78 East LabsApply

Building with Claude

Going from asking Claude questions to building something that runs — prompts, tools, retrieval, and knowing when the answer cannot be trusted.

The distance between a good conversation with Claude and a working application is mostly engineering, not prompting. This course covers both, in that proportion.

Claude is the model this lab builds on and partners with, so the examples are the ones we actually use.

Every lesson is free and needs no sign-up.

Syllabus

3 lessons published

How the model behaves

What it is good at, where it is confidently wrong, and how to design around that rather than hope.

Prompting properly

Instructions, examples, structure, and why "be accurate" does nothing.

Being written — not published yet.

Calling the API

Your first request, messages, system prompts, streaming, and what each parameter actually changes.

Being written — not published yet.

Giving it tools

Letting the model call your code, and the difference between a tool that reads and one that writes.

Being written — not published yet.

Answering from your own documents

Retrieval, chunking, citations, and refusing to answer when the documents do not say.

Being written — not published yet.

Shipping it

Evaluating output, cost, latency, failure modes, and what a human still has to approve.

Being written — not published yet.