ruen
AGENTS

AI Agents in Practice

Build agents that plan, call tools and finish real tasks: inbox, CRM, reports. With retries, memory and cost limits.

Start the courseFirst module free
7 modules34 lessons7 hLevel: Intermediate

Who it is for

  • Developers who used ChatGPT or Claude API and want more than a chat
  • Founders and ops people automating routine work
  • Anyone comfortable with Python basics and a terminal

What you will have at the end

  • An inbox agent that sorts mail and drafts replies
  • A CRM agent that updates deals from calls and chats
  • Retry budgets, cost caps and a step log for every run

Most agent tutorials stop when the demo works once. This course starts there. You give an agent real tools, teach it to recover from a failed API call, cap what it can spend and log every step so you can see why it did what it did. By the end you run two agents that do daily work without supervision.

Program

1

What an agent really is

4 lessons · 46 min
Result: A loop that plans and acts
2

Tools and strict arguments

5 lessons · 58 min
Result: Three working tools
3

Memory that does not lie

4 lessons · 50 min
Result: Short and long memory
4

When things fail

5 lessons · 55 min
Result: Retries, timeouts, fallbacks
5

Inbox agent

6 lessons · 74 min
Result: Project 1 in production
6

CRM agent

6 lessons · 70 min
Result: Project 2 in production
7

Cost, safety and logs

4 lessons · 48 min
Result: Limits you can trust

Program reviewed by

ML engineer · 8 yearsDevOps · 10 yearsBackend · 9 yearsAutomation lead · 7 yearsSecurity · 6 years
Exam & certificate

A certificate that is hard to fake and easy to check

  • 1Strict exam. Timer, one attempt at a time, switching tabs or windows stops the test.
  • 2Public record. The QR code opens course.awereads.com/v with the holder, course and date.
  • 3Signed ID. Change a name or date in the file and the verification code no longer matches.
Verify a certificate
Sample Awe Course certificate

Read before you start

What is an AI agent, in plain words

An AI agent is a language model that can take actions: it reads a task, decides which tool to call (search, email, a database), looks at the result and repeats until the task is done. A chatbot only answers. An agent does the work.

→

Course questions

Which model do the agents use?

Any model with tool calling: Claude, GPT or an open model on your own server. The code is the same, only the client changes.

Do I need a paid API key?

No. Every project also runs on a free local model. A paid key makes answers better, not possible.

Other courses

OWN AI

Your Own AI Model

Run open models on your computer, answer questions from your own documents and tune a model to your style. No data leaves your machine.

5 modules · 24 lessons · 5 h
SERVER

AI on Your Own Server

Rent a server, deploy models and agents, keep them online, private and cheap: Docker, HTTPS, backups, monitoring.

5 modules · 21 lessons · 4 h