Adam Tyrrell
Work

Systems I designed and built.

Five that are worth reading about: what the problem was, and the decision that made the thing work.

Production data analytics software60k rowsbackfilled in ~67s, idempotent

Multi-Tenant Analytics Platform

Data analytics software for vehicle retail, in production with paying tenants. Daily sales, service, parts, and inventory reports arrive as email attachments, get parsed and imported automatically, and land in per-tenant dashboards.

Every custom API route is tenant-scoped at the boundary, so one client can never read another client's numbers. Imports upsert on a stable key, which makes a re-run a no-op instead of a duplicate, and a year of history backfills in about a minute.

  • Next.js 16
  • Payload CMS
  • MongoDB
  • Auth0
  • Express ingest service
  • Recharts
  • Vercel

Client software, so the screenshots stay private. Architecture and code walkthrough on request.

Automation · AI opsDailyunattended runs

Autonomous Daily Agent Fleet

A fleet of scheduled AI agents that run unattended every day, handling security review, dependency research, and production error watch, then report to a dashboard and push to a phone.

The interesting part is what happens with nobody watching: agents run on systemd timers, a poller survives restarts, and error watch is wired to live Sentry data so a real production exception becomes a notification instead of a surprise.

  • Claude API
  • systemd services
  • Sentry
  • Next.js dashboard
  • Push / email alerts
Multi-agent AI · Data enrichment522leads, each with evidence

AI Lead-Intelligence Pipeline

A staged pipeline that runs parallel AI agents to discover, verify, and enrich small-business leads, with every claim traced back to firsthand evidence rather than a scrape.

Verification is the whole trick. An early pass read static HTML and reported missing features that were actually there, rendered by JavaScript, so roughly half of its "this site lacks X" claims were false. Re-checking against the rendered DOM fixed it.

  • Claude API
  • Multi-agent orchestration
  • Node.js
  • Rendered-DOM verification
  • MongoDB
Front-end rangeconcepts

Ten concept builds, ten different voices.

Fictional brands, built to see how far a small site can be pushed in a specific direction. Each one is live and clickable.

Happy to go deeper on any of these: the architecture, the tradeoffs, or the parts that did not work the first time.

Get in touch