Back to Courses
Intermediate 4 weeks 3 sessions/week

Advanced Prompt Engineering & AI Agents

Go far beyond basic prompts. Build RAG pipelines, AI agents with tool use, multi-agent systems, and deploy production-ready AI applications that solve real business problems.

£1,997 per person

What You'll Learn

01

Chain-of-Thought Prompting

Master advanced reasoning techniques that dramatically improve LLM output quality. Step-by-step reasoning, self-consistency, tree-of-thought, and structured output generation.

02

Few-Shot Learning

Teach LLMs new tasks with just a few examples. Design effective example sets, understand in-context learning, and build reliable classification and extraction systems.

03

RAG Pipelines

Build Retrieval-Augmented Generation systems from scratch. Document ingestion, chunking strategies, embedding models, vector search, and context injection for grounded AI responses.

04

LangChain & LlamaIndex

Master the two leading frameworks for building LLM applications. Chains, agents, tools, memory, document loaders, and index structures for production systems.

05

Building AI Agents

Create autonomous AI agents that can reason, plan, and take actions. ReAct pattern, tool use, function calling, and agent architectures that solve complex multi-step problems.

06

Tool Use & Function Calling

Connect LLMs to external APIs, databases, and services. Structured function calling, parameter validation, error handling, and building reliable AI-powered integrations.

07

Multi-Agent Systems

Orchestrate multiple AI agents that collaborate to solve complex problems. Agent communication protocols, task decomposition, supervisor patterns, and crew-based architectures.

08

Production Deployment

Deploy your AI applications to production. API design, caching strategies, cost optimisation, monitoring, evaluation frameworks, and handling edge cases at scale.

Who Is This For

Developers and engineers who want to build production AI applications beyond simple chatbots

Technical professionals with basic AI understanding who want to master the agent and RAG ecosystem

Product managers and technical leads evaluating AI agent architectures for their teams

Prerequisites

Basic AI understanding required. You should be comfortable with what LLMs are, have used ChatGPT or similar tools, and ideally have basic Python skills. Our Generative AI Essentials or AI Fundamentals course provides perfect preparation.

Course Format

Live Online Sessions

Interactive sessions with real-time Q&A and screen sharing

Recorded Replays

All sessions recorded and available for 12 months after the course

Hands-on Projects

Real-world projects that build your portfolio as you learn

1-on-1 Mentoring

Personal mentoring sessions to address your specific questions

Certificate of Completion

Industry-recognised certificate upon successful completion

Schedule & Pricing

£1,997
4 weeks · 3 sessions per week · 12 sessions total
  • Live interactive sessions
  • 12-month replay access
  • 1-on-1 mentoring
  • Certificate included
Enrol Now

Your Instructors

PP

PeusoPeupon Expert Team

Our instructors are seasoned practitioners with years of experience building production AI systems. They hold certifications across major cloud platforms and have trained thousands of professionals worldwide.

Frequently Asked Questions

Generative AI Essentials is for beginners learning to use AI tools. This course is for builders -- you will write code, build RAG systems, create AI agents, and deploy production applications. It is a significant step up in depth and complexity.

Primarily Python. You should be comfortable reading and writing basic Python code. We use LangChain, LlamaIndex, and various LLM APIs throughout the course.

Yes. By the end of the course you will have built a full RAG application, a multi-tool AI agent, and a multi-agent system -- all deployable to production. These make excellent portfolio pieces.

We work with OpenAI (GPT-4), Anthropic (Claude), and open-source models. You will learn to switch between providers and choose the right model for each use case.