Agentic engineering · AI-assisted workflows

Agents that carry real weight in { production } not another demo.

I design and ship AI-assisted workflows, opportunity audits, and custom copilots that run unattended and hold up under load. Backed by 25 years of engineering depth.

live run · sample
client-pipeline · 6 harnesses · durable memory running
router queued
planner queued
retrieval queued
executor queued
guardrails queued
memory queued
$
Proof, not promises
86%

Cut a client's cloud bill from $50K → $7K/mo by re-architecting the pipeline around agents.

1000×

Email throughput unlocked. 50M sends a month on a system that used to choke.

250M

Ad impressions served per day at scale. Driving a +40% revenue lift.

What I do

01

Agent workflow automation

Design and ship AI-assisted workflows that reduce manual work, route decisions, and keep humans in the loop where judgment still matters. Tool-calling, orchestration, guardrails, and evaluation, not notebook demos.

Orchestration Tool calling Guardrails Evaluation
02

AI opportunity audit

Review your current process, identify where agent automation is actually worth pursuing, and map the technical and operational shape of a solution before you overbuild.

Process mapping Feasibility Solution shaping
03

Custom agents & AI optimization

Build bespoke agents, copilots, and AI-enabled product features. Then improve quality, routing, retrieval, latency, and cost so the system performs reliably in production.

RAG · pgvector Model routing Latency & cost

Selected work

How an engagement runs

01

Discover

Map the workflow you're trying to automate or augment, and where an agent actually helps versus adds risk.

02

Architect

Design the agent and tool boundaries, state management, and guardrails before writing code.

03

Build

Ship in small, testable slices, instrumented for evaluation from day one.

04

Handoff

Leave your team owning it; docs, runbooks, and clear escalation paths.

My approach

I start with the business problem, not the technology. AI is a tool, not a destination.

Production over demos

Ship things that run unattended, not proofs of concept that need a handler.

Audit before build

Understand the workflow before writing code, most AI projects fail here, not at the model.

Humans in the loop

Agents augment judgment where it's expensive; they don't replace it where it matters.

Measure from day one

Evaluation, guardrails, and cost controls are part of the build, not an afterthought.

Experience

Consultant
Independent Consulting & AI Research
2024 — Now
Staff Engineer
Invative Inc.
2019 — 2024
Director & Engineering Manager
BrightBytes
2013 — 2019
Senior Software Engineer
VerticalResponse
2012 — 2013

Toolkit

Agent & AI tooling
RubyLLM RAG / pgvector Structured prompting Tool calling Whisper FastAPI
Languages & frameworks
Ruby / Rails Node.js TypeScript React / Vue Python / Django PHP
Cloud & infra
AWS Azure Docker Terraform Postgres / Redis Lambda / CI-CD
Quality & ops
GitHub Actions CircleCI RSpec / Jest Cypress / Selenium
Let's scope it

Thinking about where an agent could actually carry weight in your product or workflow?

Book a 20-min intro call