Build Your AI Assistant with Claude

6 Interactive Sessions

Short, interactive sessions: watch it work, try it, then build it yourself. You can go deeper at any time in the written chapters.

1. 1

   Send Claude a message and get a reply

   You want an assistant that summarizes your unread email, checks your 2pm meeting and drafts a prep doc. It starts with one small program that can send a message to Claude and get a reply back. That is the API.

2. 2

   Let Claude use tools: the tool-use loop

   Ask a plain chat model “what's on my calendar at 2pm?” and it may make something up, because it cannot see your calendar. Tools fix that. You give Claude a function it can ask for, your code runs it, and the real answer goes back.

3. 3

   Read your email and calendar, and draft replies safely

   Now the assistant gets tools for your email and calendar: read the unread mail, check the 2pm, draft a reply. One clear line keeps it safe. It prepares the work, and you approve anything that cannot be undone.

4. 4

   Look things up and show the sources

   “Draft a prep doc for my 2pm” needs facts that are not in the inbox or the calendar. The 2pm reviews the ML inference service, and an open task asks what GPU time costs. So the assistant researches. It searches your saved bookmarks, reads what comes back and writes a short briefing where every claim names its source.

5. 5

   Help the assistant remember you

   Yesterday you told it that monitoring alerts are always critical, and today it forgot. Without memory, every conversation starts from nothing. Memory is two things: the history of this chat, and a small saved profile of you that is sent every time.

6. 6

   Run your assistant on your own machine

   An assistant is only useful if it is there when you need it. So you package what you built into a small command-line tool on your own machine, with your own API key, and type “summarize my morning” in your terminal.

How this certificate is scored

Your certificate shows how many of your written answers met the rubric below, checked by an AI grader. Anyone who checks your certificate sees it.

• You answer 6 short questions, one for each module, in your own words (at least 40 words each).
• An AI grader checks each answer against what its module asks for: it must answer the question, use the course's practice case specifically, and be correct.
• To pass, at least 5 of the 6 answers must meet that bar. The certificate says the answers were graded by AI.

The rubric

1. Module 1, API Basics: Claude API calls with streaming.
2. Module 2, Tool Use: Function calling with 4 tools.
3. Module 3, Email & Calendar: Email triage + calendar assistant.
4. Module 4, Research Agent: Search, summarize, and cite sources.
5. Module 5, Memory & Context: Conversation history + user preferences.
6. Module 6, Deploy Locally: CLI assistant running on your machine.

What you walk away with