Merge pull request #194 from mongodb-developer/update_workshops

Adding more workshops

Author: ajosh0504

workshops/README.md

@@ -4,11 +4,13 @@ We have designed a series of hands-on workshops to take you from zero to hero wi
 
 |Workshop name | Links | Description | Language | Tools used |
 |------------|-------------|----------------|-------------|-------------|
+| AI System Design: From Problem to Production | [Slides + Self-paced lab](https://docs.google.com/presentation/d/e/2PACX-1vRX8kToVjz8-5RqXWitL2znG9ar59cT51b7BuCLoSaNSolbdgRyOSuiDZGS2n83Bd2_ITkTWAfsGc2o/pub) | Learn a structured framework for making the decisions that get your AI systems to production. Apply the framework to a real-world problem as you go, leaving with a concrete system design and a repeatable process for taking AI applications from problem to production. | | |
 | Vector Search: Beginner to Pro | [Slides + Self-paced lab](https://docs.google.com/presentation/d/e/2PACX-1vR4lPTcr2ZXPTkQLPq3HtTn4vSLG4VrFD3jkOjXmEDrrvyLEElTaz-6JC5KZN4__VJZ2h13aTabGXhG/pub) | Learn vector search concepts such as embeddings, how vector search works in MongoDB, and also advanced concepts such as pre-filtering, vector quantization etc. Gain hands-on experience by building a multimodal vector search application for an online library. | Python | MongoDB Atlas, Voyage AI|
 | Building RAG Applications with MongoDB | [Slides + Self-paced lab](https://docs.google.com/presentation/d/e/2PACX-1vSN_7zZTqpXSmtUyDalox2kAoealuO4V_aVGqLuTuDKa3I3aJ9nQUdViQKasBNnu2zQVOpT5cubnyFd/pub) | Learn RAG concepts such as embedding, chunking and vector search. Gain hands-on experience by building a RAG-based chatbot for a technical documentation website. | Python | MongoDB Atlas, Voyage AI, Anthropic/Azure OpenAI/Gemini |
 | The A to Z of Building AI Agents | [Slides + Self-paced lab](https://docs.google.com/presentation/d/e/2PACX-1vRMH-7DLejrxrEgrReZTy4p9sKzN35uTaiDRZ8JAM9xtyLFz-utjJzk97FG8mGI96VEuLPnLZWzq10Q/pub) | Learn the core concepts of AI agents, such as reasoning, tools, and memory. Gain hands-on experience by buiding a technical documentation AI agent. | Python | MongoDB Atlas, Voyage AI, Anthropic/Azure OpenAI/Gemini, LangGraph |
 | Pragmatic LLM Application Development: From RAG Pipelines to AI Agents | [Hands-on Lab](https://github.com/mongodb-developer/GenAI-Showcase/blob/main/notebooks/agents/Pragmatic_LLM_Application_Introduction_From_RAG_to_Agents_with_MongoDB.ipynb) | Build RAG pipelines and AI agents with and without abstraction frameworks such as LangChain. Also introduces techniques such as prompt compression for optimizing LLM apps. | Python | MongoDB Atlas, OpenAI, LangChain, LLMLingua |
 | Building Multimodal AI Agents from Scratch | [Video](https://www.youtube.com/watch?v=640KMYtxCeI), [Hands-on Lab](https://github.com/mongodb-developer/multimodal-agents-lab) | Learn techniques to process multimodal data and build a multimodal AI agent from scratch, no abstractions involved. | Python | Voyage AI, MongoDB Atlas, Gemini |
+| Designing Memory Systems for AI Agents | [Slides + Self-paced lab](https://docs.google.com/presentation/d/e/2PACX-1vRDCCOi-p15tmvxUYZ1VeBl_1fMztfMSK8zeV6hfCMI7PNRLV2tbqJ2ImFC15Qhz-PnceHO7gyybhCO/pub) | Learn about the different types of memory in agentic systems, and patterns for storing, retrieving, updating and pruning memories. Gain hands-on experience by building a memory-augmented AI agent from scratch. | Python | Voyage AI, MongoDB |
 
 ## Questions?