Some 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 might seem simple from the outside. They are not 👇 Here are some of the layers that are hidden from you as a user of agentic We usually start building and experimenting with Raw Model APIs. These rely on complex underlying infrastructure. 𝟭.

🔥 Want to automate chunk context-augmentation? Forget Late Embeddings and Contextual Retrieval - Good news, 𝗖𝗼𝗻𝘁𝗲𝘅𝘁𝘂𝗮𝗹𝗶𝘇𝗲𝗱 𝗖𝗵𝘂𝗻𝗸 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 are here! MongoDB has just announced voyage-context-3: a contextualized chunk embedding model. Check it out

Fundamentals of a 𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲. 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.

What I love about 𝗴𝗽𝘁-𝟱 𝗽𝗿𝗼𝗺𝗽𝘁𝗶𝗻𝗴 𝗿𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗮𝘁𝗶𝗼𝗻𝘀 👇 There is mostly one thing, but it is big: ✅ XML is back! In previous versions (gpt-4.1), the use of Markdown in your prompts was still pushed as the best way to structure your prompts and

The 𝗳𝗶𝗿𝘀𝘁 𝗰𝗼𝗵𝗼𝗿𝘁 of my 𝗘𝗻𝗱-𝘁𝗼-𝗘𝗻𝗱 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝗕𝗼𝗼𝘁𝗰𝗮𝗺𝗽 𝗶𝘀 𝗮 𝘄𝗿𝗮𝗽 and it was a blast! 👇 My mission has always been to Level Up the next generation of AI talent. This bootcamp is the largest effort in the direction so far and I

A breakdown of 𝗗𝗮𝘁𝗮 𝗣𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀 𝗶𝗻 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 👇 And yes, it can also be used for LLM based systems! It is critical to ensure Data Quality and Integrity upstream of ML Training and Inference Pipelines, trying to do that in the

𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 and what you need to know about it as an AI Engineer? Simple naive RAG systems are rarely used in real world applications. We are usually adding some agency to the RAG system - ideally a minimal amount. There is 𝗻𝗼 𝘀𝗶𝗻𝗴𝗹𝗲 𝗯𝗹𝘂𝗲𝗽𝗿𝗶𝗻𝘁 on how

The moat around your tech is shrinking. In enterprise AI, buyers aren’t sold on hype. They’re running bake-offs. You’re benchmarked against 10 others, and the winner is the one that’s secure, fast, feature-rich, and enterprise-ready. “No one will pay just because you’re a known

Less talking, more building: 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗦𝘆𝘀𝘁𝗲𝗺 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵! 👇 Some weeks ago I released an episode of my Newsletter and an update to the 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 𝗛𝗮𝗻𝗱𝗯𝗼𝗼𝗸 GitHub repository. There I implemented a Deep

My latest Newsletter episode on 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 👇 This week I wrote down my thoughts and experiences about the practice in my latest Newsletter episode. In general, Context provided to LLMs in Agentic Systems can be split into the following categories:

The main 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗗𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁 𝗧𝘆𝗽𝗲𝘀 👇 It’s no secret that an AI Agent is a piece of software wrapping an LLM or multiple LLMs as a reasoning engine to guide its execution flow. The deployment types for these agents also closely resemble those of software or