About
Built, not just advised
CloudCraft is an AWS generative-AI architecture practice. Its credibility comes from shipping and operating production AWS systems end to end — not from slideware.
Plenty of people can draw a GenAI architecture on a whiteboard. Far fewer have built one, put it into production, and lived with what it costs to run. CloudCraft is built on the second kind of experience: designing and operating real systems on AWS, where the difference between a demo and a system is the engineering nobody sees in the diagram.
That hands-on background is also why cost and token efficiency is the practice’s specialty. The skill to build a GenAI system and the skill to make it cheap to run usually live in different people; here they live in the same one, because the same person has had to ship the system and then answer for the bill.
The Golden Jacket
CloudCraft’s principal holds the full AWS certification stack — a ‘Golden Jacket’ owner. Golden Jacket owners hold every active AWS certification at once — the complete current stack. It’s a level few ever reach: an estimated few hundred people worldwide have done it. That’s what makes the Golden Jacket such a rare professional distinction — it validates both breadth of expertise across the AWS domain and a sustained commitment to continuous learning.
Production systems, end to end
The work behind the practice includes Bedrock-backed GenAI applications, RAG pipelines, serverless backends (Lambda, API Gateway, DynamoDB, Aurora), and multi-account infrastructure as code with CDK — plus the production engineering, like cache isolation, rate limiting, and promotion workflows, that turns a prototype into something that can be operated. See what CloudCraft has built →
How engagements run
Engagements are deliverable-shaped and run remote and async — scoped, executed, and delivered, with synchronous time kept to a kickoff and a readout rather than a calendar of standing meetings. It keeps the focus on the work and the artifact; when a live working session is the right tool, CloudCraft uses it.
Running GenAI on AWS — or about to?
A short conversation is the best way to see whether CloudCraft is the right fit for what you’re building or what it’s costing you.