Tag feed

#ai-engineering

366 posts3 followers

Explore Hashnode

Alternatives

Trending tags this week

MRMira royainetwork.hashnode.dev2d ago · 6 min read

A Reference Pattern for Logging and Auditing LLM API Calls

Most teams log application traffic. Far fewer can reconstruct exactly what happened when their application called an LLM three months ago. That distinction matters. If an auditor, security engineer, o

0

PKPeeyush Kumartheengineeringlab.hashnode.dev3d ago · 2 min read

Machine Learning Engineer vs Applied AI Engineer : The Smart Robot Analogy 🤖

We engineers love inventing new terms, and in this AI era, you have probably come across titles like Machine Learning Engineer and Applied AI Engineer. They may sound similar, but there is a simple wa

0

KLKrystin Limtheunscriptedk.hashnode.dev4d ago · 4 min read

How to scrape web content cleanly for LLM pipelines

I am Krystin, the non-technical co-founder of EnConvert. Most of what I know about RAG pipelines I learned from being in the room while engineers described what was breaking. Web content extraction co

1

O

HKHarshil Kumar Pindikuruharshils.hashnode.dev5d ago · 15 min read

Choosing the Right Rice: Understanding Foundation Models in Agentic AI

If you read the first article in this series, you saw the big picture of an agentic AI system. We looked at the kitchen as an architecture: Foundation models → Tools → Orchestration → Frameworks → RA

0

DDevcompassdevcompass.aiSep 25 · 34 min read

What Is a System One Model? Jev Explained

A System One model is an AI model designed to make fast, bounded decisions instead of generating text. Jev, developed by TypeSafe AI, is the first model TypeSafe has released in this category. Before

0

DBDigital BBbuildingblocksconsulting.hashnode.devSep 24 · 6 min read

AI Engineer vs AI Consultant: Which One Does Your Business Need?

A company can have a clear interest in AI without having a clear AI project. That creates a common hiring question: Should we bring in an AI consultant or an AI engineer? The answer depends largely on

0

HDHet Daveenconvert.hashnode.devSep 23 · 6 min read

How to build a unified ingestion layer for your RAG pipeline from scratch

Most RAG pipelines do not fail at the vector store. They do not fail at retrieval. They fail before any of that: at the point where content moves from a URL, a PDF, or a DOCX file into something a mod

2

B

HKHarshil Kumar Pindikuruharshils.hashnode.devSep 21 · 20 min read

The Culinary Architecture of Agentic AI: A Blueprint for Autonomous Systems

The Big Picture: Welcome to the AI Kitchen The world of Agentic AI can feel overwhelming. There are foundation models, embeddings, vector databases, RAG, tools, memory, orchestration frameworks, sandb

1

A

ACADEKUNLE CHRISTIANAH AYOMIDEi-am-christy.hashnode.devSep 19 · 15 min read

Understanding the Economics of Repeated Context: Prompt Caching...

In this article you'll learn: What prompt caching is and what it actually saves How it works, step by step, in plain terms How to tell whether it will save you money, with a simple formula How Ant

0

AJAlen Joypragmaticstack.inSep 17 · 5 min read

Reviewing Code Nobody Typed: Human Judgment in an Agentic Workflow

🗓️ Last updated: September 2026 A pull request arrives with thirty seven changed files, polished comments, comprehensive tests, and a description that explains the architecture with unusual confiden

4

II

#ai-engineering

Search Hashnode

#ai-engineering

Explore Hashnode

Trending tags this week

A Reference Pattern for Logging and Auditing LLM API Calls

Machine Learning Engineer vs Applied AI Engineer : The Smart Robot Analogy 🤖

How to scrape web content cleanly for LLM pipelines

Choosing the Right Rice: Understanding Foundation Models in Agentic AI

What Is a System One Model? Jev Explained

AI Engineer vs AI Consultant: Which One Does Your Business Need?

How to build a unified ingestion layer for your RAG pipeline from scratch

The Culinary Architecture of Agentic AI: A Blueprint for Autonomous Systems

Understanding the Economics of Repeated Context: Prompt Caching...

Reviewing Code Nobody Typed: Human Judgment in an Agentic Workflow