Skip to content
View tdloB's full-sized avatar

Block or report tdloB

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tdloB/README.md

Aaron Boldt — Projects

Talent acquisition leader by day (linkedin.com/in/aaronboldt) — builder of AI-assisted applications on nights and weekends, working with Claude Code, Codex, and Claude Design in agentic development workflows.

Most of my product repositories are private because they're active commercial projects. This page describes what's in them. I'm always happy to walk through any of these live — the code, the architecture decisions, and the agent workflows that built them.


🛡️ Aplomb — FDA/FTC claim scanner for Shopify

Stack: TypeScript · React Router · Prisma · Shopify App Bridge · Astro (marketing site)

A Shopify app that scans product descriptions and label images for the marketing claims that get supplement, CBD, and cosmetics stores in trouble — flagging risky language before the FDA, FTC, or a payment processor does.

  • Hybrid detection engine: deterministic rules + LLM classification, with per-product category detection — supplement rules for supplements, cosmetics rules for cosmetics, automatically
  • Cosmetics-specific checks including the appearance-vs-function boundary ("reduces wrinkles" is a drug claim; "reduces the appearance of wrinkles" is a cosmetic)
  • Vision pipeline reads product label images for claims that never appear in the copy
  • Category-aware guidance and one-click compliant rewrites for every flag
  • Versioned engine with verdict caching and a calibrated benchmark suite in CI (0 false negatives / 0 false positives across the fixture catalog)

Status: submitted to the Shopify App Store, in review; live with pilot stores. Unit + integration test suites (dedicated Dockerized Postgres test DB)

Marketing site: aplomb.store


🌱 Ripen Health — mood journal & habit tracker

Stack: React 18 · TypeScript · Vite · Tailwind CSS · Supabase · Stripe · PWA

An installable progressive web app for mood journaling and habit tracking, designed around gentle, sustainable behavior change.

  • Mood journaling and habit tracking with review flows
  • AI-assisted insights (Anthropic / OpenAI, server-side via Supabase Edge Functions)
  • Web push notifications, Stripe subscriptions
  • Encrypted medication tracking — sensitive health data is encrypted at rest, and all secrets live server-side only

Status: in beta with early testers.


🎼 Impresari — guided portal for agentic app development

Stack: Next.js · TypeScript · Tailwind CSS · Supabase (Postgres + Auth) · Vitest · Playwright

The product layer on top of my AI App Builder OS: a web portal that guides users through validating, designing, and building applications with orchestrated AI agents — safely.

  • Guided project intake, phase dashboards, agent activation views, and an artifact workspace
  • Governed workflow with phase gates and human approval gates — GitHub writes, live LLM calls, and code-generation jobs stay blocked until their safety gates pass
  • Read-only GitHub App integration (metadata + contents only; no write permissions)
  • AES-256-GCM credential encryption and workspace-scoped, sanitized AI run history
  • Milestone-gated development with hosted validation at each stage

Status: in active development, private preview stage.

A simplified version of the agent-organization model is open source as: agentic-app-builder-starter-kit — orchestrator, manager, lead, and specialist agent templates with routing matrices, phase gates, and artifact templates (Apache 2.0). Impresari builds well beyond it: the governed portal, human approval gates, credential encryption, and hosted validation are proprietary.


How I build

PRD-first: every project starts as a written product requirements doc and a build-prioritization matrix before any code. From there, Claude Code and Codex do the heavy lifting inside a structured agent workflow — orchestrator and specialist roles, phase gates between milestones, and automated tests (Vitest, Playwright, integration suites) as the exit criteria for each phase — with Claude Design handling UI and visual design. The same discipline I bring to recruiting operations — process, metrics, and accountability — applied to shipping software.

Pinned Loading

  1. agentic-app-builder-starter-kit agentic-app-builder-starter-kit Public

    Open-source starter kit for organizing AI coding agents with orchestrator, manager, lead, and specialist templates, routing matrices, phase gates, artifact templates, and app-building workflows.