Building Agentic and Multi-Agent Systems with LangGrap
People and companies in 2024 aim to build ever more complex and performant LLM applications. Leveraging context (e.g., Retrieval Augmented Generation, or RAG), reasoning, and access to external tools or functions (Agents), are front and center. For applications to leverage context well, they must provide useful input to the context window (e.g., [in-context learning](https://openai.com/index/language-models-are-few-shot-learners/)), through direct prompting (Prompt Engineering) or search and retrieval (RAG). To leverage reasoning is to leverage the Reasoning-Action ([ReAct](https://arxiv.org/abs/2210.03629)) pattern, and to be “agentic” or “agent-like.” Another way to think about agents is that they enhance search and retrieval through the intelligent use of tools or services.

Greg Loughnane
Co-Founder & CEO at AI Makerspace

Chris Alexiuk
Head of LLMs | Founding Machine Learning Engineer at AI Makerspace | Ox

Dozens of Free Courses with Premium
-
All Courses
ODSC 2025: 6-Week Winter AI Bootcamp
67 Lessons $499.00 -
All Courses, LLMs
ODSC AI Builders 2025 Summit - Mastering LLMs
36 Lessons $299.00 -
All Courses, AI Agents
ODSC AI Builders 2025 Summit - Mastering AI Agents
31 Lessons $299.00 -
All Courses, RAG
ODSC AI Builders 2025 Summit - Mastering RAG
26 Lessons $299.00 -
All Courses
ODSC West 2024 - All Recordings
34 Lessons $399.00 -
All Courses
Deep Learning Bootcamp with Dr. Jon Krohn
7 Lessons $699.00