I help enterprise teams design, build, and govern multi-agent systems. I don't resell any vendor's product, and every engagement ends with something your team can run after I leave.
Looking for advisory only? See /advisory. Looking for training? See /education. This page is the full menu.
Models, APIs, MCP servers, and vector stores: the raw capabilities. Most companies overspend here and get little back, because they never built the skills layer above it.
Workflows written down so anyone can run them: reusable prompts, tested chains, and named playbooks. This is where one engineer's experiment gets packaged for the whole org.
Persistent systems with a defined role in the business, audited and observable. Most companies want this layer and can't yet build it alone.
I start every engagement by mapping where you sit on this stack, and then we build the layer you're missing.
Audit of your existing agent stack: orchestration model, tool boundaries, eval setup, observability, failure modes. Deliverable: written report with prioritized fixes and a reference architecture for v2.
fit: Teams shipping agents in production who suspect they're hitting a ceiling.
I set up the policy, process, and tooling to govern agents at scale: PII filtering, alignment checks, audit logging, risk tiering, and model approval workflows, scoped to the regulations you answer to.
fit: Regulated industries, enterprises with legal-flagged AI use, or teams under board scrutiny on AI risk.
A live briefing for your C-suite or board on agentic AI as it stands today: which claims hold up, which are vendor marketing, and where the opportunity is for your industry.
fit: Leadership teams that need to make a multi-million-dollar agent bet and want a non-vendor view.
Hands-on training for your engineering, product, and operations teams on building with Claude, Codex, and Gemini. We work on problems your team already has, and everyone leaves with a take-home toolkit.
fit: Teams that have read the docs but haven't shipped, or that need to scale agent expertise past one or two early adopters.
I join your team for one build: I pair with your engineers, set the architecture, write the spec, and ship the prototype. You end up with a production-grade agent and a playbook your team can extend.
fit: Teams with budget and urgency but a capability gap, who need a flagship agent shipped within a quarter.
Speaking engagement for your conference, all-hands, or client event. Pick a topic from /speaking or commission a custom angle.
fit: Conference organizers, internal events, customer summits. Past audiences: AI4, POSSIBLE, MMA, TEDxNYU.
Advisory, build, and speaking engagements solve different problems. Switch tabs to compare them.
A custom briefing for your C-suite or board on agentic AI as it stands today: which claims hold up, which are vendor pitch, and where the opportunity is. I write the material for your company.
Monthly working sessions plus async input on architecture choices, RFPs, and vendor reviews, in a shared Slack channel that I read.
An outside review of your existing agent stack: orchestration model, evals, observability, failure modes, and governance. You get a written report with prioritized fixes and a reference architecture for v2.
I join your team for one build: I pair with your engineers, set the architecture, write the spec, and ship the prototype, then leave a playbook your team can extend.
I set up the policy, process, and tooling to govern agents at scale: PII filtering, alignment checks, audit logging, risk tiering, and model approval workflows, scoped to the regulations you answer to.
A keynote on AI agents, responsible AI, regulation, or bias and fairness, written for your audience. Recording rights are negotiable, and I travel.
Hands-on training for your engineering, product, and ops teams on building with Claude, Codex, and Gemini, using problems your team already has. Everyone leaves with a take-home toolkit.
Rates use a 4-tier scale ($–$$$$). Exact numbers depend on scope, urgency, IP, and travel. Ask for a quote.
If you're betting your next budget cycle on agents and want someone who builds them, let's talk.
$ schedule a call