Build your own functional AI coding agent from the ground up using Python and the free Gemini Flash API. This project-based tutorial provides a deep understanding of how powerful AI tools work by guiding you through the creation of an agentic loop powered by tool calling. You will implement the core abilities for your agent to interact with and modify a codebase, including reading files, writing to files, and executing code to get feedback.

Lane Wagner created this course.

Check out the interactive version of the course on boot.dev: https://www.boot.dev/courses/build-ai-agent-python

❤️ Support for this channel comes from our friends at Scrimba – the coding platform that's reinvented interactive learning: https://scrimba.com/freecodecamp

⭐️ Contents ⭐️
- 00:00:00 Introduction
- 00:01:14 Why Build an AI Agent?
- 00:01:49 Course Overview & What We're Building
- 00:02:25 How to Follow Along
- 00:03:47 What is an AI Agent? (Agentic Loops & Tool Calling)
- 00:06:03 The Agent's Four Tools
- 00:07:58 Prerequisites & Project Goals
- 00:10:08 Demo: Agentic vs. One-Shot Responses
- 00:13:07 Python Project Setup with UV
- 00:15:44 Getting Started with the Gemini API
- 00:19:21 Making Your First API Call
- 00:24:44 Accepting Command-Line Arguments
- 00:27:46 Managing Conversation History
- 00:30:39 Adding a Verbose Flag for Debugging
- 00:33:35 Setting Up the Project for Our Agent (Calculator App)
- 00:36:23 Building Tool #1: Get Files Info
- 00:49:39 Building Tool #2: Get File Content
- 00:58:24 Building Tool #3: Write File
- 01:05:26 Security Note: Dangers of Running AI-Generated Code
- 01:07:30 Building Tool #4: Run Python File
- 01:18:00 Understanding the System Prompt
- 01:33:10 How Tool Calling Works: Declaring Functions for the LLM
- 01:41:38 Adding All Function Declarations
- 01:49:19 Implementing the Function Calling Logic
- 01:57:30 Creating the Agentic Loop
- 02:07:11 Final Demo: Agent Fixes a Bug Autonomously
- 02:13:44 Conclusion & Next Steps

🎉 Thanks to our Champion and Sponsor supporters:
👾 Drake Milly
👾 Ulises Moralez
👾 Goddard Tan
👾 David MG
👾 Matthew Springman
👾 Claudio
👾 Oscar R.
👾 jedi-or-sith
👾 Nattira Maneerat
👾 Justin Hual

--

Learn to code for free and get a developer job: https://www.freecodecamp.org

Read hundreds of articles on programming: https://freecodecamp.org/news

🔹Download the free guide from HubSpot on Your 2026 Guide to
AI Agents: https://clickhubspot.com/70c662
🔹Code in this video (available inside Skool): https://www.skool.com/ai-agent....-builders/classroom/

No frameworks. No vibe coding. No third-party tools. In this beginner course I show you how to build a fully functioning AI agent from scratch in pure Python — so you actually understand what's happening under the hood, not just how to prompt a tool.

Want to LEARN how to build useful AI agents that actually get things done? Go here: https://aiagentbuilders.co/yt

🚀 Tools I Use
Get 10% off with code techwithtim
Openclaw setup: https://www.hostinger.com/techwithtim
VPS setup: https://www.hostinger.com/techwithtim10
Wispr Flow (Best AI Dictation): https://ref.wisprflow.ai/TechWithTim-aug26

🎞 Video Resources 🎞
HubSpot Free Resource - https://clickhubspot.com/70c662
Skool Lead Magnet: https://www.aiagentbuilders.co..../yt-resources/pure-p

⏳ Timestamps ⏳
00:00 | Overview
00:30 | What is an Agent
02:52 | The Three Steps
03:21 I Step 1 - Calling an API
11:50 | HubSpot Free Resource
13:15 | Step 2 - Conversation History
17:08 | Step 3 - Tool Calling
28:09 | Full Agent Build

Hashtags
#Python #AIAgents #BuildWithAI

UAE Media License Number: 3635141

Learn how to use AI tools to become more productive as a developer.

You will master AI pair programming and agentic terminal workflows using top-tier tools like GitHub Copilot, Anthropic's Claude Code, and the Gemini CLI. The course also covers open-source automation with OpenClaw, teaching you how to set up a highly customizable, locally hosted AI assistant for your development environment. Finally, you will learn how to maintain high code quality and streamline your team's workflow by integrating CodeRabbit for automated, AI-driven pull request analysis.

Some of this course is based on this article from Mrugesh Mohapatra: https://www.freecodecamp.org/n....ews/how-to-become-an

CodeRabbit provided a grant to make this course possible.
Try out CodeRabbit: https://coderabbit.link/fcc

Contents
- 0:00:00 Introduction to AI-Assisted Development
- 0:00:42 Core Fundamentals: Tokens, Context Windows, and Hallucinations
- 0:05:48 When to Use AI vs. When to Code Manually
- 0:06:57 Setting Up GitHub Copilot in VS Code
- 0:09:42 Copilot Pricing and Plans
- 0:10:18 First Steps: Ghost Text and Code Completions
- 0:13:40 Pro Tip: The Neighboring Tabs Trick
- 0:15:52 Practice Exercise: Building a To-Do App
- 0:17:15 Interaction Modes: Ask, Edit, and Agent Mode
- 0:21:44 Agent Mode: Building a Full REST API Autonomously
- 0:24:52 Repository Customization with Instruction Files
- 0:26:34 Using Participants and Slash Commands
- 0:28:34 Automated Code Reviews with CodeRabbit
- 0:30:57 Setting Up CodeRabbit for GitHub Repositories
- 0:32:03 Simulating Real-World PR Reviews and Security Fixes
- 0:37:33 Chatting with AI Directly in Pull Requests
- 0:41:12 Configuring CodeRabbit Behaviors (.yaml)
- 0:41:58 Local Reviews via the CodeRabbit CLI
- 0:48:13 Powerful Terminal AI: Claude Code vs. Gemini CLI
- 0:49:12 Claude Code: Reasoning, Thinking Modes, and Fixes
- 0:53:02 Gemini CLI: Million-Token Context and Multimodal Features
- 0:57:01 OpenClaw: Your Open-Source Personal AI Assistant
- 1:01:01 Automating Tasks with Cron Jobs and Desktop Actions
- 1:03:33 Orchestrating Your AI Workflow
- 1:08:27 Model Context Protocol (MCP): Giving AI Real-World Tools
- 1:12:40 AI Code Quality and Security Essentials
- 1:15:03 The Formula for Better Prompt Engineering
- 1:16:13 Course Recap and Final Resources

Warp is free to try but for a limited time, you can try Warp Pro free for 7 days with 2,500 AI credits - no card required. Use my link https://go.warp.dev/forrestytcow

Everyone seems to be using AI to code now, and in this video, I'm showing you how to actually code with AI - not vibe code. Because there's a huge difference between software developers who strategically guide AI, and vibe coders who just let it take the wheel.

0:00 Everyone’s Coding with AI
0:32 Stop Repeating Yourself
1:45 Prompting is Important
4:21 The Software Development Workflow
6:42 Pair Programming
7:57 Implement Multiple Agents
9:25 git worktree
9:57 Extra Stuff AI Can Help With
11:21 Pull the Plug
11:58 Always Remember This

This video is sponsored by Warp.

If you're a developer, sign up to my free newsletter Dev Notes 👉 https://www.devnotesdaily.com/

If you're a student, checkout my Notion template Studious: https://notionstudent.com

Don't know why you'd want to follow me on other socials. I don't even post. But here you go.
🐱‍🚀 GitHub: https://github.com/forrestknight
🐦 Twitter: https://www.twitter.com/forrestpknight
💼 LinkedIn: https://www.linkedin.com/in/forrestpknight
📸 Instagram: https://www.instagram.com/forrestpknight

🌟 Build Your Command Center in Notion - https://www.pressplay.cc/link/s/F8236D6B

Create your first AI agent in three simple steps using n8n! This tutorial shows you how to create an automated subscription tracker that processes natural language input and updates Google Sheets automatically.

You'll learn to configure the agent's brain (chat model and memory), connect tools like Google Sheets, and write system prompts that control agent behavior. Perfect for non-technical users ready to transition from using AI tools to actually building with them.

*TIMESTAMPS*
00:00 Build Your First AI Agent
00:29 Refresher on AI Agents
01:20 Getting Started on n8n
02:54 Why Bother?
03:32 Step 1: Building the Brain
08:21 Step 2: Connecting the Tools
10:38 Step 3: Activating the Brainstem
12:21 Testing our AI Agent
14:56 Beyond the Basics

*RESOURCES MENTIONED*
OpenAI API Setup: https://platform.openai.com/
ChatGPT System Prompt Template: https://www.jeffsu.org/build-y....our-first-ai-agent-i
Notion Command Center System: https://www.pressplay.cc/link/s/F8236D6B

*BUILD A POWERFUL WORKFLOW*
🦾 AI Systems Academy - https://systemsacademy.ai/?utm_source=youtube&utm_medium=video&utm_campaign=186
📈 The Workspace Academy - https://academy.jeffsu.org/workspace-academy?utm_source=youtube&utm_medium=video&utm_campaign=186
✍️ My Notion Command Center - https://www.pressplay.cc/link/s/DE1C4C50

*BE MY FRIEND:*
📧 Subscribe to my newsletter - https://www.jeffsu.org/newsletter/?utm_source=youtube&utm_medium=video&utm_campaign=description
📸 Instagram - https://instagram.com/j.sushie
🤝 LinkedIn - https://www.linkedin.com/in/jsu05/

*MY FAVORITE GEAR*
🎬 My YouTube Gear - https://www.jeffsu.org/yt-gear/
🎒 Everyday Carry - https://www.jeffsu.org/my-edc/

#aiagents #ai #automation

Deploy your site using here.now completely for free, copy the prompt for your agent here! https://here.now/r/twt

In this complete guide, I walk you through the best local agentic coding workflow using LM Studio and VS Code - no API keys, no cloud, no cost per token.You'll learn how to install and configure LM Studio, choose and run the right local models for coding, and connect everything to VS Code so you can use AI-powered agents directly in your editor. This is the exact setup I use for local AI coding that actually works.

Want to make real money with coding? I share high-signal insights on careers, monetization, and leverage in my free newsletter. Join here and get my guide How to Make Money With Coding instantly: https://techwithtim.net/newsletter

🚀 Tools I Use
Get 10% off with code techwithtim
Openclaw setup: https://www.hostinger.com/techwithtim
VPS setup: https://www.hostinger.com/techwithtim10
Wispr Flow (Best AI Dictation): https://ref.wisprflow.ai/TechWithTim-jun26

🎞 Video Resources 🎞
Presentation in This Video: https://clever-mirage-d82v.here.now/
LM Studio Download: https://lmstudio.ai/
VSCode Download: https://code.visualstudio.com/

⏳ Timestamps ⏳
00:00 | Overview
00:46 | What are Local Models
02:30 | VRAM & Computer Hardware
05:18 | Memory & Model Speed
06:39 | How to Pick a Model
11:10 | Trying It Live
12:23 | LM Studio Setup & Model Download
22:15 | Using Local Models in VS Code
28:43 | Autocomplete Model Setup

Hashtags
#LMStudio #AICoding #AIDevTools

UAE Media License Number: 3635141

Code link: https://github.com/krishnaik06..../Agentic-LanggraphCr
LangGraph is built for developers who want to build powerful, adaptable AI agents. Developers choose LangGraph for:

Reliability and controllability. Steer agent actions with moderation checks and human-in-the-loop approvals. LangGraph persists context for long-running workflows, keeping your agents on course.
Low-level and extensible. Build custom agents with fully descriptive, low-level primitives free from rigid abstractions that limit customization. Design scalable multi-agent systems, with each agent serving a specific role tailored to your use case.
First-class streaming support. With token-by-token streaming and streaming of intermediate steps, LangGraph gives users clear visibility into agent reasoning and actions as they unfold in real time.
Learn LangGraph basics¶
To get acquainted with LangGraph's key concepts and features, complete the following LangGraph basics tutorials series:

Build a basic chatbot
Add tools
Add memory
Add human-in-the-loop controls
Customize state
Time travel

Timestamp:

00:00:00 Introduction And Agenda
00:03:37 Langgraph Projects Structure
00:11:15 Building Blocks Of LAnggraph
00:23:47 Building a Basic Chatbot
00:49:05 Building Chatbot With Tools
01:18:37 ReACT Agent Architecture
01:26:22 Adding Memory In Langgraph
01:35:00 Streaming In Langgraph
01:44:58 Human Feedback In the loop
01:52:42 MCP Server Scratch Implementation

Avengers eg but only best moments 4k 60fps

Shop Marvel DC Apparel: https://bit.ly/3zKaSYP
Extra 5% Off Discount Code: mewtwo




Ultra HD 4k 2160p
FULL HD 60FPS
Marvel
Film HD 60FPS

Complete Agentic AI Course - AI Agents, RAG, Embeddings, Architectures, Framework, VectorDB & Memory #aiagents #agenticai #aiforbeginners #learnai #ai #2026

Join Our Discord Server :- https://discord.gg/2abyjxr4v6

🤖 Learn Agentic AI — AI Agents Explained (A Complete Powerful Course to Master It)

This is the most comprehensive Agentic AI course you'll find — completely FREE. We go from the absolute ground up — AI basics, LLMs, the Agent loop — all the way to Vector Databases, RAG, MCP, Multi-Agent Systems, and real architectures being used in production RIGHT NOW in 2026.

Whether you're a total beginner or someone who's used AI tools but never truly understood them — this video is built for you.

📌 WHAT YOU'LL LEARN IN THIS VIDEO:

✅ What AI actually is — and the 3 eras that brought us here
✅ How Transformers & the Attention Mechanism changed everything (2017 → now)
✅ How LLMs generate text — tokens, temperature, and context windows explained
✅ The EXACT difference between a Chatbot and a true AI Agent
✅ The Core Agent Loop (Perceive → Think → Act → Observe) broken down simply
✅ The ReAct Pattern — how agents reason before every single action
✅ Tools & Function Calling — how agents interact with the real world
✅ Memory systems — Sensory, Working, Episodic, and Semantic memory
✅ RAG (Retrieval-Augmented Generation) — the most important AI dev concept right now
✅ Vector Databases — Pinecone, Weaviate, Qdrant, Chroma & when to use each
✅ Embeddings & Semantic Search — the math made simple
✅ MCP (Model Context Protocol) — the "USB port" for AI, explained clearly
✅ 6 Agentic Architectures — ReAct, Chain-of-Thought, Plan-and-Execute, Tree of Thoughts, Reflexion & LATS
✅ Multi-Agent Systems — Orchestrator-Worker, Parallel, Debate Pattern & more
✅ Frameworks — LangChain, LlamaIndex, AutoGen, CrewAI
✅ Advanced patterns — Self-Modifying Agents, Stochastic Consensus, Iceberg Technique, 60-30-10 Cost Rule
✅ Safety & Guardrails — Prompt Injection, Scope Creep, Human-in-the-Loop & more
✅ Real-world use cases across Enterprise, Healthcare, Finance, Education & Dev
✅ A step-by-step 10-week roadmap to go from zero to building production agents

💡 Key Insight:

A chatbot reacts. An AI Agent plans, decides, acts, and adapts — all on its own. Understanding that difference is worth everything in today's AI landscape.

Related Topics :-

Agentic AI, AI agents explained, how AI agents work, what is an AI agent, AI agents 2026, learn AI agents, build AI agents, agentic AI course for beginners, AI agents for beginners, master AI agents, complete agentic AI course, AI Fundamentals, LLMs explained, AI agent loops, AI memory systems, AI tools, RAG explained, vector databases explained, Embeddings explained, MCP explained, AI architecture patterns, agentic architecture, AI frameworks and advanced patterns, multi-agent systems, AI safety, AI guardrails, tejas ai, tejas_aiz, ai 2026, 2026 etc.

- Tejas AI

Try out Junie: https://jb.gg/JunieAI-coding

AI is alright if you have a brain. AI can give good sloppy.

This video is sponsored by JetBrains.

// USEFUL AI RESOURCES //
MCPs: https://mcpmarket.com/server
AGENTS.MD: https://agents.md/#examples
Claude prompting best practices: https://platform.claude.com/do....cs/en/build-with-cla
OpenAI prompting best practices: https://help.openai.com/en/art....icles/6654000-best-p

// NEWSLETTER //
Sloth Bytes: https://slothbytes.beehiiv.com/subscribe

// BUSINESS INQUIRIES //
For business: [email protected]
For brand partnerships: https://tally.so/r/mZVvKa

// SOCIALS //
Twitter: https://twitter.com/TheCodingSloth1
TikTok: https://www.tiktok.com/@thecodingsloth
Discord: https://discord.gg/2ByMHqTNca

// TOOLS/THINGS I REALLY LIKE //
If you wanna build 10x developer level projects check out CodeCrafters (40% off):
https://app.codecrafters.io/jo....in?via=TheCodingSlot
If you want to build an awesome newsletter like Sloth Bytes I use beehiiv (20% off):
https://www.beehiiv.com?via=the-coding-sloth

(some of these links are affiliates, so I'll earn some money which supports the channel!)

Learn the essential AI concepts and basics. We will cover theory and also go over code for building agents. We will cover both no-code tools (Zapier, N8N) and coding frameworks (langchain etc.) for building agents.


Code and assignment: https://resources.codebasics.io/GPpiop

Build your first agent using Zapier: https://youtu.be/Jekzc6BM5_w?si=tHrbHGBPJ8mmJqZv

Air canada chatbot case: https://www.forbes.com/sites/m....arisagarcia/2024/02/

Codebasics AI engineering cohort: https://resources.codebasics.io/RjnPLS

⭐️ Timestamps ⭐️
0:00 Intro
1:01 What is an AI Agent?
7:48 ReAct Loop
8:19 Multi-Agent System
9:07 Multimodal Agent
10:02 Two ways of creating agents
12:30 Workflow vs Agents
13:37 Autonomy and Guardrails
16:12 Evaluation
19:38 Assignment PDF

Do you want to learn technology from me? Check https://codebasics.io/?utm_source=description&utm_medium=yt&utm_campaign=description&utm_id=description for my affordable video courses.

Need help building software or data analytics/AI solutions? My company https://www.atliq.com/ can help. Click on the Contact button on that website.

🎥 Codebasics Hindi channel: https://www.youtube.com/channe....l/UCTmFBhuhMibVoSfYo

#️⃣ Social Media #️⃣

🧑‍🤝‍🧑 Discord for Community Support: https://discord.gg/r42Kbuk
📸 Codebasics' Instagram: https://www.instagram.com/codebasicshub/
📝 Codebasics' Linkedin : https://www.linkedin.com/company/codebasics/
📱 Dhaval's X handle : https://x.com/dpcodebasics

------

📝 Dhaval's Linkedin : https://www.linkedin.com/in/dhavalsays/
📝 Hem's Linkedin: https://www.linkedin.com/in/hemvad/

📽️ Hem's Instagram for daily tips: https://www.instagram.com/hemvadivel/
📸 Dhaval's Personal Instagram: https://www.instagram.com/dhavalcodebasics

🔗 Patreon: https://www.patreon.com/codeba....sics?fan_landing=tru

Learn more: https://stanford.io/4iHlGQp

Build modern AI agents with Stanford's graduate-level curriculum, adapted for working professionals.

Taught by Stanford Adjunct Professor Chowdhery and Assistant Professor Mirhoseini, this Agentic AI program takes you beyond basic LLM prompting to agents that reason, plan, use tools, and improve themselves through interaction with their environment.

What you'll learn:
- Design agentic systems for complex, multi-step real-world tasks
- Apply test-time scaling to boost LLM performance
- Use self-improvement methods: verifiers, feedback loops, RL, and search
- Build agents that use tools and take actions effectively
- Add retrieval and long-term memory to LLMs
- Develop planning and multi-step reasoning
- Evaluate agent performance with robust frameworks

Drawing on Stanford research and the latest advances in the field.

About the Instructors
Stanford Engineering Adjunct Professor Dr. Aakanksha Chowdhery led end-to-end training of the 540B PaLM model (the largest densely trained language model in the world at the time) and drove pre-training and scaling of Gemini's mixture-of-experts models. Stanford Assistant Professor Azalia Mirhoseini co-developed the MoE architectures now used in nearly every frontier model, created AlphaChip (the RL method behind Google's TPU designs), and pioneered LLM test-time scaling; she worked on both Claude and Gemini.

Welcome to chai aur code, a coding/programming dedicated channel in Hindi language. Now you can learn best of programming concepts with industry standard practical guide in Hindi language.

All source code is available at my Github account:
https://github.com/hiteshchoudhary

Our Open-Source Project is here: https://freeapi.app

Join me at whatsapp: https://hitesh.ai/whatsapp

for community discord: https://hitesh.ai/discord

Instagram pe yaha paaye jaate h:
https://www.instagram.com/hiteshchoudharyofficial/

HTML video series: https://www.youtube.com/watch?v=XmLOwJHFHf0&list=PLu71SKxNbfoDBNF5s-WH6aLbthSEIMhMI

Complete javascript series: https://www.youtube.com/watch?v=Hr5iLG7sUa0&list=PLu71SKxNbfoBuX3f4EOACle2y-tRC5Q37

Complete Reactjs series: https://www.youtube.com/watch?v=vz1RlUyrc3w&list=PLu71SKxNbfoDqgPchmvIsL4hTnJIrtige

Javascript and react interview series: https://www.youtube.com/watch?v=1wqCyz7XrV4&list=PLu71SKxNbfoCy_MsA98SBfvUKF5eQit6L

Backend development with Javascript: https://www.youtube.com/watch?v=EH3vGeqeIAo&list=PLu71SKxNbfoBGh_8p_NS-ZAh6v7HhYqHW

Python Series: https://www.youtube.com/watch?v=Ca5DLSDfPec&list=PLu71SKxNbfoBsMugTFALhdLlZ5VOqCg2s

Checkout the roadmap: https://www.krishnaik.in/ai-roadmaps
Agentic AI involves creating autonomous systems that use Large Language Models (LLMs) to plan, reason, and act to achieve goals, rather than just generating content. To learn this, focus on mastering frameworks like LangGraph, CrewAI, and AutoGen to build multi-agent workflows, and focus on agentic RAG for data access. Key skills include planning, tool usage, and human-in-the-loop interaction.
----------------------------------------------------------------------------------
Learn from me and my team
visit : https://krishnaik.in/liveclasses

Ready to become a certified watsonx AI Assistant Engineer? Register now and use code IBMTechYT20 for 20% off of your exam → https://ibm.biz/BdbhXe

Learn more about Agentic AI here → https://ibm.biz/BdbhXb

Ever hit a wall with your biggest LLM? 🚧 Shad Griffin shows how Agentic AI, AI agents, and prompt engineering turn complex problems into smart, multi‑step solutions powered by machine learning. Discover how this workflow helps developers build more accurate AI results.

AI news moves fast. Sign up for a monthly newsletter for AI updates from IBM → https://ibm.biz/BdbLhV

#agenticai #llm #aiagents #promptengineering #machinelearning

Learn more about AI Code-Generation Software here → https://ibm.biz/BdpBwX

Is AI-assisted coding the future? 🤔 Cedric Clyburn explores spec-driven development, a game-changing approach that combines LLMs with software development best practices. Learn how it differs from vibe coding, integrates SDLC principles, and improves coding workflows with requirements-driven precision. 🚀

AI news moves fast. Sign up for a monthly newsletter for AI updates from IBM → https://ibm.biz/BdpBwH

#aicoding #llms #aiassisted