AI developer · Spring AI · voice agents · RAG

I build AI systems that work beyond the demo.

Software engineer exploring the edges of AI, full-stack systems, and security. I build production grade systems for the curiosity of it and to learn what the demo never shows.

// usually with a half-finished idea and too much coffee.

See what I'm building Tom Marler AI Resume

building

Parley — self-hosted voice AI agent

live

A voice agent that answers real phone calls and holds a natural conversation built to replace a rented platform (Retell) with a voice layer that lives inside my own Spring application. Twilio handles the telephony; Parley owns everything from the words onward: interpreting the caller, running the LLM, and deciding what to say or do, with direct access to the backend. Now live and answering real calls for several businesses, each on its own number (Poke Pitch Shop, JMAC Intel, and JMAC Logistics). For the card shop it looks up live inventory when a caller names a card, and it won't invent prices, hours, or order status.

  • Spring AI
  • Twilio
  • Azure OpenAI
  • MongoDB
  • Java
  • voice
Project details GitHub

IntelligentOldMan — agentic email intelligence

live

An event-driven system that turns a live inbox into a searchable, classified knowledge base. New mail arrives through Microsoft Graph, Event Grid, and Service Bus; each message is classified by intent, checked for grounding, and embedded into pgvector for RAG. Supply offers become structured leads (dealer, collection, or consignment) queued for a human to review. Now live on the Poke Pitch Shop mailbox, powering the shop's email analytics: every message classified by intent, supply offers tracked by type and lead source, and questions answered over the whole inbox. Cloud-native on Azure, provisioned with Terraform, with eval suites that keep model behavior honest.

  • Spring AI
  • RAG · pgvector
  • Azure
  • Terraform
  • Java
Project details

PokePitchShop — commerce storefront I build & run

live

A live, collector owned trading card business Pokémon, sports, and Magic: The Gathering. I build the storefront: a discovery first Next.js site with catalog browse and product pages, its inventory synced live from the eBay Trading API behind a cached read path. Recent work: a graded-slab storefront, player pages with new-card email alerts, a deal finder with daily market reports, and an AI agents page where visitors can call the shop and talk to Parley. It's the real product my AI experiments plug into.

  • Next.js
  • React
  • TypeScript
  • eBay API
  • SEO
Visit the store AI agents eBay store

Draftsmith — AI writing agent

in progress

Drop a link and get a technical tutorial draft back. Draftsmith ingests the URL into source material, then runs outline, draft, self-edit, and export steps from a step registry, with the model chosen per step (cloud or a local Ollama GPU box). A code-check step tests the draft's code samples before export, and a NAS worker turns a link dropped in an inbox into a draft pull request, with exports for Medium, tommarler.com, and X.

  • agents
  • Ollama
  • Node.js
  • pipelines
GitHub

also explored

iOS, from scratch

Real-time messaging and persistence apps built from the ground up to understand the architecture behind production collaboration tools — sockets, concurrency, and local data not tutorial follow-alongs.

  • Swift
  • sockets
  • Core Data

what I'm into

Applied AI

  • LLM integration
  • RAG
  • agent frameworks
  • voice agents
  • API orchestration

Full-stack

  • Java
  • Spring Boot
  • Next.js
  • React
  • Node.js
  • Python

Infrastructure

  • Azure
  • AWS
  • Terraform
  • Docker
  • CI/CD
  • microservices

Integrations

  • Microsoft Graph
  • Twilio
  • eBay API

Security

  • penetration testing
  • DNS security
  • network hardening

writing

blog

July 2026 · Meta

Welcome to the tommarler.com blog

A markdown-first blog for technical articles — built at deploy time so Draftsmith can publish on-domain without hand-editing HTML.

All writing · Blog · Cross-posts on Medium use a canonical URL back to tommarler.com.

about

I'm a software engineer who rarely stays in one lane long enough to stop being curious about the others. My background sits at an unusual intersection iOS, distributed cloud systems, and hands on security research and that overlap is intentional.

The most interesting problems live at the edges between disciplines. Understanding the security layer makes you a better architect; understanding the product layer makes you a better engineer. Right now most of my curiosity is pointed at applied AI what it takes to make an autonomous system reliable enough to trust.

faq

What are you building right now?

I'm working on Parley, a self-hosted voice agent that answers real calls for several businesses with the LLM layer inside my own Spring app; IntelligentOldMan, which runs email analytics for Poke Pitch Shop by turning its live inbox into something agents can reason over; PokePitchShop, a live storefront where a lot of my AI ideas get tested against real traffic; and Draftsmith, a writing agent that turns a link into a technical tutorial and drafts it for Medium, tommarler.com, and X.

Why rebuild voice AI yourself instead of using a managed platform?

Managed platforms hide latency, turn-taking, and backend access. I wanted to see what it feels like to own those decisions — Twilio handles the phone call; everything from the words onward lives in my application.

What is IntelligentOldMan?

An event-driven system that classifies incoming mail, checks the result for grounding, and stores it for RAG-powered agents, with supply offers queued as leads for a human to review. The interesting part isn't the stack — it's how much judgment you can safely hand to an autonomous system.

What has you most curious about AI lately?

The gap between a convincing demo and a system you'd trust in production: agent loops that know when to stop, RAG that retrieves the right context, and voice agents where you own latency end to end. I learn by building, not by collecting buzzwords.

Where are you based?

Columbia, Missouri. My background spans iOS, distributed systems, and security research — I tend to follow problems to whatever lane they lead.