Aurimas Griciลซnas
@Aurimas_Gr
๐จ Founder & CEO @ SwirlAI ๐ Writing about #LLM, #AI, #DataEngineering, #MachineLearning and #Data โ๏ธ Author of SwirlAI Newsletter.
Last week I released the first article in my hands-on ๐๐๐ถ๐น๐ฑ๐ถ๐ป๐ด ๐๐ ๐๐ด๐ฒ๐ป๐๐ ๐๐ฟ๐ผ๐บ ๐ฆ๐ฐ๐ฟ๐ฎ๐๐ฐ๐ต series. It covers the tool use element of an Agent. I wanted to do this for quite some time now and finally the time has arrived! If you are using any orchestrationโฆ
๐๐๐ฎ๐น๐๐ฎ๐๐ถ๐ผ๐ป ๐๐ฟ๐ถ๐๐ฒ๐ป ๐๐ฒ๐๐ฒ๐น๐ผ๐ฝ๐บ๐ฒ๐ป๐ is the only way how you can be successful in building your ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐ฆ๐๐๐๐ฒ๐บ๐ - here is my template ๐ I have been developing Agentic Systems for more than two years now. The same patterns keep emerging. Today,โฆ
Fundamentals of a ๐ฉ๐ฒ๐ฐ๐๐ผ๐ฟ ๐๐ฎ๐๐ฎ๐ฏ๐ฎ๐๐ฒ. With the rise of GenAI, Vector Databases skyrocketed in popularity. The truth - Vector Databases are also useful outside of a Large Language Model context. When it comes to Machine Learning, we often deal with Vector Embeddings.โฆ
๐ ๐๐ฃ plus ๐๐ฎ๐, here is how they complement each other ๐ Protocol wars continue to rage, let's understand how Googles A2A (Agent2Agent) protocol is different from MCP and how they complement each other (read till the end). ๐๐ฐ๐ท๐ช๐ฏ๐จ ๐ฑ๐ช๐ฆ๐ค๐ฆ๐ด ๐ช๐ฏ ๐๐๐: ๐ญ. MCPโฆ
MLOps 101: ๐๐ผ๐ป๐๐ถ๐ป๐๐ผ๐๐ ๐ง๐ฟ๐ฎ๐ถ๐ป๐ถ๐ป๐ด (๐๐ง) and what steps are needed to achieve it. CT is the process of automated ML Model retraining in Production Environments on a specific trigger. Letโs look into some prerequisites for this: 1) Automation of ML Pipelines. -โฆ
Adding ๐ ๐๐ฃ to ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐ฅ๐๐ Systems. If you are building RAG systems and packing many data sources for retrieval, most likely there is some agency present at least at the data source selection for retrieval stage. This is how MCP enriches the evolution of yourโฆ
Fusion of ๐ฅ๐๐ (Retrieval Augmented Generation) and ๐๐๐ (Cache Augmented Generation). How can you benefit from it as AI Engineer? Few months ago there was a lot of hype around a technique called CAG. While it is powerful to its own extent, the real magic happens when youโฆ
You must know these ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐ฆ๐๐๐๐ฒ๐บ ๐ช๐ผ๐ฟ๐ธ๐ณ๐น๐ผ๐ ๐ฃ๐ฎ๐๐๐ฒ๐ฟ๐ป๐ as an ๐๐ ๐๐ป๐ด๐ถ๐ป๐ฒ๐ฒ๐ฟ. If you are building Agentic Systems in an Enterprise setting you will soon discover that the simplest workflow patterns work the best and bring the most business value.โฆ
๐๐ ๐๐ด๐ฒ๐ป๐ ๐ ๐ฒ๐บ๐ผ๐ฟ๐ explained in a simple way ๐ In general, the memory for an agent is something that we provide via context in the prompt passed to LLM that helps the agent to better plan and react given past interactions or data not immediately available. It isโฆ
Building even a simple ๐ฝ๐ฟ๐ผ๐ฑ๐๐ฐ๐๐ถ๐ผ๐ป ๐ด๐ฟ๐ฎ๐ฑ๐ฒ ๐ฅ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น ๐๐๐ด๐บ๐ฒ๐ป๐๐ฒ๐ฑ ๐๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐๐ถ๐ผ๐ป (๐ฅ๐๐) ๐ฏ๐ฎ๐๐ฒ๐ฑ ๐๐ ๐๐๐๐๐ฒ๐บ is a challenging task. Read until the end to understand why ๐ Here are some of the moving parts in the RAG based systems thatโฆ
What does an ๐๐ณ๐ณ๐ฒ๐ฐ๐๐ถ๐๐ฒ ๐ ๐ฎ๐ฐ๐ต๐ถ๐ป๐ฒ ๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด ๐๐ ๐ฝ๐ฒ๐ฟ๐ถ๐บ๐ฒ๐ป๐๐ฎ๐๐ถ๐ผ๐ป ๐๐ป๐๐ถ๐ฟ๐ผ๐ป๐บ๐ฒ๐ป๐ look like? MLOps practices are there to improve Machine Learning Product development velocity, the biggest bottlenecks happen when Experimentation Environmentsโฆ
๐๐ฎ๐๐ฎ ๐ฃ๐ถ๐ฝ๐ฒ๐น๐ถ๐ป๐ฒ๐ ๐ถ๐ป ๐ ๐ฎ๐ฐ๐ต๐ถ๐ป๐ฒ ๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด ๐ฆ๐๐๐๐ฒ๐บ๐ can become complex and for a good reason ๐ It is critical to ensure Data Quality and Integrity upstream of ML Training and Inference Pipelines, trying to do that in the downstream systems will causeโฆ
Some ๐๐ ๐๐ด๐ฒ๐ป๐๐ might seem simple from the outside. They are not ๐ In my latest Newsletter episode I describe the ๐๐ป๐๐ฒ๐ฟ๐ฝ๐ฟ๐ถ๐๐ฒ ๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐๐ ๐๐ถ๐ฒ๐ฟ๐ฎ๐ฟ๐ฐ๐ต๐ ๐ผ๐ณ ๐ก๐ฒ๐ฒ๐ฑ๐ framework. You can find the deep dive here: newsletter.swirlai.com/p/enterprise-aโฆ On a highโฆ