Kurs uczy budowania agentów AI od podstaw w czystym Pythonie, bez ukrywania logiki za frameworkiem, co bardzo cenię. Tempo w drugiej połowie kursu jest trochę szybsze niż na początku, więc czasem trzeba było cofnąć nagranie. Mimo to wyszedłem z solidnym zrozumieniem, jak działa pętla decyzyjna agenta.
Building AI Agents in Python from Scratch
Understand the core mechanics of autonomous systems and write plain Python code to create intelligent agents from the ground up.
-
💬
AI instructor
Ask about any lesson and get a clear answer instantly, anytime. -
🕐
Start anytime
No schedules or deadlines — learn at your own pace, whenever suits you. -
🌐
In English
Lessons, tasks and certificate — all fully in your language.
About this course
AI agents are transforming how we interact with technology, moving beyond simple chat interfaces to autonomous, multi-step problem-solving. If you want to understand how these intelligent systems actually work under the hood, building one from scratch is the most effective approach. This course strips away the magic of heavy, complex frameworks, guiding you to build functional, autonomous AI agents using plain Python. You will learn the underlying architecture of agentic systems, from memory management to tool execution, empowering you to design custom AI solutions tailored to your specific needs.
What you'll learn:
• Understand the fundamental terminology, concepts, and architecture of autonomous AI agents.
• Build core agent loops and decision-making processes using standard Python.
• Implement modern tool calling capabilities so your agents can interact with external APIs and services.
• Design basic memory systems and retrieval-augmented generation (RAG) patterns for context awareness.
• Apply modern Python practices, including type hints and async functions, to structure your agent code effectively.
• Practice foundational prompt engineering techniques to guide agent behavior reliably.
You will start by exploring the foundational definitions and concepts of agentic AI before moving into practical implementation. The text-based lessons will walk you step-by-step through writing the logic, managing state, and expanding your agent's capabilities through written coding exercises. This course is designed specifically for beginners with basic Python knowledge who want to understand AI agents without any prior machine learning experience. Start reading today to unlock the mechanics of autonomous AI and build your first intelligent agent from scratch.
What you'll get
-
📜
Certificate of completion
Add it to your LinkedIn profile -
💬
Personal AI tutor
Stuck on a lesson? Ask your built-in tutor anything, any time. -
🎧
Audio version included
Learn on the go — no screen needed -
♾️
Lifetime access
Come back anytime, no expiry -
📱
Phone or computer
Works anywhere, any device -
💸
14-day refund
No questions asked -
⚡
Short & focused
2h 42m of practical content
Certificate of completion
Every course you complete on PickAClass issues a credential like this — original, with its own code, verifiable by URL, and detailed about what was actually demonstrated.
P
PickAClass
Skills profile · verifiable
Document
Certificate of Mastery
This certifies that
Name Surname
has successfully demonstrated mastery of
Building AI Agents in Python from Scratch
Skills demonstrated
✓
Behavioral pattern analysis
Foundational
1.2 hrs
✓
Decision-architecture frameworks
Proficient
1.4 hrs
✓
A/B test design
Proficient
1.7 hrs
✓
Behavioral copywriting
Advanced
1.9 hrs
P
PickAClass — Name Surname
Building AI Agents in Python from Scratch
Page 2 of 2
Performance detail
Coursework summary
Lessons completed
14 / 14
Practice questions
26 / 28
Assignments submitted
4 (avg 4.5 / 5)
Capstone project
Reviewed — 4.6 / 5
Total practice
6.2 hrs
Performance benchmark
Cohort rank
Top 12% of 1,625
Time to completion
11 days (median: 22)
Mastery score
91 / 100
Practice-question score
94%
Skill verification
Verified Skill Path
Reviews (16)
شرح ممتاز لكن يحتاج أمثلة أكثر
Ce cours va vraiment au fond des choses en expliquant la mécanique des agents autonomes sans passer par des bibliothèques toutes faites. J'ai apprécié écrire le code en Python pur, ça force à vraiment comprendre chaque étape plutôt que de copier-coller. Seul bémol, certains passages sur la gestion de la mémoire de l'agent auraient mérité plus de détails.
Comprendre enfin la boucle d'un agent autonome en écrivant tout en Python pur, sans cacher la mécanique derrière une librairie, c'était exactement mon besoin.
Building an agent loop in plain Python with no heavy framework demystified the whole thing for me; the tool-calling section was gold.
هذه الدورة غيّرت فهمي بالكامل لكيفية عمل الوكلاء الذكية من الداخل، لأنها لا تعتمد على أي مكتبات جاهزة بل تبني كل شيء بلغة بايثون خالصة خطوة بخطوة. أعجبني كثيرًا أسلوب الشرح الذي يبدأ من الأساسيات البسيطة مثل حلقة القرار ثم يتوسع تدريجيًا نحو أنظمة أكثر تعقيدًا. كل درس يضيف طبقة جديدة من الفهم دون أن يشعرك بالتشتت أو الإرهاق. بعد إنهاء الدورة استطعت بناء وكيل بسيط خاص بي من الصفر وفهمت فعليًا كل سطر كتبته فيه. أنصح بشدة بمتابعتها لمن يريد فهم الآليات الحقيقية وراء الوكلاء الذكية وليس مجرد استخدام أدوات جاهزة.
Penjelasan agen AI yang jelas dan mendalam
라이브러리 없이 순수 파이썬으로 에이전트를 처음부터 만드는 과정이라 원리를 제대로 이해할 수 있었어요. 설명 순서도 논리적이라 따라가기 편했고, 강의 끝날 때쯤엔 제 손으로 작은 에이전트를 완성했습니다. 개념만 배우는 게 아니라 직접 만들어보는 방식이라 훨씬 오래 기억에 남을 것 같아요.
Курс объясняет механику автономных агентов на чистом Python без готовых фреймворков, и это реально помогает понять, что происходит под капотом.
Khóa học giải thích rất rõ cách xây dựng agent AI bằng Python thuần từ đầu đến cuối, không dùng thư viện có sẵn nên hiểu sâu hơn hẳn.
Finalmente ho capito gli agenti AI
Świetny kurs dla osób, które chcą naprawdę zrozumieć, jak działają agenci AI pod maską, a nie tylko korzystać z gotowych bibliotek. Kod pisany od zera w czystym Pythonie sprawia, że każdy element mechaniki staje się jasny. Po ukończeniu kursu czuję, że rozumiem temat dużo głębiej niż wcześniej.
Kursus ini mengajar cara bina ejen AI dari asas menggunakan Python tulen, jadi saya betul-betul faham mekanik di sebaliknya berbanding sekadar guna library sedia ada.
Duidelijke uitleg over hoe autonome agents echt werken onder de motorkap, al had ik graag wat meer voorbeelden gezien bij het laatste hoofdstuk.
This course strips away all the framework magic and shows you exactly how an AI agent's decision loop works using plain Python. I really valued that approach because it forced me to understand the mechanics instead of just importing a library and hoping for the best. The early lessons on the core loop are excellent and very well paced. Where it loses a star for me is the section on tool integration, which moves faster than the rest and could use another example or two. Still, by the end I had built a working agent from scratch and actually understood every piece of it.
Me gustó mucho que el curso construya los agentes desde cero en Python puro, sin depender de frameworks que ocultan lo que realmente pasa. Se nota que está pensado para entender la mecánica interna y no solo usar herramientas. Lo único es que algunas secciones intermedias avanzan bastante rápido.
Learners also took
⚡ Best to start
🎓 With certificate
Agentic AI Development with LangGraph and LangChain
Certificate
Hands-on
K21.000
→
⚡ Best to start
🎓 With certificate
No-Code AI Automation: Build Chatbots and Launch an Agency
Certificate
Hands-on
K21.000
→
🎓 With certificate
Building RAG Systems and AI Agents with Python and OpenAI
Certificate
Hands-on
K21.000
→
🔥 In demand
🎓 With certificate
Prompt-Driven Development: Build Full-Stack Next.js Apps with Cursor AI
Certificate
Hands-on
K21.000
→
Frequently asked
What do I need to take this course? +
Just a phone or computer with internet. No installs, no special hardware.
How do I pay? +
By card via Stripe. We don’t store card details — Stripe handles them securely.
Can I get a refund? +
Yes — full refund within 14 days, no questions asked.
How long will I have access? +
Forever. Once you purchase, the course is yours to revisit anytime.
Will I get a certificate? +
Yes. On completion you'll receive a certificate you can add to your LinkedIn profile.
Built for learners in
Tech
Design
Finance
Marketing
Healthcare
Education
Hospitality
Manufacturing
10
Get 10 courses a month
Members get 10 courses of their choice every month for K0. No per-course charges — you pay only the subscription.
K100.000 / per month
- ✓ 10 courses every month
- ✓ Cancel anytime
Renews monthly. Unused courses expire at the end of each billing month.