Building with the Claude API

Go from your first API call to a tool-using, retrieval-aware Claude agent.

Start from client.messages.create(). Leave with working Python for tool use, hybrid RAG, MCP servers, and agent loops. The parts the docs don't cover.

Taught by Edwin Ashdown. Founder of AIFirstPartner, 12 production AI systems shipped.

Read the first lesson freeNo signup, no email.

What You'll Learn

Who this is for

For

Software engineers comfortable with Python and HTTP who have not yet shipped a feature on Claude. No prior experience with LLMs or Claude required.

Not for

ML researchers who want the math, product managers who want the strategy, or people looking for ChatGPT tutorials. We skip every line of that.

About the instructor

Edwin Ashdown founded AIFirstPartner and has shipped 12 production AI systems for clients in government, legal, and enterprise. He is fractional CTO at Speculo, a cyber risk software company, and manages cloud and data platform engineering for a large Australian government department supporting 20+ agencies across the portfolio. He publishes his build process at 150days.aifirstpartner.com.

This course is the playbook he uses when onboarding a team onto the Claude API.

Course Structure

1

Why most API tutorials fail in production

Free

What this course covers, who it's for, and why the free docs stop where the real work starts.

1 lessons

2

Pick the right Claude model in thirty seconds

Free

Haiku, Sonnet, Opus: which one, when, and what each one costs to run.

1 lessons

3

Your first working API call, end to end

Free

Thirteen lessons from your first request to streaming clean JSON out. Every concept lands in code you run.

13 lessons

4

Stop guessing whether a prompt is good

Free

Build an eval pipeline with model-based and code-based graders so you know a prompt works before users find out it doesn't.

8 lessons

5

Take a prompt from 2.32 to 7.86 on the eval

Free

Four techniques that measurably improve prompt quality, with the scores to prove each one.

7 lessons

6

Let Claude reach into your systems without handing it the keys

Free

Give Claude access to real-time data through custom tools, from schema design to multi-turn tool loops.

13 lessons

7

Retrieve the right chunk, whether the user searches by meaning or by word

Free

One retriever class. Two index types. No hallucinated "your document says..." moments.

7 lessons

8

The advanced features worth turning on (and the ones that aren't)

Free

Extended thinking, image and PDF support, citations, prompt caching, code execution: when each one is worth the cost.

9 lessons

9

Build an MCP server anyone can plug into

Free

Tools, resources, and prompts: the MCP primitives built by hand with FastMCP.

12 lessons

10

Drive Claude Code like an agent, not a chatbot

Free

Effective development workflows with Claude Code, and extending it with your own MCP servers.

4 lessons

11

When to pick a workflow over an agent (and when you'll regret it)

Free

Four workflow patterns you'll actually ship, plus the decision rule for reaching for a full agent.

8 lessons

12

Final assessment

Free

Prove you can build any of this from scratch.

1 lessons

13

Three projects to build next

Free

Skills summary and concrete projects to build with what you just learned.

1 lessons

Frequently Asked Questions

Why not just read Anthropic's free docs?+

The docs tell you what every endpoint does. They don't tell you which three endpoints you'll actually use, what the failure modes look like in production, or how tool use, RAG, and MCP compose into a working feature. This course is the second half of that story.

Won't the Claude API have changed by the time I finish?+

The API surface this course teaches (Messages, tool use, streaming, caching, MCP) is stable and versioned. Model names shift, the patterns don't. Lifetime access includes updates when they matter.

What will I walk away with that I can show someone?+

Six working programs in your own repo: a multi-turn chat app, an eval pipeline, a reminder-tool assistant, a hybrid RAG retriever, an MCP server and client pair, and a workflow-vs-agent reference design.

Do I need prior experience with AI or LLMs?+

No. The course starts from your first API call and builds up. You should be comfortable writing Python and calling REST APIs. No AI or ML background is required.

How long does the course take to complete?+

56 lessons across 13 modules. Most learners complete it in 6-8 hours of focused study. You can work through it at your own pace.

Can I start right away?+

Yes. The entire course is free and open. Start with Module 1 to get a feel for the voice and pace, then keep going through all 13 modules.

Do I need an Anthropic API key?+

Yes. You'll need an Anthropic API key for the hands-on exercises. The course walks you through obtaining one. Some modules also use VoyageAI for embeddings (free tier available).

Is this affiliated with Anthropic?+

No. Building with the Claude API is independent. This course is not an Anthropic product and has not been reviewed or endorsed by them.