  • Cache-friendly by design. The system prompt is byte-stable within the hour and history is never rewritten, which is why 82.8% of input tokens are served from the provider's prompt cache.
  • Tradeoff: whole-note reads cost more tokens per query than top-k retrieval, and this approach is sized for a personal-scale vault (hundreds of notes), not millions of documents.
def inject_root_instructions(cache_stable: bool = True) -> str:
    # Read fresh on every call (<1ms): human edits in Obsidian are live on the next LLM turn
    template = ROOT_INSTRUCTIONS_PATH.read_text(encoding="utf-8")
    ...
    vault_structure_tree = get_directory_tree(path=None, show_files=False, max_depth=2)

    # Hour-aligned timestamp so per-second ticks never bust the provider's KV prompt cache
    timestamp_str = (
        datetime.now().strftime("%Y-%m-%d %H:00")
        if cache_stable
        else datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    )
    return (
        template
        .replace("{user_name}", settings.nexus_user_name)
        .replace("{current_time}", timestamp_str)
        .replace("{vault_structure}", vault_structure_tree)
        .replace("{shared_tools}", get_shared_tools_catalog())
    )

Recently Shipped

v3.4.0 changelog
  • •Conversation branching DAG with distill-and-merge back into the parent thread
  • •Image & PDF upload with text-layer + table extraction for multimodal chat
  • •Read-only Chrome tab-group bridge (MV3 extension → WebSocket → Markdown)
  • •Stop & Revert: cancels a running turn and rolls back its checkpoints
  • •HITL stale-base detection, 3-way rebase and one-click rollback
  • •Mobile PWA control panel over LAN / Tailscale

Tool Modules

12 deterministic Python/Node utilities in src/nexus/shared_tools/, callable by the agent or from the CLI.

View Source on GitHub
gmail_engine.pyComms

Gmail REST API v1, multi-account search, threads, labels and drafts. Never sends.

calendar_engine.pyComms

Google Calendar OAuth2 client for listing, creating and updating events.

web_search.pyResearch

Tavily-backed web search with depth/domain filters and Markdown citations.

browser_bridge.pyResearch

Reads open Chrome tab groups and rendered DOM via an unpacked MV3 extension.

read_webpage.pyResearch

Extracts clean article Markdown from a URL with trafilatura.

youtube_transcript.pyResearch

Downloads YouTube transcripts to text for note distillation.

medical_xml_parser.pyHealth Data

Parses HL7 CDA clinical XML exports into structured Markdown.

ingest_phone.pyMobile

ADB screen-scraper for 11 Android chat apps via the UI hierarchy.

generate_podcast.pyAudio

Turns a Markdown note into an MP3 with edge-tts.

export_conversation.pyTooling

JSON/JSONL chat transcript → Markdown with turn coalescing.

vault_reader.pyKnowledge

Pure-Python vault navigation, search, recent-edit queries and PDF ingestion.

resume_engine/Documents

Playwright PDF + DOCX resume renderer with page-fill metrics.

REQUEST LIFECYCLE

End-to-End Execution Pipeline

Click any stage below to inspect the real Python module and function that handles it in Nexus.

src/nexus/agent/graph.py

Universal NexusAgent & Tiered Model Routing

One universal LangGraph StateGraph (agent ⇄ tools) replaces rigid domain routers. It navigates the Vault directly, reads <Section>/Section Instructions.md on demand, and routes across Gemini, OpenAI, and Anthropic tiers—automatically falling back to a low-latency tier if a primary model hits a 504 deadline timeout.

Modules & Primitives:
LangGraph StateGraphSqliteSaver (WAL)ChatGoogleGenerativeAIChatOpenAI504 Tier Fallback
src/nexus/agent/graph.pyreal source · trimmed
def call_model(state: NexusAgentState, config: RunnableConfig | None = None) -> dict:
    ...
    system_prompt_content = inject_root_instructions()
    ephemeral_sys_msg = SystemMessage(content=system_prompt_content)
    messages_for_llm: list[BaseMessage] = [ephemeral_sys_msg] + cleaned_messages
    ...
    active_llm = get_chat_model(tier=requested_tier, temperature=0.0)
    try:
        response = active_llm.bind_tools(TOOLS).invoke(messages_for_llm)
    except Exception as e:
        ...
        if is_deadline_or_timeout and effective_tier != "low":
            fallback_llm = get_chat_model(tier=fallback_tier_arg, temperature=0.0)
            response = fallback_llm.bind_tools(TOOLS).invoke(messages_for_llm)
EXPERIENCE & OPERATIONS

Professional Experience & Track Record

300+ hours of LLM and multimodal evaluation paired with clinical billing automation and 8 years of business operations and HIPAA-regulated medical records work.

AI Training Fellow

300+ Hrs Model Evaluation
Handshake AI Fellowship•Remote / New York, NY
Nov 2025 – Aug 2026
  • Completed 300+ hours of human evaluation and comparative grading across LLM and image generation outputs; tested prompts for factual errors, hallucinations, and instruction-following failures against structured rubrics.
  • Performed iterative resampling with corrective feedback across LLMs and latent diffusion models, identifying systematic failure modes and context degradation patterns.
LLM EvaluationComparative GradingHallucination AuditingPrompt TestingStructured Rubrics

Python Billing Automation (Contract / Independent)

Clinical Workflow Automation
MEM Billing — Clinical Practice Automation•New York Metro
2025
  • Built Python scripts for an independent LCSW clinical practice to automate insurance billing workflows and replace manual claim entry, eliminating recurring claim formatting errors and saving weekly administrative hours.
PythonHealthcare BillingWorkflow AutomationData Validation

Co-Owner & Operations Lead

2x Revenue Over 18 Mos
SiliSlick Knives•Farmingdale, NY / US, UK & EU
June 2017 – June 2025
  • Doubled private-brand revenue over 18 months by engineering automated inventory forecasting pipelines, competitor pricing analysis, and catalog SEO across Amazon Seller Central, Shopify, and wholesale channels.
  • Streamlined international fulfillment and unit margins across US, UK, and EU hubs by developing automated data reconciliation workflows and SQL reporting for customs logistics, cross-border freight, and supplier replenishment.
Inventory ForecastingSQL ReportingData ReconciliationMulti-Channel OperationsSupply Chain

Medical Records & Patient Services

100% HIPAA Compliance
Vitreous Retina Macula Consultants•New York, NY
June 2015 – Feb 2017
  • Co-managed patient charts and medical records for a high-volume ophthalmology practice, maintaining 100% HIPAA compliance across EHR entry, chart retrieval, and inter-office record transfers.
  • Created structured tracking sheets for patient flow and staff scheduling to reduce chart retrieval wait times during peak clinic hours.
HIPAA ComplianceEHR SystemsClinical DataClinic Workflow Tracking

Education & Academic Honors

Sept 2023 – Dec 2025Magna Cum Laude (GPA: 3.7)

Bachelor of Science in Computer Science

Fordham University — New York, NY

Dean's List. Coursework in Algorithms, Operating Systems, Database Systems, Artificial Intelligence, and Software Engineering.

Jan 2020 – Dec 2022Dean's List, Phi Theta Kappa (GPA: 3.7)

Associate of Science in Computer Science

LaGuardia Community College — Long Island City, NY

Foundation in Object-Oriented Programming (Java/C++), Data Structures, and Discrete Mathematics.

CREATIVE STUDIO & SPATIAL ART

Visual Art & Aesthetic Systems

Engineering and visual art share the same root: spatial reasoning, composition, and taste. A curated collection of original physical paintings, digital compositions, and computational studies.

Trip 1
digital2025
Inspect Artwork

Trip 1

Chromatic study in layered form, light, and spatial depth—also used as the ambient background canvas in the site hero.

Original Visual Composition3049 × 2046 px
Trip 2
traditional2024
Inspect Artwork

Trip 2

Companion piece exploring high-contrast color movement, organic texture, and structural balance.

Original Visual Composition3222 × 2328 px

The Philosophy of Creative & Technical Synthesis

Visual art builds acute spatial intuition and composition discipline that directly informs system architectures, modular component design, and UI telemetry clarity.

Inquire About Originals / Prints
TECHNICAL STACK

Skills & Where They're Used

Every item below points to a concrete module, project, or role where I used it.

LangGraph & LangChain
Nexus StateGraph & tools
ReAct & Tool Calling
NexusAgent + 12 tool modules
Parallel Subagent Swarms
spawn_subagent + blackboard.db
Prompt Caching & Hydration
82.8% cache hit rate (476 runs)
Conversation Branching DAGs
Fork, tangent slice & merge
Gemini, OpenAI & Anthropic APIs
Tiered routing + 504 fallback
Pydantic v2 Structured Outputs
API schemas & agent state
Multimodal Vision & PDF Ingestion
PyMuPDF text + table extraction
Python (Asyncio, FastAPI)
Nexus backend & MEM Billing
TypeScript & JavaScript
Nexus GUI & portfolio site
Next.js 16 (App Router) & React 19
Nexus Control Panel & portfolio
SQL (SQLite WAL, PostgreSQL, MySQL)
chats.db, hitl.db & ops reporting
Server-Sent Events & WebSockets
Live trace stream & Chrome relay
Tailwind CSS v4
Nexus GUI & portfolio UI
Node.js
Playwright PDF resume compiler
Java & C++
Fordham & LaGuardia CS
PowerShell & Bash
start.ps1 & repo automation
Google OAuth2 (Gmail & Calendar REST)
gmail_engine & calendar_engine
Chrome Extension (MV3) DOM Bridge
browser_bridge.py WebSocket
Playwright & python-docx
Dual-format resume_engine
ADB (Android Debug Bridge)
11-app UI-hierarchy scraper
HL7 CDA Medical XML Parsing
medical_xml_parser.py
Tavily Search & Trafilatura
web_search & read_webpage
Git, git-crypt & Syncthing
Engine + encrypted Vault sync
Vercel & Cloudflare DNS
williamvolodarsky.com edge
Pytest (Unit & FastAPI Integration)
171 passing tests (16 modules)
HITL Two-Phase Commit & 3-Way Rebase
hitl_queue.py + Monaco diff UI
LLM-as-a-Judge & Human Evaluation
Handshake (300+ hrs) & eval runner
Token Cost & Cache Auditing
run_logger.py & audit_run_costs.py
HIPAA Medical Records Compliance
VRMNY ophthalmology records
RESUME

Master Resume

Kept in sync with the Nexus repository and my master Markdown resume.

Request PDF / DOCX

William Volodarsky

Software & AI Engineer (Full-Stack / Applied AI / Enterprise Systems)

Fort Lee, NJ 07024 • bill@williamvolodarsky.com • williamvolodarsky.com • github.com/brolodarsky • linkedin.com/in/williamvolodarsky

BS CS Magna Cum Laude (3.7 GPA)8+ Yrs Operations & Clinical Data

01 // Summary

Software & AI Engineer (Full-Stack / Applied AI / Enterprise Systems) building production web applications, agentic workflows, and internal tooling. Computer Science graduate (BS CS, Magna Cum Laude, Dec 2025) combining modern Python, TypeScript, and SQL engineering with 8+ years of real-world operations and clinical data systems. Builder of Nexus (a LangGraph + FastAPI + Next.js 16 platform with pre-call prompt hydration, parallel subagent swarms, conversation branching, and a two-phase commit HITL queue verified by 171 pytest tests) and MEM Billing (clinical practice automation).

02 // Projects & Engineering

Nexus — Personal Knowledge & Agent System (LangGraph, FastAPI, Next.js 16, SQLite)
Jan 2025 – Present
•Eliminated unverified AI file mutations across ~400 notes by building a Next.js 16 + FastAPI control panel with real-time SSE trace streaming, a SQLite conversation branching DAG, Stop & Revert rollback, and a two-phase commit HITL diff queue (Monaco Editor + hitl.db) with cumulative edit stacking, stale-base conflict detection, 3-way line rebase, and revision rollback.
•Cut context bloat and achieved an 82.8% prompt-cache hit rate (129M / 156M input tokens cached across 476 runs) by building a unified LangGraph StateGraph (NexusAgent) with hour-aligned pre-call instruction/tree hydration (inject_root_instructions), tiered Gemini / OpenAI / Anthropic routing (504 fallback), and parallel subagents (spawn_subagent) on a SQLite blackboard.
•Delivered grounded retrieval without vector-chunking loss by building deterministic Python filesystem and multimodal PDF tools (search_vault, read_file, get_directory_structure, get_recent_modifications, PyMuPDF text + table extraction) that navigate domain instructions and whole notes on demand.
•Automated multi-channel ingestion across 12 Python/Node modules: multi-account Gmail REST API (v1) and Google Calendar OAuth2 clients, a read-only Chrome MV3 Extension WebSocket DOM bridge (browser_bridge.py), Tavily search, trafilatura webpage/YouTube extractors, an HL7 CDA XML parser, an ADB Android chat scraper (11 apps), and a Playwright PDF + python-docx resume compiler.
•Verified engine reliability and cost observability with 171 pytest unit and FastAPI integration tests across 16 modules (HITL commits, 3-way rebase, branching DAG, SQLite WAL concurrency), an LLM-as-a-Judge eval runner, and JSON run cost auditing (audit_run_costs.py).
MEM Billing — Clinical Practice Billing Automation (Python)
2025

Built Python scripts for an independent LCSW clinical practice to automate insurance billing workflows and replace manual claim entry, eliminating recurring claim formatting errors and saving weekly administrative hours.

03 // Professional Experience

Handshake AI Fellowship — AI Training Fellow
Nov 2025 – Aug 2026

Completed 300+ hours of human evaluation and comparative grading across LLM and image generation outputs; tested prompts for factual errors, hallucinations, and instruction-following failures against structured rubrics.

SiliSlick Knives — Co-Owner & Operations Lead
June 2017 – June 2025

Doubled private-brand revenue over 18 months by engineering automated inventory forecasting pipelines, competitor pricing analysis, and catalog SEO across Amazon Seller Central, Shopify, and wholesale channels. Streamlined international fulfillment and unit margins across US, UK, and EU hubs by developing automated data reconciliation workflows and SQL reporting for customs logistics, cross-border freight, and supplier replenishment.

Vitreous Retina Macula Consultants — Medical Records & Patient Services
June 2015 – Feb 2017

Co-managed patient charts and medical records for a high-volume ophthalmology practice, maintaining 100% HIPAA compliance across EHR entry, chart retrieval, and inter-office record transfers. Created structured tracking sheets for patient flow and staff scheduling to reduce chart retrieval wait times during peak clinic hours.

04 // Education

Fordham UniversityBS in Computer Science, Magna Cum Laude (GPA: 3.7)
Dean's List • Sept 2023 – Dec 2025
LaGuardia Community CollegeAS in Computer Science (GPA: 3.7)
Dean's List, Phi Theta Kappa • Jan 2020 – Dec 2022
SYSTEM_STATUS // OPEN FOR OPPORTUNITIES

Let's Build Production AI Together.

I am currently evaluating high-impact Agentic AI Engineering and Systems Orchestration roles (NYC, Hybrid, or Remote). Whether you are building autonomous agents, tackling LLM alignment, or scaling complex operations, let's connect.

Official Communication Channel
bill@williamvolodarsky.com
Send Email