Call the API with control
Make requests, hold multi-turn conversations, set system prompts and temperature, stream replies and ask for structured data.
Partners and press
Overview
Your first request is the easy part. This course takes you through to agents.
Building with the Claude API is a nine-hour Academy course for software engineers putting Claude into production applications. It covers authentication, tool use, retrieval, MCP and agent workflows, with prompt evaluations graded by models and by code. You need Python, basic JSON and an Anthropic API key; seven quizzes and a final assessment lead to a badge that does not expire.
8Modules
9Hours
9Skills
8Roles
What it covers
Learn all the way down.
Learn all the way down.
Perform when it matters.
Test your prompts
Build an eval workflow with generated test sets, and grade results with models and with code.
Give Claude tools and data
Define tools and schemas, handle tool results, and build retrieval pipelines with embeddings and BM25 search.
Design agent workflows
Build MCP servers and clients, then choose between chaining, routing, parallelization and agents.
Course outline
From an API key
From an API key
to agents you can test and trust.
We design this course ourselves. Anthropic issues the credential, and LUNARTECH is independent of Anthropic.
Start with the Messages API from Python. You authenticate, send a request, hold a multi-turn conversation, and shape replies with system prompts, temperature and streaming.
- API keys and the Python SDK
- Your first request and its response
- Multi-turn conversations
- System prompts and temperature
- Streaming replies
- Getting structured data back
You build A command-line chat that streams replies and keeps its own conversation history.
Prompts decide most of what a model does. You write clear, direct and specific instructions, structure them with XML tags, and add worked examples that show the model what good output looks like.
- Being clear and direct
- Specific instructions and constraints
- XML tags to separate inputs
- Worked examples
- Giving Claude a role
- Iterating on a weak prompt
You build A prompt rewritten in stages, with each change and its effect on the output.
A prompt you cannot measure is a guess. You build an eval workflow, generate test datasets, run them, and grade the results with models and with code, so that each change is judged by evidence.
- Why prompts need evaluations
- Generating a test dataset
- Running a prompt across the dataset
- Code-based grading
- Model-based grading
- Scoring and comparing prompt versions
You build An eval pipeline that grades two prompt versions on a generated test set.
Tools let Claude call your code. You write tool functions and JSON schemas, handle tool-use blocks, return results, chain multi-turn tool conversations, and use the text edit and web search tools.
- Tool functions and schemas
- Tool-use blocks and results
- Multi-turn tool conversations
- Batching and multi-tool requests
- The text edit tool
- The web search tool
You build A multi-tool assistant that completes a request over several tool calls.
Claude can only use what it sees. You chunk documents, create embeddings, add BM25 lexical search, and join the two in a multi-index retrieval pipeline that feeds the right passages into a prompt.
- Why retrieval matters
- Chunking strategies
- Creating embeddings
- Vector search
- BM25 lexical search
- Combining indexes in one pipeline
- Evaluating retrieval quality
You build A retrieval pipeline that combines embeddings and BM25 over a document set.
The API goes beyond text. You turn on extended thinking, send images and PDFs, ask for citations, cut cost with prompt caching, and run code with the Files API.
- Extended thinking
- Image and PDF input
- Citations
- Prompt caching
- Code execution
- Uploading and reusing files
You build A document analysis tool that reads a PDF, cites its sources and caches repeated context.
The Model Context Protocol standardizes how Claude reaches tools and data. You build a server with tools, resources and prompts, test it with the inspector, and write a client that uses it.
- Why MCP exists
- Defining tools on a server
- Resources and prompts
- Testing with the server inspector
- Writing an MCP client
- Connecting a server to an application
You build An MCP server with a tool, a resource and a prompt, plus a client that calls it.
Complex tasks need structure. You compare chaining, routing and parallelization workflows with true agents, decide when each fits, and meet Claude Code and computer use as agents you can set to work.
- Chaining workflows
- Routing workflows
- Parallelization
- Agents and their loops
- Choosing a workflow or an agent
- Setting up Claude Code
- Extending Claude Code with MCP servers
- A first look at computer use
You build The same task built as a workflow and as an agent, with a comparison of the results.
Issued by
Certifying body · Independent of LUNARTECH
Anthropic
Four role-based certifications for people building on Claude, and free Academy courses with badges. The four certifications are open to members of the Claude Partner Network, not the general public. Membership is free for firms. Exams are proctored and delivered by Pearson, and the credential is issued through Credly. Academy courses are free, and a badge comes from passing the course’s quizzes.
How you get there
Top-tier roles go to people who can do the work.
Top-tier roles go to people who can do the work.
Here’s how you get there.
Know where you start.
Proficiency in Python, basic familiarity with JSON, and an Anthropic API key. Anthropic aims it at engineers integrating Claude into production applications.
Work through the course.
Eight modules, designed by LUNARTECH, at your own pace.
Earn it with Anthropic.
Anthropic issues the credential, so you earn it directly with them.
Support
Support at every stage.
Support at every stage.
You won’t be working through this alone.
Before you start
Try it first.
A 3-day free trial opens a selection of the content. Your card is only charged once it ends.
While you learn
Mentors within reach.
Stuck on a concept? Reach out to a mentor whenever you need help.
While you learn
One-on-one sessions.
On the yearly plan, one-on-one sessions give you dedicated support.
Any time
A team behind you.
Write to info@lunartech.ai at any point, from your trial onwards. If your employer is funding you, we’ll set it up with them directly.
All the way through
A schedule that fits around your life.
Your own paceFrom anywhereAt any hour
After the last lesson
Stay in the network.
Your alumni network stays with you: ongoing support, opportunities and industry insight.
Career support
Career support, past the last lesson. Coaching, a sharper resume, real interview preparation and the people to know.
Career direction
Tailored coaching helps you decide where to aim and how to get there.
Strong portfolio
Hands-on projects become work you can show, not just claim.
Resume and profile
Personalized refinement, so what you send says what you can actually do.
Interview preparation
Preparation for the questions that decide it, so you walk in ready.
Network and search
Connections with industry leaders, and an alumni network that stays with you.
Reviews
Real stories from the community.
LUNARTECH Academy has been the most empowering learning experience of my life, giving me a clear, structured path from the absolute basics to building real-world AI systems with confidence.
Your page is fantastic. As a bachelor’s student in Data Science now accepted for a master’s at UConn, your work has been a real source of motivation.
The programme’s clear, bite-sized content and practical projects dramatically improved my speed from fuzzy idea to MVP and my ability to communicate AI value. I followed the system, and it works.
I really appreciate your teaching style and the way you break down complex topics. It has been incredibly helpful.
After years working mainly with R for econometrics, I found your Python machine learning course a refreshing and engaging way to learn Python.
As a Data Science graduate, I want to thank you for the effort you put into making videos to support growing data scientists.
I’ve been following your work since taking your machine learning course, and I’m impressed by your practical approach to applying AI.
Why choose us
Built around how you actually learn.
One standard behind every course, from the first lesson to long after the last.
Hands-on practice
Apply every idea to real problems, so it becomes something you have used, not only seen.
Industry-aligned curriculum
We keep courses current with the tools, techniques and skills the field asks for.
Flexible learning
Study at your own pace, from anywhere, at any hour.
Certificate of completion
Finish the course and earn a certificate that shows what you have learned.
Focus on your success
Personalized learning plans and support structures carry you through the hard parts.
Lifetime alumni network
Stay connected after you finish, with ongoing support, opportunities and industry insight.
Your certificate
It doesn’t raise its voice. Neither will you.
Finish a LUNARTECH course and its certificate is issued in your name, under our signature. Anthropic’s credential comes from Anthropic.
Certificate of completion
Your Name
Building with the Claude API course
LUNARTECH RISE Academy
Pricing
This course comes with the membership.
This course comes with the membership.
So does everything else.
One membership opens every course, certification, workshop and masterclass in the Academy. Every plan starts with a 3-day free trial. Anthropic issues the credential.
3 days free, then $29.97 a month. Your card is only charged once the trial ends.
Included in every plan
- Every course in the Academy
- Every certification course
- Workshops and masterclasses
- A certificate of completion
- A 3-day free trial
- Learning at your own pace
- The lifetime alumni network
- Upgrades at any time
In practice
Eight roles.
Eight roles.
One credential across them all.
No single job owns it. Here’s where each role leans hardest, and where its work ends up.
- 01API access
- 02Evals
- 03Prompting
- 04Tool use
- 05Retrieval
- 06Features
- 07MCP
- 08Claude Code
- 09Agents
-
Evals tell you whether a prompt change helped. Retrieval and tools decide what Claude can know.
Evals, Tool use, Retrieval, Agents
Product engineering, Customer support
-
Most AI features start as one API call. Caching and streaming make them affordable and fast.
API access, Prompting, Features
Product engineering, Internal tooling, Startups
-
MCP standardizes how Claude reaches your systems. Workflows decide how much autonomy to allow.
MCP, Agents
Consulting, Internal tooling
-
A model call is a network call that can fail or lag. Streaming and caching shape how it behaves.
API access, Features
Product engineering, Internal tooling
-
Prompt changes need the same test discipline as models. Model-graded and code-graded evals cover both.
Evals, Prompting
Product engineering
-
Retrieval quality depends on how documents are prepared. Chunks and embeddings come before the first query.
Retrieval
Internal tooling
-
Users see the answer arrive as it is written. Tools let the app act on their behalf.
API access, Tool use, Features
Product engineering, Startups
-
Client systems differ, and so do their tool needs. MCP and agent workflows give you a common method.
MCP, Agents
Consulting
- Product engineering
- Internal tooling
- Customer support
- Consulting
- Startups
AI Engineer
Evals tell you whether a prompt change helped. Retrieval and tools decide what Claude can know.
Over 10,000 students trust LUNARTECH
LUNARTECH gives you the skills
to learn, build, create and lead.
Engineers
Understand systems all the way down. Build the ones others rely on.
Scientists
Understand what the data says. Build models that hold up.
Researchers
Understand the papers. Build on them, and take the work further.
The field
Anyone can use AI.
Anyone can use AI.
Few can engineer it. This is where that starts.
+340%growth in open roles requiring AI skills
Roles and pay
~35,000 open roles right now
Open roles: Built In, Greenhouse, LinkedIn.
Typical salaries: Glassdoor, Levels.fyi, Payscale, Indeed, Ravio, JobRise, U.S. BLS. Military: 2026 U.S. basic pay, drone officers with aviation incentive pay.
Updated November 2026.
FAQ
Frequently asked questions.
Need help? These answers cover most of what people ask before they start.
No. Anthropic issues it. LUNARTECH is independent of Anthropic, and its names and marks belong to it. When you finish a course of ours, you earn a LUNARTECH certificate of completion for that course.
No. We design this course ourselves, around what the credential covers. Anthropic has no part in it, and you still earn the credential directly with Anthropic.
9 hours, online course. The passing score is Pass each quiz.
Proficiency in Python, basic familiarity with JSON, and an Anthropic API key. Anthropic aims it at engineers integrating Claude into production applications.
Does not expire. Completion badges do not expire. You can retake a course after a major update.
We last reviewed it on 5 November 2026, from Anthropic’s own pages. Details change, so check the official page before you book.
Our 3-day free trial gives you access to a selection of content in the bootcamps, courses and materials, so you can experience the value of our content first-hand. This includes comprehensive learning materials and interactive sessions. You won’t be charged during this period, though we require your credit card details at the start to ensure a seamless transition should you choose to continue.
Yes, entering your credit card details is a necessary step to begin your free trial. The process is entirely secure, and we ask for it to provide a seamless transition to a paid subscription if you decide to continue beyond the trial. You will only be charged after the trial period ends, with full access to our content based on the plan you choose.
After your 3-day free trial you gain access to the full breadth of our content, depending on the subscription plan you choose. We offer free trials for our monthly, bi-annual and annual plans, and each plan provides a different scope of access and benefits.
If your employer has agreed to fund your learning, in part or in full, please contact us at info@lunartech.ai. We’ll work with you and your employer to set up everything needed for your subscription.
Yes. Our support remains strong both during your free trial and after you subscribe. Reach the team at info@lunartech.ai with any question, whether you’re onboarding, navigating your trial, or need help as a member. Subscribers to the yearly plan also receive dedicated support in one-on-one sessions.
You can upgrade your plan at any time during your subscription. Downgrading is not available for bi-annual or annual plans, but you can cancel and then choose a new plan that suits you better. For bi-annual and annual plans we also offer payment in instalments; please reach out to learn more.
The course
Build the skills behind Building with the Claude API.
Learn to build production applications on the Claude API. Start with a free trial, or enroll in a plan and work through the course at your own pace. Anthropic issues the credential.
LUNARTECH is independent of the vendors and certifying bodies listed here. Their names, exam titles and marks belong to them, exams are run by them, and credentials are issued by them. Reviewed 5 November 2026. Catalogues change often, so confirm the details on the official page before you book.
