Farid
Deploy open-source LLMs on AWS EC2 and build real AI agents with Ollama, Qwen2.5& ServiceNow, Totally hands-on Course
What you’ll learn
Host Local LLM Qwen2.5 on your Laptop or EC2 Server
Use Ollama to manage LLM
Create your own agents
ServiceNow integration, MCP
Requirements
Aware about python programming and LLM eco-systems
Description This course contains the use of artificial intelligence. AI tools were used to assist in creating some course materials, including visuals, written content, and code examples. All content has been reviewed and curated by the instructor to ensure accuracy and quality.
Want to move beyond ChatGPT prompts and actually build and deploy your own AI systems? This hands-on course teaches you how to run open-source Large Language Models (LLMs) on your own infrastructure and turn them into working AI agents that take real actions.
You’ll start by deploying an open-source LLM – Qwen2.5 – on an AWS EC2 instance using Ollama, learning how to configure the server, connect to it securely from your local machine, and test connectivity end to end. No expensive GPUs or paid APIs required to follow along.
From there, you’ll learn the core concepts of AI agents: the difference between an agent and a tool, how an LLM decides which tool to call, and how to build a decision-making loop in plain Python. You’ll create practical tools and see the agent choose between them based on user input.
Finally, you’ll take it into the enterprise world by integrating your agent with ServiceNow – building an IT support triage agent that analyzes issues, suggests resolutions, and automatically creates incidents when needed.
By the end, you’ll understand LLM deployment, agent architecture, tool integration, and real enterprise automation. Whether you’re a developer, an IT professional, or an aspiring AI engineer, you’ll leave with practical skills and working code you can adapt to your own projects.
Enroll now and start building AI systems that actually do things.
Who this course is for
Most AI courses send your data – and your money – to a cloud API. This one doesn’t. You’ll run a real large language model, Qwen2.5, entirely on your own laptop using Ollama, with no per-token cost and no data ever leaving your machine. Then you’ll turn that model into a working **AI agent** that does something genuinely useful for IT teams: it takes a user’s problem, reasons about it, suggests a step-by-step fix, and – only if the user rejects that fix – automatically raises an incident in ServiceNow through the Table API. By the end, you won’t just understand agentic AI in theory. You’ll have built one, end to end, from an empty laptop to a live ServiceNow incident.
Udemy Learn To Host Your Own LLM And Build Agent
🔗RapidGator
https://rapidgator.net/file/9a2f6cc97ccb131c07caed13b762e11a/Udemy.Learn.To.Host.Your.Own.LLM.And.Build.Agent.rar
🔗NitroFlare
https://nitroflare.com/view/B5D91B95E9453C9/Udemy.Learn.To.Host.Your.Own.LLM.And.Build.Agent.rar
?referrer=1635666
