— Practice / AI
AI engineering, not AI demos.
Anyone can wire a chatbot to a model. We engineer the parts that come after — retrieval, evals, guardrails, observability, and the systems that keep the feature honest in production.
— Practice / What we ship
What we ship.
-
Production RAG.
Vectorize on Cloudflare. Hybrid retrieval. Chunking strategies tuned to the actual corpus, not a tutorial.
-
Agent systems.
Anthropic SDK and OpenAI SDK with tool use, function calling, and the boring infrastructure that keeps an agent from looping.
-
MCP servers.
Model Context Protocol servers on Cloudflare Workers — for Claude, Cursor, or any other MCP client.
-
Evals as a habit.
If you can’t measure regressions, you don’t have an AI system — you have a prompt. We write evals into the deploy pipeline.
— Practice / What we don’t do
What we don’t do.
-
Model training or fine-tuning.
If your problem genuinely needs custom weights, we’ll point you at people who do that for a living.
-
Bolted-on chatbots.
A chat widget on a marketing site is rarely the right answer. We design AI as a feature, not a UI gimmick.
-
“Just generate the content.”
Marketing-volume text generation is well served by other tooling. That’s not an engineering engagement.
Stack — opinionated
Smaller toolkit, more depth.
Models
Anthropic Claude · OpenAI GPT · Cloudflare Workers AI
Retrieval
Cloudflare Vectorize · D1 · BM25 hybrid
Orchestration
Anthropic SDK · OpenAI SDK · MCP · Workers
Observability
Workers Logs · Sentry · custom evals
Prompts
Versioned in source · evaluated in CI
Surface
API · agent · MCP server · embedded UI
Field notes — AI
Recent writing on the practice.
-
What we learned running a public MCP server
We exposed our own site as a public, unauthenticated MCP server — six tools, stateless streamable HTTP, rate-limited where it costs money or sends email. The design decisions that mattered, and what we would do differently.
-
The US government now calls AI "Super Intelligence". What changes for your business
A September 2026 US executive order has federal agencies say "Super Intelligence" instead of AI. What it changes, what it does not, and what owners should do.
-
An AI receptionist for a small business: what it handles and where it fails
What an AI receptionist does well, where it breaks, and the guardrails to set before it answers your phone: approved answers, human handoff, and weekly review.
-
ChatGPT, Copilot, or Claude: choosing an AI assistant for a small team
How a small team can choose between ChatGPT, Microsoft Copilot, and Claude: where your work lives, what the work is, business plans, admin controls, and cost.
— From the GitHub
Templates we ship and maintain.
Working production patterns we use ourselves, MIT-licensed. Both deploy to your own Cloudflare account in under five minutes. Companion blog posts explain the architecture in full.
-
Production RAG pipeline on Cloudflare Workers
-
Production MCP server on Cloudflare Workers
— Work with us
— Read deeper
Field notes from this practice
-
What we learned running a public MCP server
We exposed our own site as a public, unauthenticated MCP server — six tools, stateless streamable HTTP, rate-limited where it costs money or sends email. The design decisions that mattered, and what we would do differently.
-
AI meeting notes and transcription for small business: what is safe and what is not
AI notetakers can save real time, but they record, transcribe, and sometimes train on your conversations. A practical guide to the consent and data-handling risks, how to set them up safely, and when to leave the recorder off.
-
Before you turn on Microsoft 365 Copilot, fix your oversharing
Copilot only shows people what they can already access. That is exactly the problem in most tenants. Here is how to find overshared SharePoint and OneDrive content, clean up permissions and links, and run a sensible pilot before rolling Copilot out.
-
What it costs to run a retrieval-augmented AI system on Cloudflare
The honest cost anatomy of a RAG system on Cloudflare — embeddings, Vectorize, model inference, storage, and the request path — plus how the bill scales and where it surprises people. A method to estimate yours, not a fake total.
-
MCP Servers in Production: When to Build, When to Skip
Model Context Protocol is the best primitive Anthropic shipped in 2024 — and the most over-applied. A field guide to when an MCP server is the right answer, when it's overkill, and how to operate one in production on Cloudflare Workers.
-
Structured output from language models: getting reliable JSON instead of prose
Free-text model output breaks pipelines. Here is how schema-constrained generation, tool calling, validation, and retries turn a language model into a component you can build on — and where the approach still fails.
-
RAG evaluation: how to know your AI answers are actually correct
A retrieval system that sounds confident is not the same as one that is right. How to build an evaluation set, measure retrieval and faithfulness, run human spot-checks, and catch regressions before your users do.
-
When Not to Use an LLM
A working checklist for keeping large language models out of the places they don't belong: deterministic logic, unverifiable outputs, high-stakes decisions, and problems a database query already solves.
-
Making Your Website Agent-Ready: What Actually Matters in 2026
AI agents and answer engines read your site before people do. What makes a site legible to them — structured data, markdown, an AI-crawler policy, and MCP.
-
Workers AI vs OpenAI: A Cost-Quality Matrix at Low Volume
Most production AI features default to OpenAI by reflex. They shouldn't. A real comparison of Workers AI, OpenAI, and Anthropic Claude across the four tasks that actually show up in client engagements — embeddings, generation, transcription, classification — with real numbers and a routing strategy that uses each for what it's good at.
-
Production RAG on Cloudflare Without LangChain
A 200-line RAG pipeline on Cloudflare Workers + Vectorize + D1 — the five primitives that matter, why frameworks rot at the wrong layer, and how to keep retrieval debuggable in production.
Working on something AI-shaped? Tell us about it.
Two paragraphs is enough. We respond in writing, with a fit / no-fit answer, within one business day.