Loading...
Loading...
Part of the bootcamp
Advanced Design Patterns in AI Agents is one workshop inside AI Bootcamp for Software Engineers.
See the full path with mentor reviews and a portfolio outcome.
Stop reinventing the wheel. Get the definitive catalog of battle-tested agent architectures, from basic prompt chaining to metacognitive reasoning loops.
Engineers are learning here from
The most comprehensive collection of AI agent design patterns available online. Prompt chaining, parallelization, multi-agent coordination, RAG pipelines, safety guardrails, metacognitive reasoning, each with production-ready Python code you can ship.
Battle-tested agent patterns. The reference guide that didn't exist until now.
What you'll ship
What you'll learn
Curriculum
Welcome & foundations
Get started with AI agentic patterns, set up your environment, and learn the foundational patterns: prompt chaining and routing.
Parallel processing & Self-improvement
Run tasks simultaneously for speed, reflect on outputs, and integrate external tools into your agents.
Planning & Multi-agent systems
Decompose complex goals into plans, coordinate multiple specialized agents, and manage conversation memory.
Integration & protocol patterns
Connect to external services via MCP, set and monitor goals, handle exceptions gracefully, and incorporate human oversight.
Knowledge & communication
Retrieve external knowledge with RAG, enable agents to communicate, and optimize resource usage.
Reasoning patterns
Master chain-of-thought reasoning, self-correction, and structured problem decomposition.
Safety, quality & management
Implement guardrails, evaluate outputs with LLM-as-judge, monitor performance, prioritize tasks, and explore new topics.
System architecture patterns
Take a mid-course assessment, then build agentic RAG systems, orchestrate workflows, compose subgraphs, manage state machines, and create recursive agents.
RAG pipeline patterns
Execute code safely, rewrite queries for better retrieval, check relevancy, and process data for RAG pipelines.
Advanced architectures
Master Plan-Execute patterns, ReAct loops, blackboard systems, and dual memory architectures.
Frontier reasoning patterns
Explore advanced patterns: Tree of Thoughts branching, mental simulation, meta-controller orchestration, and graph-based knowledge memory.
Self-improvement & capstone
Build self-improving agents with RLHF and metacognition, then bring everything together in a capstone multi-pattern pipeline.
Who it's for
You build agents but pick architectures based on vibes, not knowledge.
You're tired of scattered blog posts. You want one definitive reference.
You're designing AI systems and need patterns you can trust in production.
FAQ
Not at all. It's intermediate. You should know basic LLM concepts and Python. Building AI Agents is a great warmup.
Every single one. Code, explanation, and when to use it.
Yes. LiteLLM makes them provider-agnostic.
Building AI Agents teaches fundamentals from zero. This one is a pattern catalog for when you already know the basics and need the playbook.
Battle-tested agent patterns. The reference guide that didn't exist until now.