Work · DriveAIWerks + BLZ Foundry

Systems that run.

A sample of what we have built across the companies: products, brands, and the AI that runs behind them.

01 · Automotive serviceIn build

Shop AI platform

A licensed shop platform with an AI layer for service advisors and a diagnostics agent for technicians in the bay.

OutcomeAdvisor briefings generated from shop data with no model in the decision path.

  • Python
  • SQL
  • Agents
  • Evals
02 · Product launch + opsLive

Spoiler-Saver

Took an automotive aftermarket kit from product to market: storefront, payments, order alerts, and a live ops dashboard for every order from paid to delivered.

OutcomeRetail, wholesale and international orders in one private dashboard, with every change on record.

  • Cloudflare Workers
  • D1
  • Stripe
  • Access
View ↗
03 · Brand + websiteLive

JC Classics & Restomods

Full brand and site for a classic and restomod shop: vector logo, chrome truck hero, challenge-coin build registry, and a self-serve edit page for the owner.

OutcomeThe shop updates builds, gallery and for-sale cars without touching code; every publish lands as a reviewed change.

  • Static site
  • Cloudflare Pages
  • Access
  • GitHub
View ↗
04 · Sales motion + marketingLive

Spoiler-Saver sales engine

An AI-built go-to-market: distributor kits, wholesale pricing playbooks, a launch hub and lead tracker, and agents that draft numbers-first replies to dealers.

OutcomeShops and distributors move from first touch to reorder through one tracked funnel.

  • AI agents
  • Lead funnel
  • Distributor kits
  • Workers
05 · Decision workbenchOpen source

AI Cost Estimator

Describe an AI workload, get a cost-per-completed-task range and a model starting point. Governed, deterministic, near-zero token cost.

OutcomeTurns "what will this cost?" from a guess into a range you can defend.

  • Python
  • FastAPI
  • Streamlit
View ↗
06 · Operating system for AI agentsOpen source

TeamOS

A set of agent definitions and handoff contracts that make AI agents work like a team: facts first, clear control points, logged decisions.

OutcomeAgents keep context across tools instead of starting over every session.

  • Claude Code
  • Markdown agents
  • GitHub
View ↗

Want the deeper story on any of these?

Ask for a walkthrough →