What I Build

Telecom room power coordination was a repeated pain point: sizing UPS, generators, PoE budgets, and cooling loads by hand from scattered references on every project. No reliable tool existed for the limited energy community that wasn't buried inside expensive software or dependent on a spreadsheet that required manual maintenance.

A single browser-native calculator that handles UPS sizing, generator sizing, PoE budget, and cooling demand for telecom rooms and equipment rooms. Aligned to BICSI and TIA standards. No login, no server, no data transmission. Output is for preliminary coordination, not construction documents.

Continued refinement to reduce the class of power coordination errors that happen when engineers estimate UPS and generator requirements from memory or incomplete references. Additional room types and standards alignment improvements are on the roadmap. The tool will remain free.

Limited energy estimating relies heavily on general-purpose spreadsheets that were never designed for Division 27/28 scope, BICSI work breakdown structures, or the overtime math that governs how crews are actually priced on commercial jobs.

A complete job estimator built around BICSI WBS codes. Configurable crew roles, workweek patterns, and federal or California overtime rules. Generates a customer-ready proposal and an internal bid report with financial roll-up, bid health indicators, and auto-generated risk flags. No account required.

Expanding scope coverage and improving the bid health and risk flag logic: the indicators that surface problems before a job is priced wrong and the cost falls on the contractor downstream. The tool will remain free.

Local networks accumulate unknown devices, exposed ports, outdated services, and unnoticed configuration drift. Most home and small office environments have no repeatable way to see what is actually running on the network, let alone whether anything has changed since the last time someone looked.

A local-first network awareness and vulnerability assessment tool that discovers devices via ARP, scans ports, checks for known CVEs using nmap scripts, tracks device baseline changes between scans, assigns a triage-level risk rating, and generates a PDF report with findings, CVSS scores, and recommendations. Results stream live to a browser dashboard as the scan runs. Designed for authorized networks only: no exploitation, no credential testing, no lateral movement.

Improving baseline comparison, differential analysis, and remediation guidance so small environments can identify weak points and track improvement over time before those weak points become security or operational problems.

Modern AI assistants are powerful, but each carries different strengths, weaknesses, and biases. Important decisions benefit from independent review rather than reliance on a single model. VolteX was built to coordinate structured collaboration between multiple AI agents so the result reflects genuine consensus rather than a single perspective. The user can evaluate that consensus with confidence before approving it.

A local-first multi-agent AI orchestration platform that coordinates independent agents through a structured consensus workflow. Each agent contributes its analysis, critiques the others where appropriate, and converges on a bounded recommendation. That recommendation is presented to the user for review and approval. No output leaves the loop without human sign-off. The current implementation focuses on software engineering; the underlying architecture is intentionally domain-agnostic.

Expanding beyond software engineering into a general-purpose collaboration platform capable of supporting engineering reviews, technical writing, documentation, planning, research, and design critiques: any domain where multiple independent AI perspectives improve decision quality. Human oversight and bounded review loops remain non-negotiable at every stage.

Cloud-dependent home automation creates single points of failure, data exposure risks, and subscription lock-in. Local inference enables private AI tooling without transmitting sensitive information to external services. The home lab is where engineering ideas get tested before they influence production design decisions.

A dedicated home server running a private inference stack and home automation platform. Sensor network covers environmental monitoring, energy monitoring, lighting control, appliance integration, and access management. Dashboards built in Grafana against InfluxDB time-series data. All VolteX private engineering tools run here.

Deeper integration between the inference stack and automation triggers, and improved energy visibility through Tesla Powerwall and solar data, building toward a home that maintains capability when normal infrastructure degrades rather than one that depends on it remaining stable.