Skip to content
Skills

What I do.

Three tracks, in the order I claim them. AI consulting is the work. Engineering is how it ships. Go-to-market is what I speak to rather than sell.

AI consulting

Making AI useful, not just present.

Under all of it sits plain model-level fluency. I know how these systems fail. I know what they cost. I know when a smaller one wins.

  • LLM Systems

    Retrieval, prompting and tool use in one working system.

  • RAG

    Chunking, embeddings and reranking tuned to your corpus.

  • AI Agents

    Agents that take real actions inside guardrails you set.

  • Evaluation

    Test sets and metrics that show if the system improves.

  • AI Governance

    Policy, access and audit trails for systems on real data.

  • Opportunity Mapping

    I find where AI helps you and where it wastes your money.

  • Retrieval
  • Embeddings
  • Reranking
  • Tool Use
  • Guardrails
  • Evaluation
  • Fine-tuning
  • Prompt Design
  • Context Windows
  • Observability
  • Cost Control
  • Latency
Tools & services

The stack behind meaningful work.

One stack for all of it. TypeScript, React, Cloudflare, Supabase and Postgres. Claude Code is the build engine.

  1. Websites

    Marketing sites and landing pages, static on Cloudflare’s edge.

  2. Web Apps

    React dashboards on Postgres with auth and row-level security.

  3. Mobile & PWAs

    One React Native codebase for iOS, Android and the web.

  4. Automations

    Scheduled jobs and queues that remove your manual steps.

  5. AI Agents

    Agents that take real actions, with evals live from week one.

  6. APIs & Data

    Endpoints on Workers, typed straight from the database schema.

  • TypeScript
  • React
  • React Native
  • Expo
  • SQL
  • Postgres
  • Supabase
  • Cloudflare Workers
  • Cloudflare Pages
  • D1
  • Turnstile
  • Claude Code
Go-to-market

Also fluent in the commercial side.

I speak this language rather than sell it. It decides whether good work ever reaches anyone. I can hold a real conversation about it.

  • Positioning

    What the product is, who it serves and what it beats.

  • Demand Gen

    Channels and campaigns measured on real pipeline.

  • Sales Process

    Stages, criteria and handoffs a team can follow.

  • Discovery

    Questions that surface the problem behind the request.

  • Enablement

    Materials that let someone else run the conversation.

  • Revenue Analytics

    Funnel and cohort reports that survive a hard question.

  • Positioning
  • ICP Definition
  • Messaging
  • Pipeline
  • Forecasting
  • Onboarding
  • Retention
  • Pricing
  • Segmentation
  • Attribution
  • Cohorts
  • Churn

Open for projects

Find the work worth doing.

Tell me what runs slow or costs too much or keeps breaking. If AI is the wrong answer I say so.

Start a conversation