Blaize D'souza ❤️ (@blaizedsouza) 's Twitter Profile
Blaize D'souza ❤️

@blaizedsouza

technologist | distributed systems | reactive systems | edge computing | ml | ai | agentic computing | multi-cloud | k8s | embedded systems | iot

ID: 48144253

calendar_today17-06-2009 22:33:39

86,86K Tweet

3,3K Followers

5,5K Following

Dr Milan Milanović (@milan_milanovic) 's Twitter Profile Photo

𝗪𝗵𝗮𝘁 𝗶𝘀 𝗗𝗼𝗺𝗮𝗶𝗻-𝗗𝗿𝗶𝘃𝗲𝗻 𝗗𝗲𝘀𝗶𝗴𝗻? Domain-Driven Design (DDD) is the approach to software development that enables us to translate complex problem domains into rich, expressive, and evolving software. It's how we design applications when the needs of our users

𝗪𝗵𝗮𝘁 𝗶𝘀 𝗗𝗼𝗺𝗮𝗶𝗻-𝗗𝗿𝗶𝘃𝗲𝗻 𝗗𝗲𝘀𝗶𝗴𝗻?

Domain-Driven Design (DDD) is the approach to software development that enables us to translate complex problem domains into rich, expressive, and evolving software. It's how we design applications when the needs of our users
Femke Plantinga (@femke_plantinga) 's Twitter Profile Photo

Your RAG system just failed another complex query. The issue isn't your embeddings or vector database - it's that traditional RAG treats every document chunk like it exists in a vacuum. Graph RAG solves this. Let’s break it down: 𝗡𝗮𝗶𝘃𝗲 𝗥𝗔𝗚 𝗣𝗶𝗽𝗲𝗹𝗶𝗻𝗲: 1. User

Your RAG system just failed another complex query.

The issue isn't your embeddings or vector database - it's that traditional RAG treats every document chunk like it exists in a vacuum.

Graph RAG solves this. Let’s break it down:

𝗡𝗮𝗶𝘃𝗲 𝗥𝗔𝗚 𝗣𝗶𝗽𝗲𝗹𝗶𝗻𝗲:
1. User
Nikki Siapno (@nikkisiapno) 's Twitter Profile Photo

Kafka vs AutoMQ — What's the difference? Kafka operates as a distributed pub-sub messaging system. Allowing applications to publish and subscribe to real-time data feeds. Its strengths? High throughput, scalability, fault-tolerance, and a mature ecosystem. But Kafka is also

Kafka vs AutoMQ — What's the difference?

Kafka operates as a distributed pub-sub messaging system. Allowing applications to publish and subscribe to real-time data feeds.

Its strengths? High throughput, scalability, fault-tolerance, and a mature ecosystem.

But Kafka is also
Chris Laub (@chrislaubwrites) 's Twitter Profile Photo

Everyone talks about AI “memory,” but nobody defines it. This paper finally does. It categorizes LLM memory the same way we do for humans: • Sensory • Working • Long-term Then shows how each part works in GPTs, agents, and tools. Here's everything you need to know:

Everyone talks about AI “memory,” but nobody defines it.

This paper finally does.

It categorizes LLM memory the same way we do for humans:

• Sensory
• Working
• Long-term

Then shows how each part works in GPTs, agents, and tools.

Here's everything you need to know:
Sumanth (@sumanth_077) 's Twitter Profile Photo

All-in-One RAG System! RAG-Anything is a unified framework with a multi-stage multimodal pipeline that extends traditional RAG architectures. It handles diverse content through intelligent orchestration and cross-modal understanding. 100% Open Source

All-in-One RAG System!

RAG-Anything is a unified framework with a multi-stage multimodal pipeline that extends traditional RAG architectures.

It handles diverse content through intelligent orchestration and cross-modal understanding.

100% Open Source
Maryam Miradi, PhD (@maryammiradi) 's Twitter Profile Photo

🛠️🧭 How to Build MCP AI Agents from Scratch – Even If You’ve Never Used MCP Before 𝗧𝗵𝗶𝘀 𝗶𝘀 𝗮 𝟵-𝗦𝘁𝗲𝗽 𝗿𝗼𝗮𝗱𝗺𝗮𝗽 𝗳𝗿𝗼𝗺 𝗹𝗼𝗰𝗮𝗹 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝘁𝗼 𝗿𝗲𝘂𝘀𝗮𝗯𝗹𝗲 𝗔𝗜 𝗔𝗽𝗽𝘀. 》Step 1: Define the Tool’s Goal and Context ✸ What does the tool solve?

🛠️🧭 How to Build MCP AI Agents from Scratch – Even If You’ve Never Used MCP Before
𝗧𝗵𝗶𝘀 𝗶𝘀 𝗮 𝟵-𝗦𝘁𝗲𝗽 𝗿𝗼𝗮𝗱𝗺𝗮𝗽 𝗳𝗿𝗼𝗺 𝗹𝗼𝗰𝗮𝗹 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝘁𝗼 𝗿𝗲𝘂𝘀𝗮𝗯𝗹𝗲 𝗔𝗜 𝗔𝗽𝗽𝘀.

》Step 1: Define the Tool’s Goal and Context
 ✸ What does the tool solve?
Aurimas Griciūnas (@aurimas_gr) 's Twitter Profile Photo

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

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
Andrew Ng (@andrewyng) 's Twitter Profile Photo

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by @Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to

Paweł Huryn (@pawelhuryn) 's Twitter Profile Photo

AI Evals are critical for AI PMs and Engineers. But many still confuse them with unit tests. By popular request, I removed a paywall from the Hamel Husain's Mastering AI Evals, A Complete Guide. Key insights, free guide, and massive resources: 🧵

AI Evals are critical for AI PMs and Engineers.
But many still confuse them with unit tests.

By popular request, I removed a paywall from the <a href="/HamelHusain/">Hamel Husain</a>'s Mastering AI Evals, A Complete Guide.

Key insights, free guide, and massive resources: 🧵
elvis (@omarsar0) 's Twitter Profile Photo

Don't sleep on small models! Anemoi is the latest multi-agent system that proves small models pack a punch when combined effectively. GPT-4.1-mini (for planning) and GPT-4o (for worker agents) surpass the strongest open-source baseline on GAIA. A must-read for devs:

Don't sleep on small models!

Anemoi is the latest multi-agent system that proves small models pack a punch when combined effectively.

GPT-4.1-mini (for planning) and GPT-4o (for worker agents) surpass the strongest open-source baseline on GAIA.

A must-read for devs:
Aurimas Griciūnas (@aurimas_gr) 's Twitter Profile Photo

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

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