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 20+ years of engineering depth.
20 minutes. No deck. We pick one workflow and decide if an agent belongs in it.
BrightBytes, 2013–19. Cut AWS from $50K → $7K/mo by consolidating data pipelines.
VerticalResponse, 2012–13. Email throughput that unlocked 50M sends a month.
Adpeak, 2010–12. Ad impressions served per day; +40% revenue.
What I do
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.
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.
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.
Selected work
Buck Workflow
A structured, discoverable workflow for AI-assisted software development with durable memory — the actual toolkit I use to run agent-assisted engineering, not a demo.
HealthHacking AI
Architected a conversational AI sales experience guiding users through personalized health assessments that generate tailored nutrition and workout plans.
Overhub Commerce Platform
Architected and delivered Overhub, a multi-tenant commerce platform handling 100K+ monthly transactions with sub-200ms latency.
How an engagement runs
Discover
Map the workflow you're trying to automate or augment, and where an agent actually helps versus adds risk.
Architect
Design the agent and tool boundaries, state management, and guardrails before writing code.
Build
Ship in small, testable slices, instrumented for evaluation from day one.
Handoff
Leave your team owning it; docs, runbooks, and clear escalation paths.
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.